> **Building with AI coding agents?** Install the authstack plugin with one command. This equips your agent with accurate Scalekit implementation patterns. > > **Recommended** (the `-y` flags skip prompts, so the command runs without an interactive terminal): > ```bash > npx -y @scalekit-inc/cli setup -y > ``` > > Global: > ```bash > npm install -g @scalekit-inc/cli > scalekit setup -y > ``` > > Supports Claude Code, Cursor, GitHub Copilot, Codex + skills for other Agent Skills-compatible agents in `~/.agents/skills`. > Skills: integrate-agentkit, implement-saaskit, add-mcp-oauth, implement-sso, implement-scim. > [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/) --- # Connect AI agents to the Bugsnag MCP server The Bugsnag MCP connector routes your AI agent's tool calls to Bugsnag's own MCP server through Scalekit. Each user signs in to Bugsnag once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 19 tools. **Authentication:** OAuth 2.1/DCR **Categories:** Monitoring, Developer Tools, AI **Tools:** 19: 17 read, 2 write, 0 destructive **Users sign in with:** OAuth **OAuth app:** Scalekit's or your own **Built by:** Vendor MCP **Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=BUGSNAGMCP) ## Setup 1. ### Install the SDK **Node.js** ```bash npm install @scalekit-sdk/node dotenv ``` **Python** ```bash pip install scalekit-sdk-python python-dotenv ``` 2. ### Set your credentials Add your Scalekit credentials to your `.env` file. Find values in **[app.scalekit.com](https://app.scalekit.com)** > **Developers** > **API Credentials**. ```sh title=".env" SCALEKIT_ENVIRONMENT_URL= SCALEKIT_CLIENT_ID= SCALEKIT_CLIENT_SECRET= ``` 3. ### Create the Bugsnag MCP connection In **AgentKit > Connections**, create a Bugsnag MCP connection. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/). Scalekit credentials are available for Bugsnag MCP server, so you don't need to register an OAuth app. 4. ### Authorize a user and make your first call **Node.js** (`quickstart.mts`) ```typescript 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.actions const connector = 'bugsnagmcp' const identifier = 'user_123' // Generate an authorization link for the user const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier }) console.log('Authorize Bugsnag MCP:', link) const rl = createInterface({ input: process.stdin, output: process.stdout }) await rl.question('Press Enter after authorizing...') rl.close() // Make your first call const result = await actions.executeTool({ connector, identifier, toolName: 'bugsnagmcp_bugsnag_get_current_project', toolInput: {}, }) console.log(result) ``` ```bash npx tsx quickstart.mts ``` **Python** (`quickstart.py`) ```python import os from scalekit import ScalekitClient from dotenv import load_dotenv load_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.actions connection_name = "bugsnagmcp" identifier = "user_123" # Generate an authorization link for the user link_response = actions.get_authorization_link( connection_name=connection_name, identifier=identifier, ) print("Authorize Bugsnag MCP:", link_response.link) input("Press Enter after authorizing...") # Make your first call result = actions.execute_tool( tool_input={}, tool_name="bugsnagmcp_bugsnag_get_current_project", connection_name=connection_name, identifier=identifier, ) print(result) ``` ```bash python quickstart.py ``` Each user signs in once. See [Authorize a user](/agentkit/tools/authorize/) for the full flow and statuses. ## Tools Pass the exact name to `execute_tool`, with an input like each tool's example. To ask for a tool that's missing, use the [request form](https://scalekitsupport.portal.usepylon.com/forms/request-a-connector-tool). **Node.js** ```typescript const result = await actions.executeTool({ toolName: 'bugsnagmcp_bugsnag_get_build', toolInput: { buildId: '', }, connector: 'bugsnagmcp', identifier: 'user_123', }) ``` **Python** ```python result = actions.execute_tool( tool_name="bugsnagmcp_bugsnag_get_build", tool_input={ "buildId": "", }, connection_name="bugsnagmcp", identifier="user_123", ) ``` `result.data` is the app's response as JSON, and `result.execution_id` (`executionId` in Node.js) is the ID of the call. ### `bugsnagmcp_bugsnag_get_build` Get Build · Read-only Retrieve details for a specific build by its ID, including source control metadata. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `buildId` (`string`, required): Unique identifier of the app build - `projectId` (`string`, optional): Unique identifier of the project. This is optional if a current project is set and is used to set the current project for BugSnag tools. Example input: `{"buildId":""}` ### `bugsnagmcp_bugsnag_get_current_project` Get Current Project · Read-only Retrieve the default project set for the current session. Tools use this project when no projectId is specified. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: none. Example input: `{}` ### `bugsnagmcp_bugsnag_get_error` Get Error · Read-only Retrieve full details on an error, including aggregated stats across all occurrences and the latest event's stacktrace, breadcrumbs, and metadata. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `errorId` (`string`, required): Unique identifier of the error to retrieve - `filters` (`object`, optional): Apply filters to narrow down the error list. Use the List Project Event Filters tool to discover available filter fields. Time filters support extended ISO 8601 format (e.g. 2018-05-20T00:00:00Z) or relative format (e.g. 7d, 24h). - `projectId` (`string`, optional): Unique identifier of the project. This is optional if a current project is set and is used to set the current project for BugSnag tools. Example input: `{"errorId":""}` ### `bugsnagmcp_bugsnag_get_event` Get Event · Read-only Retrieve detailed information about a specific error event by its ID. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `eventId` (`string`, required): Unique identifier of the event - `projectId` (`string`, optional): Unique identifier of the project. This is optional if a current project is set and is used to set the current project for BugSnag tools. Example input: `{"eventId":""}` ### `bugsnagmcp_bugsnag_get_event_details_from_dashboard_url` Get Event From Dashboard URL · Read-only Retrieve event details using a Bugsnag dashboard URL. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `link` (`string`, required): Full URL to the event details page in the BugSnag dashboard (web interface), containing project slug and event_id parameter. Example input: `{"link":""}` ### `bugsnagmcp_bugsnag_get_events_on_an_error` Get Events On Error · Read-only List events (occurrences) grouped under a specific error. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `errorId` (`string`, required): Unique identifier of the error - `direction` (`string`, optional): Sort direction for ordering results. One of: `asc`, `desc`. Default: `desc`. - `filters` (`object`, optional): Apply filters to narrow down the event list. Use the List Project Event Filters tool to discover available filter fields. Time filters support extended ISO 8601 format (e.g. 2018-05-20T00:00:00Z) or relative format (e.g. 7d, 24h). - `nextUrl` (`string`, optional): URL for retrieving the next page of results. Use the value in the previous response to get the next page when more results are available. Only values provided in the output from this tool can be used. Do not attempt to construct it manually. - `perPage` (`number`, optional): How many results to return per page. Default: `30`. - `projectId` (`string`, optional): Unique identifier of the project. This is optional if a current project is set and is used to set the current project for BugSnag tools. Example input: `{"errorId":""}` ### `bugsnagmcp_bugsnag_get_network_endpoint_groupings` Get Network Endpoint Groupings · Read-only Retrieve the network endpoint grouping rules configured for a project. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `projectId` (`string`, optional): Unique identifier of the project. This is optional if a current project is set and is used to set the current project for BugSnag tools. Example input: `{}` ### `bugsnagmcp_bugsnag_get_release` Get Release · Read-only Retrieve details for a specific release by its ID, including source control info and associated builds. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `releaseId` (`string`, required): Unique identifier of the app release - `projectId` (`string`, optional): Unique identifier of the project. This is optional if a current project is set and is used to set the current project for BugSnag tools. Example input: `{"releaseId":""}` ### `bugsnagmcp_bugsnag_get_span_group` Get Span Group · Read-only Retrieve performance metrics for a specific span group. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `spanGroupId` (`string`, required): ID of the span group - `filters` (`object`, optional): Apply filters to narrow down the span group list. Use the List Trace Fields tool to discover available filter fields. Time filters support extended ISO 8601 format (e.g. 2018-05-20T00:00:00Z) or relative format (e.g. 7d, 24h). - `projectId` (`string`, optional): Unique identifier of the project. This is optional if a current project is set and is used to set the current project for BugSnag tools. Example input: `{"spanGroupId":""}` ### `bugsnagmcp_bugsnag_get_trace` Get Trace · Read-only Retrieve all spans within a specific distributed trace. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `from` (`string`, required): Start time (ISO 8601 format) - `to` (`string`, required): End time (ISO 8601 format) - `traceId` (`string`, required): Trace ID - `nextUrl` (`string`, optional): URL for retrieving the next page of results. Use the value in the previous response to get the next page when more results are available. Only values provided in the output from this tool can be used. Do not attempt to construct it manually. - `perPage` (`number`, optional): How many results to return per page. Default: `30`. - `projectId` (`string`, optional): Unique identifier of the project. This is optional if a current project is set and is used to set the current project for BugSnag tools. - `targetSpanId` (`string`, optional): Optional target span ID to focus on Example input: `{"from":"","to":"","traceId":""}` ### `bugsnagmcp_bugsnag_list_project_errors` List Project Errors · Read-only List and search errors in a project with filters, sorting, and pagination. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `direction` (`string`, optional): Sort direction for ordering results. One of: `asc`, `desc`. Default: `desc`. - `filters` (`object`, optional): Apply filters to narrow down the error list. Use the List Project Event Filters tool to discover available filter fields. Time filters support extended ISO 8601 format (e.g. 2018-05-20T00:00:00Z) or relative format (e.g. 7d, 24h). - `nextUrl` (`string`, optional): URL for retrieving the next page of results. Use the value in the previous response to get the next page when more results are available. Only values provided in the output from this tool can be used. Do not attempt to construct it manually. - `perPage` (`number`, optional): How many results to return per page. Default: `30`. - `projectId` (`string`, optional): Unique identifier of the project. This is optional if a current project is set and is used to set the current project for BugSnag tools. - `sort` (`string`, optional): Field to sort the errors by. One of: `first_seen`, `last_seen`, `events`, `users`, `unsorted`. Default: `last_seen`. Example input: `{}` ### `bugsnagmcp_bugsnag_list_project_event_filters` List Project Event Filters · Read-only Retrieve available event filter fields for a project. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `projectId` (`string`, optional): Unique identifier of the project. This is optional if a current project is set and is used to set the current project for BugSnag tools. Example input: `{}` ### `bugsnagmcp_bugsnag_list_projects` List Projects · Read-only List all projects in the organization the current user can access, or find a project by API key. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `apiKey` (`string`, optional): The API key of the BugSnag project, if known. Example input: `{}` ### `bugsnagmcp_bugsnag_list_releases` List Releases · Read-only List releases for a project with optional stage and visibility filters. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `nextUrl` (`string`, optional): URL for retrieving the next page of results. Use the value in the previous response to get the next page when more results are available. Only values provided in the output from this tool can be used. Do not attempt to construct it manually. - `perPage` (`number`, optional): How many results to return per page. Default: `30`. - `projectId` (`string`, optional): Unique identifier of the project. This is optional if a current project is set and is used to set the current project for BugSnag tools. - `releaseStage` (`string`, optional): Filter releases by this stage (e.g. production, staging), defaults to 'production'. Default: `production`. - `visibleOnly` (`boolean`, optional): Whether to only include releases that are marked as visible in the dashboard. Default: `false`. Example input: `{}` ### `bugsnagmcp_bugsnag_list_span_groups` List Span Groups · Read-only List span groups (tracked operations) for performance monitoring in a project. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `direction` (`string`, optional): Sort direction for ordering results. One of: `asc`, `desc`. Default: `desc`. - `filters` (`object`, optional): Apply filters to narrow down the span group list. Use the List Trace Fields tool to discover available filter fields. Time filters support extended ISO 8601 format (e.g. 2018-05-20T00:00:00Z) or relative format (e.g. 7d, 24h). - `nextUrl` (`string`, optional): URL for retrieving the next page of results. Use the value in the previous response to get the next page when more results are available. Only values provided in the output from this tool can be used. Do not attempt to construct it manually. - `perPage` (`number`, optional): How many results to return per page. Default: `30`. - `projectId` (`string`, optional): Unique identifier of the project. This is optional if a current project is set and is used to set the current project for BugSnag tools. - `sort` (`string`, optional): Field to sort by. One of: `total_spans`, `last_seen`, `name`, `display_name`, `network_http_method`, `rendering_slow_frame_span_percentage`, `rendering_frozen_frame_span_percentage`, `duration_p50`, `duration_p75`, `duration_p90`, `duration_p95`, `duration_p99`, `system_metrics_cpu_total_mean_p50`, `system_metrics_cpu_total_mean_p75`, `system_metrics_cpu_total_mean_p90`, `system_metrics_cpu_total_mean_p95`, `system_metrics_cpu_total_mean_p99`, `system_metrics_memory_device_mean_p50`, `system_metrics_memory_device_mean_p75`, `system_metrics_memory_device_mean_p90`, `system_metrics_memory_device_mean_p95`, `system_metrics_memory_device_mean_p99`, `rendering_metrics_fps_mean_p50`, `rendering_metrics_fps_mean_p75`, `rendering_metrics_fps_mean_p90`, `rendering_metrics_fps_mean_p95`, `rendering_metrics_fps_mean_p99`, `http_response_4xx_percentage`, `http_response_5xx_percentage`. - `starredOnly` (`boolean`, optional): Show only starred span groups Example input: `{}` ### `bugsnagmcp_bugsnag_list_spans` List Spans · Read-only List individual spans belonging to a span group. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `spanGroupId` (`string`, required): ID of the span group - `direction` (`string`, optional): Sort direction for ordering results. One of: `asc`, `desc`. Default: `desc`. - `filters` (`object`, optional): Apply filters to narrow down the span group list. Use the List Trace Fields tool to discover available filter fields. Time filters support extended ISO 8601 format (e.g. 2018-05-20T00:00:00Z) or relative format (e.g. 7d, 24h). - `nextUrl` (`string`, optional): URL for retrieving the next page of results. Use the value in the previous response to get the next page when more results are available. Only values provided in the output from this tool can be used. Do not attempt to construct it manually. - `perPage` (`number`, optional): How many results to return per page. Default: `30`. - `projectId` (`string`, optional): Unique identifier of the project. This is optional if a current project is set and is used to set the current project for BugSnag tools. - `sort` (`string`, optional): Field to sort by. One of: `duration`, `timestamp`, `full_page_load_lcp`, `full_page_load_fid`, `full_page_load_cls`, `full_page_load_ttfb`, `full_page_load_fcp`, `rendering_slow_frame_percentage`, `rendering_frozen_frame_percentage`, `system_metrics_cpu_total_mean`, `system_metrics_memory_device_mean`, `rendering_metrics_fps_mean`, `rendering_metrics_fps_minimum`, `rendering_metrics_fps_maximum`, `http_response_code`. Example input: `{"spanGroupId":""}` ### `bugsnagmcp_bugsnag_list_trace_fields` List Trace Fields · Read-only Retrieve available trace attribute fields for filtering. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `projectId` (`string`, optional): Unique identifier of the project. This is optional if a current project is set and is used to set the current project for BugSnag tools. Example input: `{}` ### `bugsnagmcp_bugsnag_set_network_endpoint_groupings` Set Network Endpoint Groupings · Write Set network endpoint grouping rules for a project. Read only: no. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `endpoints` (`array`, required): Array of URL patterns by which network spans are grouped. Endpoints follow OpenAPI path templating syntax (https://swagger.io/specification/#path-templating) where path parameters use curly braces (e.g., /users/{id}). If you encounter colon-prefixed parameters (e.g., :userId from Express/React Router), convert them to curly braces (e.g., {userId}). Wildcards (*) can be used in domains (e.g., https://*.example.com) to match multiple subdomains. - `projectId` (`string`, optional): Unique identifier of the project. This is optional if a current project is set and is used to set the current project for BugSnag tools. Example input: `{"endpoints":[]}` ### `bugsnagmcp_bugsnag_update_error` Update Error · Write Update the status of an error (e.g., ignore, snooze, open, or mark as fixed). Read only: no. Destructive: no. Idempotent (safe to retry): no. Inputs: - `errorId` (`string`, required): Unique identifier of the error - `operation` (`string`, required): The operation to apply to the error. One of: `override_severity`, `open`, `fix`, `ignore`, `discard`, `undiscard`, `snooze`, `link_issue`, `unlink_issue`. - `issue_url` (`string`, optional): The URL of the issue to link to the error - required when operation is 'link_issue' - `projectId` (`string`, optional): Unique identifier of the project. This is optional if a current project is set and is used to set the current project for BugSnag tools. - `reopenRules` (`object`, optional): Reopen rules for snooze operation - required when operation is 'snooze' Example input: `{"errorId":"","operation":"override_severity"}` ## Related Other Monitoring connectors ([all 22](/agentkit/connectors/?category=monitoring)): - [Datadog](/agentkit/connectors/datadog/): Scalekit connector, API key, 105 tools - [PagerDuty](/agentkit/connectors/pagerduty/): Scalekit connector, OAuth, 71 tools - [Agency Analytics MCP server](/agentkit/connectors/agencyanalyticsmcp/): Vendor MCP, OAuth, 35 tools --- ## More Scalekit documentation | Resource | What it contains | When to use it | |----------|-----------------|----------------| | [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content | | [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas | | [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |