The Devin MCP connector routes your AI agent's tool calls to Devin's own MCP server through Scalekit. Each user connects their own Devin access token once, and Scalekit sends it with every call, so your agent never handles credentials. It comes with 29 tools.
- Tools
- 29
- What they doRead · write · destructive
- 1 · 28 · 01 read28 write0 destructive
- Users sign in with
- Access token
Setup
Install the SDK
Terminal window npm install @scalekit-sdk/node dotenvTerminal window pip install scalekit-sdk-python python-dotenvSet your credentials
Add your Scalekit credentials to your
.envfile. Find values in app.scalekit.com > Developers > API Credentials..env SCALEKIT_ENVIRONMENT_URL=<your-environment-url>SCALEKIT_CLIENT_ID=<your-client-id>SCALEKIT_CLIENT_SECRET=<your-client-secret>Create the Devin MCP connection
In AgentKit > Connections, create a Devin MCP connection. The name you give it is the
connection_nameyour code passes. See Configure connections.Console steps with screenshots
Register your Devin API key with Scalekit so it stores it securely and injects it into every request. Devin uses API key authentication.
-
Get your Devin API key
- Sign in to Devin and go to Settings → Devin API.
- Click the API keys (legacy) tab.
- Under Personal API key, click View key to reveal your key, or expand the dropdown to regenerate it.

-
Create a connection in Scalekit
- In Scalekit dashboard, go to AgentKit → Connections → Create Connection. Find Devin MCP and click Create.
- Note the Connection name — you will use this as
connection_namein your code (e.g.,devinmcp). - Click Save.
-
Add a connected account
Connected accounts link a specific user identifier in your system to their Devin API key. Add one in the dashboard to test. In production, each user adds their own through the authorization link: they enter their credentials on the page it opens.
In the dashboard, to test
- Open the connection you created and click the Connected Accounts tab → Add account.
- Fill in:
- Your User’s ID — a unique identifier for this user in your system (e.g.,
user_123) - API Key — the Devin API key from step 1
- Your User’s ID — a unique identifier for this user in your system (e.g.,
- Click Create Account.
From your backend, if your app already has the credentials
For example, when users enter them on a settings page in your app:
import { Scalekit, ConnectorStatus } from '@scalekit-sdk/node';const scalekit = new Scalekit(process.env.SCALEKIT_ENVIRONMENT_URL,process.env.SCALEKIT_CLIENT_ID,process.env.SCALEKIT_CLIENT_SECRET,);// Never hard-code credentials — read from secure storage or user inputconst devinApiKey = getUserDevinApiKey(); // retrieve from your secure storeconst authorizationDetails = {details: {case: 'staticAuth',value: {details: {token: devinApiKey,},},},};let { connectedAccount } = await scalekit.actions.upsertConnectedAccount({connectionName: 'devinmcp',identifier: 'user_123',authorizationDetails,});// Make sure the account is ACTIVE before the first tool call.if (connectedAccount?.status !== ConnectorStatus.ACTIVE) {({ connectedAccount } = await scalekit.actions.upsertConnectedAccount({connectionName: 'devinmcp',identifier: 'user_123',authorizationDetails,}));}import osfrom scalekit import ScalekitClientscalekit_client = ScalekitClient(env_url=os.environ["SCALEKIT_ENVIRONMENT_URL"],client_id=os.environ["SCALEKIT_CLIENT_ID"],client_secret=os.environ["SCALEKIT_CLIENT_SECRET"],)# Never hard-code credentials — read from secure storage or user inputdevin_api_key = get_user_devin_api_key() # retrieve from your secure storeauthorization_details = {"static_auth": {"token": devin_api_key}}response = scalekit_client.actions.upsert_connected_account(connection_name="devinmcp",identifier="user_123",authorization_details=authorization_details,)# Make sure the account is ACTIVE before the first tool call.if response.connected_account.status != "ACTIVE":response = scalekit_client.actions.upsert_connected_account(connection_name="devinmcp",identifier="user_123",authorization_details=authorization_details,)
-
Authorize a user and make your first call
quickstart.mts import { ScalekitClient } from '@scalekit-sdk/node'import 'dotenv/config'import { createInterface } from 'node:readline/promises'const scalekit = new ScalekitClient(process.env.SCALEKIT_ENVIRONMENT_URL,process.env.SCALEKIT_CLIENT_ID,process.env.SCALEKIT_CLIENT_SECRET,)const actions = scalekit.actionsconst connector = 'devinmcp'const identifier = 'user_123'// Generate an authorization link for the userconst { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })console.log('Authorize Devin MCP:', link)const rl = createInterface({ input: process.stdin, output: process.stdout })await rl.question('Press Enter after authorizing...')rl.close()// Make your first callconst result = await actions.executeTool({connector,identifier,toolName: 'devinmcp_list_wiki_repos',toolInput: {},})console.log(result)Terminal window npx tsx quickstart.mtsquickstart.py import osfrom scalekit import ScalekitClientfrom dotenv import load_dotenvload_dotenv()scalekit_client = ScalekitClient(env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),client_id=os.getenv("SCALEKIT_CLIENT_ID"),client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),)actions = scalekit_client.actionsconnection_name = "devinmcp"identifier = "user_123"# Generate an authorization link for the userlink_response = actions.get_authorization_link(connection_name=connection_name,identifier=identifier,)print("Authorize Devin MCP:", link_response.link)input("Press Enter after authorizing...")# Make your first callresult = actions.execute_tool(tool_input={},tool_name="devinmcp_list_wiki_repos",connection_name=connection_name,identifier=identifier,)print(result)Terminal window python quickstart.pyEach user opens the link once and enters their Devin MCP server credentials there. If your app already has a user's credentials, add the account from your backend instead, as the console steps above show. See Authorize a user for the full flow and statuses.
Tools
Pass the exact name toexecute_tooldevinmcp_list_wiki_reposList the repositories that have a DeepWiki index, i.e.Read-onlyList Wiki Repos
List the repositories that have a DeepWiki index, i.e. the ones that ask_wiki_question and read_wiki_* can answer about. This is not the set of repositories you have access to: repositories without a generated wiki are omitted.
Inputs
This tool takes no inputs.
devinmcp_ask_wiki_questionAsk any question about a GitHub repository's codebase and get an AI-powered answer grounded in its DeepWiki.WriteAsk Wiki Question
Ask any question about a GitHub repository's codebase and get an AI-powered answer grounded in its DeepWiki.
Inputs
questionstringrequired- The question to ask about the repository.
repoNamestringrequired- GitHub repository or list of repositories (max 10) in owner/repo format.
devinmcp_devin_automation_manageManage Devin automations that run Devin in response to events (GitHub, Slack, Linear, schedules, webhooks) — list, get, create, update, delete, or run them.WriteDevin Automation Manage
Manage Devin automations that run Devin in response to events (GitHub, Slack, Linear, schedules, webhooks) — list, get, create, update, delete, or run them.
Inputs
actionstringrequired- Call 'schemas' before building or changing an automation. 'validate_*' dry-run without approval. 'run' fires now and bypasses trigger conditions. 'script_check_*' work only when 'schemas' reports Preflight available.one of
listgetschemastemplatescreatevalidate_createupdatevalidate_updateset_avatardeleterunrun_grantscript_check_getscript_check_samplesscript_check_eventsscript_check_eventscript_check_testscript_check_run actionsarray- Required for 'create'; replaces all actions on 'update'. Shape in action='schemas'; workflow in the managing-automations skill, if available.
afterstring- Cursor from a previous page's end_cursor.
agent_typesstring- Filter 'list': new_session, long_running, triage_session, auto_triage, code_scan, remediate_finding, incident_session.
attachment_urlstring- For set_avatar: the image URL returned by upload_attachment. Sets only your own bot's public avatar.
automation_idstring- Target automation (`auto-<uuid>` or a bare UUID). Omit for 'list', 'schemas', 'templates', 'create', and draft script checks.
backgroundstring- For set_avatar: background color (black, brown, red, orange, yellow, green, teal, blue, purple, pink, gray, rose, magenta, indigo, azure, emerald, tan, amber, tangerine, vermilion, silver, charcoal) or transparent. Omit attachment_url to change only the current custom image's background.
concurrencyobject- No description.
creator_idstring- Filter 'list' by creator user id.
descriptionstring- 'create' only: one sentence of at most 70 characters, starting with a verb, saying what it does and where the result goes, not when it runs. Shown on the approval card; not saved.
enabledstring- Sets the state on 'create'/'update'; filters on 'list'.
event_datastring- 'run' only: structured stand-in for the event.
event_typestring- Filter 'list' by trigger event type; required for 'run_grant'.
eventsstring- 'run' only: up to 50 source records, one run each.
firststring- Page size for 'list' (default 100) and 'script_check_events' (default 20); max 200.
grant_idstring- 'run' with events: from 'run_grant'.
limitsobject- No description.
llm_checkobject- LLM check.
metadatastring- String labels; filters on 'list'.
namestring- 1-500 characters. Required for 'create' and 'validate_create'.
notificationsobject- No description.
promptstring- 'run' only: free-text stand-in for the event (max 10000 chars).
queued_event_idstring- For 'script_check_event' and 'script_check_test'; from 'script_check_events'.
reasonstring- 'update' and 'delete' only: one sentence of at most 100 characters saying why. Shown on the approval card; not saved.
report_required_permissionsboolean- Set by the pre-approval hook; not needed by hand.default
false run_asobject- Required for 'create'.
run_idstring- For 'script_check_run': from 'script_check_test'.
sample_event_typestring- For 'script_check_samples' and 'script_check_test'.
sample_webhook_bodystring- For 'script_check_test' on 'webhook:incoming': the JSON body the webhook will receive.
script_checkobject- Preflight check script.
searchstring- Filter 'list' by name substring.
security_profilestring- No description.
session_settingsobject- No description.
template_idstring- 'create' only: a template_id from action='templates'.
toolsobject- Tool grants for spawned sessions.
triggersarray- Required for 'create'; replaces all triggers on 'update'. Shape in action='schemas'; workflow in the managing-automations skill, if available.
ttl_secondsstring- 'run_grant' only: grant lifetime in seconds (default 3600, max 86400).
devinmcp_devin_billing_tag_manageManage Devin billing tags (groupings of Devin sessions for usage tracking) with a single action-based tool: list/get/create tags, assign sessions one at a time or in bulk (up to 500 per call, sent in sequential batches of 100), and read the billing tags of up to 100 sessions at once ('get_session_tags').WriteDevin Billing Tag Manage
Manage Devin billing tags (groupings of Devin sessions for usage tracking) with a single action-based tool: list/get/create tags, assign sessions one at a time or in bulk (up to 500 per call, sent in sequential batches of 100), and read the billing tags of up to 100 sessions at once ('get_session_tags'). Only available in private mode (via devin.ai endpoints).
Inputs
actionstringrequired- Operation to perform: 'list', 'get', 'create', 'assign_session', 'assign_sessions', or 'get_session_tags'.one of
listgetcreateassign_sessionassign_sessionsget_session_tags afterstring- Opaque cursor for 'list' pagination (from a previous response's end_cursor).
assignmentsstring- Map of Devin session ID -> billing tag ID (1-500 entries). Required for 'assign_sessions'. A null value marks the session as miscellaneous (no billing tag). Assignments are sent to the API in sequential batches of 100. Partial success: sessions or tags not found in the organization, or sessions you can't write, are reported per entry.
billing_tag_idstring- Billing tag id. Required for 'get'. For 'assign_session', the tag to assign; omit it to mark the session as miscellaneous (no tag).
descriptionstring- Free-form description of what work the tag covers. Optional for 'create'.
devin_idstring- ID of the Devin session to assign. Required for 'assign_session'. Assigning replaces the session's current billing tag.
firststring- Page size for 'list' pagination (default 100, max 200).
namestring- Billing tag display name. Required for 'create'.
session_idsstring- Session ids to look up billing tags for, at most 100. Required for 'get_session_tags'. Both 'devin-abc123' and 'abc123' are accepted. Each session comes back with its billing tag, as having no billing tag when it was categorized as Miscellaneous or its tag was deleted, as never categorized, or as not found.
devinmcp_devin_blueprint_testTest a candidate blueprint YAML in an authoring VM: start â run initialize â fix â run initialize again (clean VM) â run maintenance â then persist with update_environment_config.WriteDevin Blueprint Test
Test a candidate blueprint YAML in an authoring VM: start â run initialize â fix â run initialize again (clean VM) â run maintenance â then persist with update_environment_config.
Inputs
actionstringrequired- Operation: start, run, get, cancel, or close.one of
startrungetcancelclose afterinteger- Log cursor for get.default
0 author_session_idstring- Author session ID for run, get, cancel, and close.
namestring- Knowledge command name, when target is knowledge.
platformstring- Authoring VM platform label.default
default platformsstring- Platform labels matching YAML "runs-on" values; use "default" for the default platform. Defaults to [platform].
poll_interval_secondsinteger- Seconds between run polls; capped so keepalives keep flowing.default
5 repo_namestring- Repository name used to create or set the session working directory.
run_idstring- Run ID for get and cancel.
scopestring- Optional repository scope for the run working directory.
targetstring- Blueprint target: initialize, maintenance, or knowledge.
wait_timeout_secondsinteger- Maximum time to wait for a run. Capped below the 15-minute approval window; use `get` to keep following a longer run.default
600 yamlstring- Candidate blueprint YAML for a run.
devinmcp_devin_campaign_manageRead and publish a bot's campaign: its plan, its append-only readings and its status.WriteDevin Campaign Manage
Read and publish a bot's campaign: its plan, its append-only readings and its status. Access follows the bot: a personal bot's owner and the bot's own sessions, or any org member for a multiplayer bot; org admins may read a personal bot's campaign. A Devin session may publish drafts, readings and status, but never approve the plan: send plan.approved exactly as stored (a person approves in the campaign panel). 'running' requires an approved plan. The first update creates the campaign.
Inputs
actionstringrequired- 'get' reads the campaign; 'update' publishes the given fields; 'validate' runs every check 'update' makes without saving.one of
getupdatevalidate automation_idstring- The bot's root automation (auto-<id>), resolved to its bot. A campaign Devin passes its own session automation id here. Pass this or bot_id.
bot_idstring- The bot (bot-<id>) whose campaign to read or publish. Pass this or automation_id.
campaignstring- For update/validate: the complete plan and/or complete latest_readings document, plus an optional status. Omitted fields stay unchanged. Parse local YAML into JSON first.
devinmcp_devin_code_scan_manageManage Devin code scans and scan profiles — list scans and findings, manage profiles, create scans, or remediate findings.WriteDevin Code Scan Manage
Manage Devin code scans and scan profiles — list scans and findings, manage profiles, create scans, or remediate findings.
Inputs
actionstringrequired- The operation to perform. Per-action rules are in the tool description and the creating-code-scans skill. A 409 means the scan's state does not allow it.one of
list_scansget_scanlist_findingslist_threatslist_scan_typeslist_profilesget_profilecreate_profileupdate_profilecreate_scancreate_bulk_scanget_bulk_scanupdate_scanscan_new_commitsrecover_scancancel_scancreate_auto_scandelete_auto_scanupdate_finding_statusupdate_finding_contentget_sessionremediate_findingremediate_findingsunlink_finding_session afterstring- Opaque cursor for list pagination (from a previous response's end_cursor). 'get_bulk_scan': the repository name the previous page says to continue after.
attachment_urlsstring- Devin attachment URLs for 'create_scan' (at most 10), e.g. findings for an ingest scan.
batch_idstring- Required for 'get_bulk_scan': the batch ID returned by 'create_bulk_scan'.
board_idstring- 'create_scan': finding board named by the setup. Never invent one.
branchstring- Base branch for remediation pull requests; omit to use the repository default branch.
commit_shastring- Commit to scan first ('create_scan', single repository); omit for the default branch.
communication_guidancestring- What happens when the scan finishes ('create_profile', 'update_profile'); discover scans only.
descriptionstring- Description of the profile ('create_profile' and 'update_profile'), or the finding's new description ('update_finding_content').
dismissal_notestring- Dismissal note for 'update_finding_status'; stored only when dismissed.
dismissal_reasonstring- 'update_finding_status' when dismissed: 'false_positive', 'mitigated', 'accepted_risk', 'duplicate', 'not_actionable'.
dry_runboolean- 'create_bulk_scan': list the repositories it would scan without starting anything.default
false effortstring- 'normal' or 'deep' ('create_scan', 'create_bulk_scan', 'create_auto_scan'). Only security scans offer the choice. Describe it by time and thoroughness, never cost.
enabledboolean- Whether the 'create_auto_scan' schedule starts enabled (default true).default
true exclude_globsstring- Glob patterns of files to exclude from scans ('create_profile' and 'update_profile').
filter_namestring- 'create_bulk_scan' with dry_run=true: list the repositories whose name contains this text. Start the scans with the approved names in repos.
finding_idstring- The finding ID for 'remediate_finding', 'update_finding_status' or 'unlink_finding_session'.
finding_idsstring- Findings of scan_id for 'remediate_findings', 'update_finding_status' or 'unlink_finding_session' (1-1000).
firststring- Page size for list actions (default 100, max 200).
fix_effortstring- The finding's new fix effort ('update_finding_content').
hoststring- Git host of the repository/repositories ('create_scan' only).
impactstring- The finding's new impact ('update_finding_content').
include_globsstring- Glob patterns of files to include in scans ('create_profile' and 'update_profile').
ingestion_source_guidancestring- Guidance describing the ingestion source ('create_profile' and 'update_profile').
interactivestring- 'create_scan', security scans only: true pauses for the user to review the threat model; false (default) runs unattended.
investigation_guidancestring- Guidance for the investigation phase ('create_profile' and 'update_profile').
localestring- BCP-47 tag of the user's language ('create_scan', 'create_bulk_scan'). Pass it when they are not writing in English.
modestring- Profile mode: 'discover' (default) or 'ingest' ('create_profile' only; the mode is fixed at creation).
notestring- The finding's new note; empty clears it ('update_finding_content').
ownersstring- The finding's code owners; empty clears them ('update_finding_content').
post_ingestion_guidancestring- Guidance for the post-ingestion phase ('create_profile' and 'update_profile').
profile_idstring- Required for 'get_profile', 'update_profile', 'update_scan'; optional for 'create_scan', 'create_bulk_scan'. Required for non-security scans.
profile_namestring- Name of the profile. Required for 'create_profile'; optional new name for 'update_profile'.
querystring- Text search: over finding title, description, and file path ('list_findings', combines with repo_name and other filters), or over a threat's id, title, description and tags, such as a CVE id or package name ('list_threats').
recommendationstring- The finding's new recommendation; empty clears it ('update_finding_content').
related_finding_idsstring- The finding's related finding IDs; empty clears them ('update_finding_content').
remediation_guidancestring- Guidance for the remediation phase ('create_profile' and 'update_profile').
repo_namestring- Repository filter, or the repository to scan ('create_scan'; exactly one of repo_name or repos).
report_guidancestring- Guidance for the report phase ('create_profile' and 'update_profile').
reposstring- 'create_scan': repositories to scan together (exactly one of repo_name or repos). 'create_bulk_scan': repositories to scan separately, one scan each (at most 1000; repos or filter_name).
resolution_notestring- Resolution note for 'update_finding_status'; stored only when resolved.
rrulestring- Required for 'create_auto_scan': iCal RRULE driving the recurring schedule for scanning new commits, e.g. 'FREQ=DAILY'.
scan_idstring- The scan the action applies to.
scan_pathsstring- Repository-relative paths to restrict scans to ('create_profile', 'update_profile'); [] lifts it.
scan_typestring- Scan type from 'list_scan_types' ('create_scan', 'create_bulk_scan', 'create_profile', 'update_profile', 'list_profiles', 'list_scans'). Must match the profile's type.
select_allboolean- 'remediate_findings' instead of finding_ids: every open finding of scan_id, narrowed by severity and repo_name. Fails above 1000.default
false severitystring- Filter findings to these severities: 'critical', 'high', 'medium', 'low' ('list_findings', and 'remediate_findings' with select_all), or the finding's new severity ('update_finding_content').
statusstring- Filter for 'list_findings', or the new status for 'update_finding_status': 'open', 'dismissed', 'resolved'.
strategystring- Scan strategy ('create_scan' only): 'agentic_map_reduce' (default) or 'exploit' (security scans only). Non-default strategies are staging/dev-only.
summarystring- One-sentence, user-facing description of the proposed change, shown on the approval card when 'update_profile' targets a 'security' profile.
threat_model_guidancestring- Guidance describing the threat model ('create_profile' and 'update_profile').
time_afterstring- Unix seconds lower bound. Optional creation-time filter ('list_scans' only).
time_beforestring- Unix seconds upper bound. Optional creation-time filter ('list_scans' only).
titlestring- The finding's new title ('update_finding_content').
triage_guidancestring- Guidance for the triage phase ('create_profile' and 'update_profile').
type_configstring- Compliance profiles only: {'system', 'framework', 'criteria'}. Copy 'system.guidance' unchanged. See the creating-code-scans skill.
validation_guidancestring- Guidance for the validation phase ('create_profile' and 'update_profile').
validation_severitiesstring- Severities runtime validation covers ('create_profile', 'update_profile'; security profiles only).
devinmcp_devin_find_settingFind a Devin webapp setting and get a deep-link URL to it.WriteDevin Find Setting
Find a Devin webapp setting and get a deep-link URL to it. Use for "where do I change X?". The output includes everything needed to build the final URL.
Inputs
querystring- Feature keywords (e.g. "queue messages", "fast mode"). Omit for the full settings catalog.
devinmcp_devin_knowledge_manageManage Devin knowledge notes and suggestions — list, get, create, or update entries.WriteDevin Knowledge Manage
Manage Devin knowledge notes and suggestions — list, get, create, or update entries.
Inputs
actionstringrequired- No description.one of
listgetcreateupdatedeletefolderslist_suggestionsview_suggestiondismiss_suggestions afterstring- No description.
bodystring- No description.
contentstring- No description.
event_idstring- No description.
event_idsstring- No description.
firststring- No description.
folder_pathstring- No description.
limitstring- No description.
namestring- No description.
note_idstring- No description.
offsetstring- No description.
pinned_repostring- No description.
querystring- No description.
searchstring- No description.
since_daysstring- No description.
statusstring- No description.
triggerstring- No description.
devinmcp_devin_list_integrationsList native integrations and MCP servers for the organization, with status and settings/install URLs.WriteDevin List Integrations
List native integrations and MCP servers for the organization, with status and settings/install URLs. Returns a JSON object with two arrays: "integrations" (native integrations like GitHub, Jira, Slack) and "mcp_servers" (marketplace MCP servers). Each entry includes whether it's installed and a path-only URL to the settings/setup page (no host, works with custom enterprise domains). Pass `query` to look up a specific server by name â an empty "mcp_servers" array then means it is not in the marketplace (install it as a custom server with devin_mcp_server_manage instead).
Inputs
filterstring- Filter results â 'all' (default), 'installed', or 'not_installed'.one of
allinstallednot_installeddefaultall querystring- Case-insensitive substring matched against name, slug, and description. Use it whenever you are looking for one specific integration or MCP server (e.g. query='whimsical'); the unfiltered catalog is large.
devinmcp_devin_mcp_server_manageManage MCP server installations for the organization: install (from the marketplace or custom), update, delete, enable, or disable.WriteDevin Mcp Server Manage
Manage MCP server installations for the organization: install (from the marketplace or custom), update, delete, enable, or disable. To connect a server, call install with marketplace_server_slug set to its name or slug as the first and only step: the name is resolved against the marketplace catalog in-tool, so there is no skill for this and no need to call devin_list_integrations, grep the repo, or web-search first. Only if the result says the server is not in the marketplace, look up the provider's official remote MCP endpoint and authentication method and install it as a custom server. For an API key, use request_secret first, then pass only its name: as auth_header_secret_name for HTTP servers, or in env_secret_names for STDIO servers. Never ask the user to paste a secret into normal session text. The pre-approval check rejects OAuth when automatic registration cannot complete. Install, update, and delete show the approval card unless the call is pre-approved; that card is the approval prompt, so do not send a separate "please approve" message. Only available in private mode.
Inputs
actionstringrequired- Operation to perform. 'resolve_install' is read-only: it resolves a marketplace server or validates a custom server before the approval card.one of
installresolve_installupdatedeleteenabledisable auth_header_formatstring- How to format auth_header_secret_name: 'bearer' creates 'Bearer ${SECRET_NAME}'; 'raw' creates '${SECRET_NAME}'. Defaults to 'bearer'.
auth_header_keystring- Header name for custom auth_header installs. Defaults to Authorization.
auth_header_secret_namestring- Protected Brain secret name for a custom auth_header install. First use request_secret and tell the user never to paste the value into normal session text. Pass only the name here; the credential value is never included in the install card. The name must start with MCP_ to limit access to MCP-specific secrets. For an org installation, use an org-scoped saved secret. A temporary secret works only in the current session.
auth_methodstring- 'none', 'auth_header', or 'oauth'. Before a custom install, research the provider's official documentation and select a supported method. Never put a credential value in this tool call.
commandstring- Command line to run, e.g. '/home/ubuntu/.fly/bin/flyctl mcp server'. Required for STDIO transport on a custom 'install'. The process starts from a login shell with only the env below plus the session's default environment, so use an absolute executable path.
descriptionstring- Longer description. Optional.
env_secret_namesstring- Environment variables for a custom STDIO server, as env var name -> protected Brain secret name (e.g. {'FLY_API_TOKEN': 'MCP_FLY_API_TOKEN'}). The value is never in the tool call: first use request_secret with a name that starts with MCP_, then pass only that name here. Each variable expands to that secret when the server starts.
iconstring- Icon URL for the approval card. Set automatically; do not set it.
installation_idstring- Installation id. Required for 'update', 'delete', 'enable', and 'disable'. Find it with devin_list_integrations.
installation_scopestring- Optional override: 'org' (Organization) shares one credential org-wide; 'user' (Personal) has each member connect their own account. Omit unless the user requests a scope; the marketplace default (or 'org') applies. Only for install. Change an existing scope in Settings.
marketplace_server_slugstring- For 'install': the marketplace server's slug or exact name (e.g. 'notion' or 'Notion'); no prior devin_list_integrations call is needed. Transport, command, and auth come from the marketplace manifest and cannot be overridden; url may only select a variant the manifest allows. Omit to install a custom server.
namestring- Display name. Required for a custom 'install'.
oauth_client_idstring- Pre-registered OAuth client ID for a custom install. Client IDs are identifiers, not secret values. If the provider also requires a client secret, configure that secret in Settings instead of putting it in session text.
oauth_resourcestring- OAuth resource indicator. Custom installs only.
oauth_scopestring- OAuth scope. Custom installs only.
shared_installation_idstring- Set by the approval card when the user shares a connection they already have instead of installing a new one; do not set it.
short_descriptionstring- One-line description. Required for a custom 'install'.
slugstring- URL-safe identifier for the installation. Required for a custom 'install'.
transportstring- 'HTTP', 'SSE', or 'STDIO'. Required for a custom 'install'.
urlstring- Server URL. Required for HTTP/SSE transport on a custom 'install'. On a marketplace 'install', only to select a URL variant (e.g. a region): it must keep the scheme and host of one of the manifest's URLs; omit it for the default.
devinmcp_devin_oncall_manageView a Devin Oncall report's current responder membership, or a responder's open issues.WriteDevin Oncall Manage
View a Devin Oncall report's current responder membership, or a responder's open issues.
Inputs
actionstringrequired- Operation on 'resource': list, get, create, validate_create, update, validate_update, delete, issues, trigger, trigger_grant, stop, resume, runs, run. Without a resource: 'schemas' or 'ingest_dashboard'.one of
listgetcreatevalidate_createupdatevalidate_updatedeleteissuestriggertrigger_grantstopresumerunsrunschemasingest_dashboardscript_check_getscript_check_samplesscript_check_eventsscript_check_eventscript_check_testscript_check_runreport_contextresponder_issuesreport_statsdigest_runsincident_candidatessubmit_report_run afterstring- Opaque cursor for list/issues/runs pagination (from a previous response).
auto_join_enabledstring- incident_settings: whether Devin auto-joins new public channels matching the prefix (default true â keep it on unless the user wants to invite Devin manually).
dashboardstring- 'ingest_dashboard': reference to the dashboard to ingest â a URL, id, or name.
destination_org_idstring- enterprise_incident_settings, slack source: the one org every incident lands in (must have finished Oncall onboarding and have incidents enabled). '' clears.
enabledstring- Responder: whether it triages new messages (default true). incident_settings: whether the incident feature is on for the org.
event_typestring- Responder 'trigger' and 'trigger_grant' (required): the event type of every item in 'events'.
eventsstring- Responder 'trigger' (required): up to 50 source events. Shape and rules in action='schemas'.
firststring- Page size for list/issues/runs (default 100, max 200).
grant_idstring- Responder 'trigger': the grant_id from 'trigger_grant' for this responder and event_type.
incident_idstring- Incident id for incident get/stop/resume.
incident_idsstring- Report 'runs': incidents classified into this period. Supplying it (even []) submits a run.
incident_session_settingsobject- incident_settings session overrides. Shape in action='schemas'.
incident_sourcestring- Who announces incidents: 'slack' or 'pagerduty'; '' clears. Details in action='schemas'.
incidents_matchstring- Report create/update: which incidents belong in this report, in plain language; '' clears on update.
limitsobject- Responder limits. Omit unless the user asks. Shape in action='schemas'.
metadatastring- Responder labels. Only set when the user asks. A null value deletes the key.
multi_org_enabledstring- enterprise_incident_settings: let incidents run in several orgs of the enterprise.
namestring- Display name for responder/report create (required) or update.
notificationsobject- Report create only: Slack or Teams delivery. Never invent an ID. Shape in action='schemas'.
order_bystring- Responder 'issues' ordering: 'last_activity' (default) or 'occurrence_count'.
pagerduty_connection_idstring- PagerDuty responders only: read it from action='schemas'.
queued_event_idstring- Responder 'script_check_event' and 'script_check_test': an id from 'script_check_events'. Excludes sample_event_type.
reportstring- Report 'runs' POST: the full report body in markdown.
report_idstring- Report id for report actions, or a filter for incident list.
resourcestring- What to operate on. Omit only for 'schemas' and 'ingest_dashboard'.
responder_automation_idsstring- Report create/update: fixed responder ids. Excludes responder_tags; replaces the list on update.
responder_idstring- Responder id for responder get/update/validate_update/delete/issues.
responder_tagsstring- Report create/update: members whose metadata matches all these key/values.
response_modestring- incident_settings: 'proactive' or 'one_shot_rca'; '' clears.
reveal_secretboolean- Webhook responder create/update: include the one-time secret in the result. Only when the user explicitly wants it here.default
false routing_rulesarray- enterprise_incident_settings, pagerduty source: ordered rules; replaces the list. Shape in action='schemas'.
run_asobject- Identity spawned sessions run as; defaults to the organization. Shape in action='schemas'.
run_idstring- Report run id for report 'run'.
runbookstring- Responder or org incident instructions. Omit unless the user asks; '' resets on update.
sample_event_typestring- Responder 'script_check_samples' and 'script_check_test': the sample trigger type. Excludes queued_event_id.
sample_webhook_bodystring- Responder 'script_check_test' with 'webhook:incoming': the JSON body to test with, at most 64KB.
script_checkobject- Preflight check group, only when 'schemas' reports script_check_available. Shape in action='schemas'.
script_check_run_idstring- Responder 'script_check_run': the run_id returned by 'script_check_test'.
sessionobject- Session tags for spawned sessions, when the org requires them. Shape in action='schemas'.
session_settingsobject- Responder devin_mode and net_policy. Preserve on update unless asked. Shape in action='schemas'.
slack_channel_prefixstring- incident_settings: prefix for auto-created incident channels (server default 'inc-'). Pass '' on update to clear the stored prefix.
slack_team_idstring- incident_settings: Slack workspace ID incidents are watched in (omit for one workspace). Pass '' on update to clear the stored workspace.
summarystring- Report 'runs' POST: at-most-2-sentence overview of the period vs the previous run.
team_idstring- Slack workspace (team) ID for the responder's channel; omit when the org has one workspace.
toolsobject- Tool grants for spawned sessions. Shape in action='schemas'.
triage_issue_typestring- Required on responder create: 'alerts' or 'bugs'. Fixed after create.
triggersarray- Responder create (required)/update. Shape and rules in action='schemas'. Never invent channel IDs.
ttl_secondsstring- Responder 'trigger_grant': how long the grant stays valid, in seconds (default 3600, at most 86400). Choose the time the backfill loop needs.
typestring- 'ingest_dashboard': dashboard source, 'datadog' (default) or 'newrelic'.
unmatched_org_idstring- enterprise_incident_settings, pagerduty source: org for incidents no rule matches; omit/'' = no incident for them.
devinmcp_devin_playbook_manageManage Devin playbooks — list, get, create, or update playbook entries.WriteDevin Playbook Manage
Manage Devin playbooks — list, get, create, or update playbook entries.
Inputs
actionstringrequired- No description.one of
listgetcreateupdatedelete afterstring- No description.
bodystring- No description.
contentstring- No description.
firststring- No description.
macrostring- No description.
playbook_idstring- No description.
structured_output_schemastring- No description.
titlestring- No description.
devinmcp_devin_review_manageTrigger a Devin Review for a pull/merge request, or fetch its latest review status.WriteDevin Review Manage
Trigger a Devin Review for a pull/merge request, or fetch its latest review status.
Inputs
actionstringrequired- 'trigger' starts a Devin Review for the PR; 'get_status' fetches the latest review status for the PR; 'get_findings' fetches the findings of a completed review. By default, only the severities the org delivers to sessions are returned; the rest remain available on the Devin Review page and can be fetched by passing the severity explicitly. 'report_triage' reports what you did about each finding of a review in a single call; findings marked needs_human are then posted on the PR (code_quality findings are counted in the PR status comment and stay on the Devin Review page). Call it only when the review's findings notification asked you to report triage; other reviews already post their findings on the PR.one of
triggerget_statusget_findingsreport_triage pr_urlstringrequired- Full URL of the pull/merge request (e.g. 'https://github.com/owner/repo/pull/123').
commit_shastring- get_status/get_findings: commit SHA to look up (full or short prefix). Defaults to the PR's current head commit. report_triage: required; the commit the findings were reported for.
decisionsstring- report_triage only: one decision for every finding of the review.
severitystring- get_findings only: filter findings to one severity ('bug', 'security', 'flag', 'info', 'code_quality', or 'reviewer'). Bug means a concrete correctness, regression, or repo-rule violation; security means a vulnerability or hardening gap; flag means something needing further investigation that may or may not be a bug; info means an informational note; code_quality means a maintainability or readability issue; reviewer means a finding raised by one of the account's custom reviewers. Omit to return only the severities the org delivers to sessions; the remaining severities stay available on the Devin Review page and can be fetched by passing the severity explicitly.
devinmcp_devin_schedule_manageManage scheduled Devin sessions — list, get, create, update, or delete schedules.WriteDevin Schedule Manage
Manage scheduled Devin sessions — list, get, create, update, or delete schedules.
Inputs
actionstringrequired- The operation to perform: 'list', 'get', 'create', 'update', or 'delete'.one of
listgetcreateupdatedelete agentstring- Which agent to run: 'devin', 'data_analyst', or 'advanced'.
bypass_approvalstring- Skip MCP tool permission checks for created sessions.
enabledstring- Enable or disable the schedule (used with 'update').
frequencystring- Cron expression (e.g. '0 9 * * 1-5'). Required for 'create' with recurring schedules.
limitstring- Max number of results for 'list' (capped at 100).
namestring- Human-readable name for the schedule. Required for 'create'.
notify_onstring- When to send notifications: 'always', 'failure', or 'never'.
offsetstring- Pagination offset for 'list'.
platformstring- VM platform for sessions spawned by this schedule (e.g. 'windows'). When omitted, sessions fall back to the org's default platform at trigger time. Must match a platform configured for the organization (case-insensitive); unknown values are rejected with a 400 that lists the available platform labels.
playbook_idstring- Optional playbook to attach to the scheduled session.
promptstring- The prompt Devin will run on each trigger. Required for 'create'.
schedule_idstring- The schedule ID. Required for 'get', 'update', and 'delete'.
schedule_typestring- 'recurring' (default) or 'one_time'.
scheduled_atstring- ISO 8601 datetime to run at. Required for 'create' with one_time schedules.
tagsstring- Session tags (cost codes) for sessions this schedule spawns. Orgs that require session tags need exactly one tag from their allowed list. On update, omit to keep or pass [] to clear.
target_devin_idstring- Devin session ID to send the prompt to instead of starting a new session. Only valid for one_time schedules. Use this to schedule a message to be sent to an existing session at a future time (e.g. to wake yourself up later).
devinmcp_devin_session_createCreate one or more child Devin sessions via the REST API.WriteDevin Session Create
Create one or more child Devin sessions via the REST API.
Inputs
sessionsarrayrequired- Array of session specs; only 'prompt' is required in each.
board_ticket_idsstring- Devin Boards ticket ids (from devin_ticket_manage) that ALL created sessions are dispatched to work on. Each session spec can also include a 'board_ticket_ids' key to override this value for that session. The server validates the ids against the org, persists them on the child and tags it 'board'. Each ticket is checked before the session is created (the create fails if a ticket is already claimed or has unfinished prerequisites) and then claimed for the new session. If another session claims a ticket in between, the create still succeeds without that claim and the session tries to claim it on its first turn.
devin_modestring- Devin agent mode for ALL created sessions, by the id of an option in the user's agent picker. Picker names â ids: 'Normal' = 'normal', 'Fast' = 'fast', 'Fusion' = 'fusion', 'Lite' = 'lite', 'Ultra' = 'ultra', 'SWE-2 Medium' = 'swe-2-medium', 'SWE-2 High' = 'swe-2-high', 'SWE-2 Max' = 'swe-2-max'. Always refer to modes by picker name when talking to the user, never by id. Batch-level only â a 'devin_mode' key inside a session spec is rejected with guidance to move it to this batch-level field. When omitted, children run on the parent session's agent. Gated like the picker (feature flags and enterprise agent-mode policies); a 400 lists the modes available to this user.
platformstring- Prefer leaving this unset. When omitted (or set to 'inherit'), the child inherits the parent session's placement â its VM platform AND its outpost (BYOB) pool â so a Windows session spawns Windows children, and a session running on an outpost pool spawns children on the same pool, by default. Only set this when the user explicitly asks for a different machine type or a specific outpost pool: pass a platform label (e.g. 'linux', 'windows') or the name of an outpost pool. Each session spec can also include a 'platform' key to override this value for that session. Any value must match either a platform label or an outpost pool name registered for the org (built-in platforms take priority when a name matches both).
reposstring- List of repository identifiers in 'owner/repo' format (e.g. ['myorg/myrepo']) to restrict ALL created sessions to. Each session spec can also include a 'repos' key to override this value for that session.
structured_output_schemastring- JSON Schema (Draft 7) applied to ALL sessions that don't specify their own. Only pass this when you need a task-specific result from the child; without it no structured output is requested. The child reports output conforming to the schema via provide_structured_output. Don't poll for it: set notify_on_response=true on each spec in sessions, and when notified that the child settled, read structured_output once via devin_session_interact(action='get'). If it is absent, handle the settled child as you would any other (check status_detail and its latest messages) instead of polling.
tagsstring- Tags to apply to ALL created sessions (e.g. a shared run or campaign identifier). Each session spec can also include a 'tags' key to override this value for that session.
devinmcp_devin_session_eventsInspect events within a Devin session — list summaries, fetch full details, or search.WriteDevin Session Events
Inspect events within a Devin session — list summaries, fetch full details, or search.
Inputs
actionstringrequired- No description.one of
listdetailssearch session_idstringrequired- No description.
afterstring- No description.
categoriesstring- No description.
created_afterstring- No description.
created_beforestring- No description.
directionstring- No description.
event_idsstring- No description.
event_typesstring- No description.
firststring- No description.
limitstring- No description.
max_content_lengthstring- No description.
offsetstring- No description.
querystring- No description.
devinmcp_devin_session_folder_manageOrganize the sidebar session folders of the user who approves the call.WriteDevin Session Folder Manage
Organize the sidebar session folders of the user who approves the call. Every action, 'list' included, shows the user an approval card and then runs as them on their own sidebar, so batch the work: one 'move' takes many sessions, and the user's folders are listed after each change. 'delete' removes the folder and takes its sessions out of it; the sessions themselves are untouched. Only available to the sessions of a bot, in private mode (via devin.ai endpoints).
Inputs
actionstringrequired- Operation to perform: list, move, remove, create, rename, reorder, reorder_sessions, set_icon, delete.one of
listmoveremovecreaterenamereorderreorder_sessionsset_icondelete folderstring- Folder name. Required for 'move' (created if missing), 'create', 'rename' (the current name), 'reorder_sessions', 'set_icon' and 'delete'. 'pinned' is the sidebar's pin list. 'Done' and 'Recent' are not folders (see below) and are only valid as a 'move' target.
folder_namesstring- The folders in their new sidebar order, top first. Required for 'reorder'; folders left out keep their relative order after the ones named.
icon_idstring- Icon shown beside the folder's name in the sidebar, one of the curated set: automation, code, security, oncall, slack, github, linear, ticket, user, robot, bug, rocket, document, magnifying-glass, flask, server, palette, speedometer, blocked, hourglass, globe, warning, question, lightbulb, banknote, lock, link, folder, database, cloud, flag, star, bookmark. Required for 'set_icon' (an empty string clears the icon); optional on 'create' and 'move' to icon the folder in the same call.
new_namestring- The folder's new name. Required for 'rename'.
session_idsstring- Sessions to act on, at most 100; 'devin-abc123' and 'abc123' are both accepted. Required for 'move' (into `folder`; a session is in at most one folder, so this also takes it out of its current one), 'remove' (out of whatever folder each is in) and 'reorder_sessions' (the sessions of `folder` in their new order, top first; sessions left out follow in the default order).
devinmcp_devin_session_gatherWait for multiple Devin sessions to reach a settled state before returning.WriteDevin Session Gather
Wait for multiple Devin sessions to reach a settled state before returning.
Inputs
session_idsarrayrequired- No description.
poll_interval_secondsinteger- No description.default
30 timeout_secondsinteger- No description.default
300
devinmcp_devin_session_insightsPer-session cost, message counts and AI-generated analysis (session insights).WriteDevin Session Insights
Per-session cost, message counts and AI-generated analysis (session insights). Cost fields: acus_consumed is always present; on_demand_usage_usd is the USD overage of the session itself (children excluded) and only appears for organizations on a Teams plan â when it is absent, acus_consumed is the cost. Actions: list: sessions matching the filters (all optional, combined with AND; same filters as devin_session_search), one block per session â cost, num_user_messages, num_devin_messages, session_size, analysis_status, then classification, issues (title, impact, label) and action items when an analysis exists. Long issue titles are cut short here; use 'get' for the full text. Paginated via first / after. get: the same for one session with full issue titles, plus each issue's id and description, the timeline (one line per step, with the issue_id of the issue it belongs to, if any) and the suggested improved prompt. generate: starts analysis generation for one session in the background and reports 'started', or 'already_exists' when an analysis exists or is already running. Poll 'get' for the result.
Inputs
actionstringrequired- Operation to perform â list, get, generate.one of
listgetgenerate afterstring- Opaque cursor for 'list' pagination (from a previous response's end_cursor).
automation_idsstring- Filter to sessions created by any of these automations (automation ids, e.g. 'auto-abc123...').
billing_tag_idsstring- Filter by billing tag. Values are billing tag ids (see devin_billing_tag_manage) or the special values 'miscellaneous' (explicitly tagged Miscellaneous) and 'uncategorized' (never tagged); a session matches if it matches any value. Only available for organizations with billing tags enabled â the search fails with an error otherwise.
categorystring- Filter by session category. Valid values: 'bug_fixing', 'ci_cd_and_devops', 'code_quality_and_security', 'code_review', 'code_review_and_analysis', 'data_and_automation', 'documentation_and_content', 'feature_development', 'migrations_and_upgrades', 'other', 'production_investigation', 'refactoring_and_optimization', 'research_and_exploration', 'security', 'unit_test_generation'.
created_afterstring- Unix timestamp lower bound for creation time.
created_beforestring- Unix timestamp upper bound for creation time.
firststring- Number of results per page for 'list' (default 20, max 100).
originsstring- Filter by origin. Valid values: 'webapp', 'slack', 'teams', 'api', 'linear', 'jira', 'automation', 'cli', 'desktop', 'code_scan', 'other'.
parent_session_idstring- Filter to child sessions spawned by this parent session (accepts the 'devin-' prefix).
playbook_idstring- Filter by playbook.
schedule_idstring- Filter by schedule.
session_idstring- Target Devin session ID, e.g. 'devin-abc123...' (required for 'get' and 'generate').
session_idsstring- Filter to specific session IDs (must include the 'devin-' prefix, e.g. 'devin-abc123...').
tagsstring- Filter by tags.
updated_afterstring- Unix timestamp lower bound for update time.
updated_beforestring- Unix timestamp upper bound for update time.
user_idsstring- Filter by user.
devinmcp_devin_session_interactInteract with a Devin session — get status, send a message, sleep, or terminate.WriteDevin Session Interact
Interact with a Devin session — get status, send a message, sleep, or terminate.
Inputs
actionstringrequired- Operation to perform â get, message, sleep, terminate, archive, unarchive, get_messages, get_attachments, set_tags, forward_to_slack.one of
getmessagesleepterminatearchiveunarchiveget_messagesget_attachmentsset_tagsforward_to_slack session_idstringrequired- Target Devin session ID, e.g. 'devin-abc123...' (the 'devin-' prefix is optional â bare IDs, such as the ones in child_session_ids, also work). A bot is targeted through its current conversation: pass 'superdevin-<id>' (the id in its page URL '.../superdevin/<id>') or its 'bot-...' id in place of a session ID (terminate, archive and unarchive need the conversation's own session ID, which action='get' returns). action='get' also accepts a list of up to 100 IDs to read several sessions in one call; every other action takes exactly one ID.
afterstring- Opaque cursor for get_messages pagination (v3 cursor param).
archive_on_terminateboolean- Also archive the session when terminating (default False).default
false attachment_urlsstring- Optional list of already-uploaded attachment URLs to attach to the message (only used when action is 'message'). Listing a URL here is what links the file to the session and lets it read the file; a URL that only appears in the message text is not linked. Each URL must belong to the session's org â same mechanism as the initial prompt's attachments.
firststring- Page size for get_messages pagination (v3 cursor param). get_attachments is not paginated â v3 returns the full list.
forward_user_message_idsstring- Only used when action is 'message', in place of `message`: the `message_id` of user messages of your own session, in order. Each is delivered verbatim (text, attachments, original sender and time), marked as forwarded by you. Prefer this to retyping or summarizing what the user said.
messagestring- Message text (required when action is 'message').
notify_on_responsestring- Only used when action is 'message', and only honored when the caller is itself a Devin session. Then, when true, you are notified (and woken if sleeping) once when this session next settles (finishes, blocks, or exits). One-shot: consumed on delivery â pass it again on a later message to re-subscribe. A Superdevin is also woken by each message the session posts while it keeps working, batched. Works for any session you are allowed to message (descendants, same-automation siblings, and sessions currently claiming tickets on a board you manage). Other API clients (PATs, service users, external MCP clients) cannot receive notifications; the flag is dropped and they should poll devin_session_interact(action='get').
request_idstring- Required when action is 'forward_to_slack': the pending request of the session to forward â the request_id of its network_access_request, permission_request or request_secret event, or the event id of its environment_config_suggestion event (devin_session_events).
summaryboolean- Only used when action is 'get'. When true, each session also carries a short AI-written summary of what happened in it (about 500 characters). Summaries are generated after a session sleeps or finishes, so very recent or still-running sessions may have none yet.default
false tagsstring- Tag list (required when action is 'set_tags'). Replaces all existing tags on the session â this is a full replacement, not a union/append.
devinmcp_devin_session_searchSearch and filter Devin sessions by date, tags, playbook, schedule, or user.WriteDevin Session Search
Search and filter Devin sessions by date, tags, playbook, schedule, or user.
Inputs
afterstring- Opaque cursor for pagination (from a previous response's end_cursor).
automation_idsstring- Filter to sessions created by any of these automations (automation ids, e.g. 'auto-abc123...').
billing_tag_idsstring- Filter by billing tag. Values are billing tag ids (see devin_billing_tag_manage) or the special values 'miscellaneous' (explicitly tagged Miscellaneous) and 'uncategorized' (never tagged); a session matches if it matches any value. Only available for organizations with billing tags enabled â the search fails with an error otherwise.
categorystring- Filter by session category. Valid values: 'bug_fixing', 'ci_cd_and_devops', 'code_quality_and_security', 'code_review', 'code_review_and_analysis', 'data_and_automation', 'documentation_and_content', 'feature_development', 'migrations_and_upgrades', 'other', 'production_investigation', 'refactoring_and_optimization', 'research_and_exploration', 'security', 'unit_test_generation'.
created_afterstring- Unix timestamp lower bound for creation time.
created_beforestring- Unix timestamp upper bound for creation time.
firststring- Number of results per page (default 20, max 100 â tool-level cap below server's 200).
has_appstring- True: only sessions managing a Devin App you can open. False: only sessions managing none. This is how you find an App the user refers to, e.g. has_app=true with query='coffee'. An App whose managing session was deleted is not findable here.
include_bot_sessionsstring- With user_ids: also include sessions run by those users' Bots (bots), and the sessions those bots started. user_ids alone misses them because a bot's sessions belong to its service user. Set it whenever you look for a user's own work: users count what their Bots did as theirs.
originsstring- Filter by origin. Valid values: 'webapp', 'slack', 'teams', 'api', 'linear', 'jira', 'automation', 'cli', 'desktop', 'code_scan', 'other'.
parent_session_idstring- Filter to child sessions spawned by this parent session (accepts the 'devin-' prefix).
playbook_idstring- Filter by playbook.
querystring- BM25 keyword search over session titles and message content (bag of words, not semantic): a session only matches on the exact words it contains. The user's description is usually a paraphrase, so run several queries in parallel, each a different guess at the words the session itself would use: synonyms, likely identifiers, config keys, error text, file, PR or product names. Keep each query short (1-4 terms). Results come back best match first, each with a snippet of its best-matching message. Combine with the other filters to narrow down.
schedule_idstring- Filter by schedule.
session_idsstring- Filter to specific session IDs, e.g. 'devin-abc123...' (the 'devin-' prefix is optional).
tagsstring- Filter by tags.
updated_afterstring- Unix timestamp lower bound for update time.
updated_beforestring- Unix timestamp upper bound for update time.
user_idsstring- Filter by user.
devinmcp_devin_superdevin_createCreate a new Superdevin owned by the user who owns you, and start its conversation so it can be messaged right away.WriteDevin Superdevin Create
Create a new Superdevin owned by the user who owns you, and start its conversation so it can be messaged right away. Only available in the user's home Superdevin.
Inputs
namestringrequired- The new Bot's name, as its sidebar and page show it.
avatar_urlstring- The icon the user picked on the approval card. Bots do not see this input.
handoff_contextstring- Pass this Bot's job here, with what the user told you that it needs: it starts that job in its first conversation, without a message from you, unless this says to wait for one. Optional.
slack_icon_urlstring- The icon the user picked on the approval card. Bots do not see this input.
template_idstring- A `template_id` from devin_superdevin_templates to make the Bot from, which gives it that role's plugin. Optional.
devinmcp_devin_superdevin_templatesList the template library: the ready-made Bots you can make for the user who owns you, each with its `template_id`, name and what it does.WriteDevin Superdevin Templates
List the template library: the ready-made Bots you can make for the user who owns you, each with its `template_id`, name and what it does.
Inputs
This tool takes no inputs.
devinmcp_devin_user_listList the current organization's users, one membership kind per call.WriteDevin User List
List the current organization's users, one membership kind per call. Rows are `user_id | email | name` (roles appended with include_roles).
Inputs
afterstring- Opaque cursor for pagination (from a previous response's 'after=' notice).
emailstring- Exact email address to filter by (case-insensitive).
firststring- Number of results per page (default 20, max 100).
include_rolesboolean- Append each user's organization roles to their row (default false).default
false membershipstring- 'direct': users added to the organization individually, with roles assigned to them. 'idp': users who are members via an identity-provider (SSO/SCIM) group mapped to the organization, with roles inherited from the group. A user can be both; list both to enumerate every member.one of
directidpdefaultdirect
devinmcp_generate_wikiGenerate a codebase wiki for a repository and wait for it to complete.WriteGenerate Wiki
Generate a codebase wiki for a repository and wait for it to complete.
Inputs
repoNamestringrequired- No description.
devinmcp_read_wiki_contentsView documentation content for a GitHub repository.WriteRead Wiki Contents
View documentation content for a GitHub repository.
Inputs
repoNamestringrequired- No description.
devinmcp_read_wiki_structureGet a list of documentation topics for a GitHub repository.WriteRead Wiki Structure
Get a list of documentation topics for a GitHub repository.
Inputs
repoNamestringrequired- No description.
No tools match.