> **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 Anakin MCP server

The Anakin MCP connector routes your AI agent's tool calls to Anakin's own MCP server through Scalekit. Each user signs in to Anakin once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 21 tools.

**Authentication:** OAuth2.1/DCR
**Categories:** AI, Automation, Productivity
**Tools:** 21: 8 read, 11 write, 2 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=ANAKINMCP)

## 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=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>
   ```

3. ### Create the Anakin MCP connection

   In **AgentKit > Connections**, create an Anakin MCP connection. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/).

   Scalekit credentials are available for Anakin 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 = 'anakinmcp'
   const identifier = 'user_123'

   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Anakin 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: 'anakinmcp_ai_visibility_sources',
     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 = "anakinmcp"
   identifier = "user_123"

   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize Anakin MCP:", link_response.link)
   input("Press Enter after authorizing...")

   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="anakinmcp_ai_visibility_sources",
       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: 'anakinmcp_ai_visibility_search',
  toolInput: {
    query: '<query>',
  },
  connector: 'anakinmcp',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="anakinmcp_ai_visibility_search",
    tool_input={
        "query": "<query>",
    },
    connection_name="anakinmcp",
    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.

### `anakinmcp_ai_visibility_search`

AIVisibilitySearch · Read-only

Ask multiple AI answer engines (ChatGPT, Gemini, Google AI Overview) the same question and compare their answers. Returns one result per engine — status, an answer summary, latency, credits used, and a consensus/outlier verdict — plus an AI-generated synthesis of where the engines agree and diverge. Async; typically completes within 1–2 minutes and this tool polls to completion. Use for brand/AI-SEO visibility checks ("what do AI engines say about X"), answer comparison, and geo-specific AI answers (set country). Billed per source at that Wire action's rate; failed sources are free. Set include_full_content=true only when you need each engine's raw full answer — it is large.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `query` (`string`, required): The question to ask every engine (max 2000 characters).
- `country` (`string`, optional): Two-letter ISO country for the search geography (proxy exit). Defaults to "us". Default: `us`.
- `include_full_content` (`boolean`, optional): Include each engine's raw full answer in the results (large). Defaults to false — summaries and the synthesis are returned regardless. Default: `false`.
- `sources` (`array`, optional): Engine slugs to query (see ai_visibility_sources). Omit to query all enabled engines.

Example input: `{"query":"<query>"}`

### `anakinmcp_ai_visibility_sources`

AIVisibilitySources · Read-only

List the AI answer engines available to ai_visibility_search — each with its slug (what you pass as `sources`) and display label. Call this when you need to query a subset of engines or check what is currently enabled.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs: none.

Example input: `{}`

### `anakinmcp_map`

Map · Read-only

Discover all reachable URLs under a given site. Useful for understanding a domain's structure before crawling, or finding the sub-pages an agent should scrape. Returns lists of internal links, external links, and counts. Honors depth and limit parameters.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `url` (`string`, required): The starting URL for discovery (typically a homepage or section root).
- `depth` (`integer`, optional): How many link-hops from the starting URL to follow. Default: `2`.
- `includeExternalLinks` (`boolean`, optional): Also collect (but do not follow) external links. Default: `false`.
- `includeSubdomains` (`boolean`, optional): Include URLs on subdomains of the starting host. Default: `false`.
- `limit` (`integer`, optional): Maximum number of URLs to return overall. Default: `100`.
- `limitPerLevel` (`integer`, optional): Maximum URLs collected per depth level (controls breadth). Default: `100`.
- `search` (`string`, optional): Optional keyword filter — only return URLs whose path/title matches.
- `useBrowser` (`boolean`, optional): Render with a headless browser (for SPAs). Default: `false`.

Example input: `{"url":"<url>"}`

### `anakinmcp_monitor_changes`

MonitorChanges · Read-only

Get the detected changes for a monitor — each entry records when the watched content differed from the previous check, with a diff/summary (and the AI change summary when aiMode is on). Use monitor_list first to find the monitor id.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `id` (`string`, required): The monitor ID (from monitor_list or monitor_create).

Example input: `{"id":"<id>"}`

### `anakinmcp_monitor_list`

MonitorList · Read-only

List your website monitors, or pass `id` to fetch one monitor's full configuration and status (next/last check time, active state, per-check credit cost, alert settings). Use this to find a monitor's id before monitor_changes or monitor_control.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `id` (`string`, optional): Monitor ID — fetch just this monitor instead of the full list.

Example input: `{}`

### `anakinmcp_scrape`

Scrape · Read-only

Fetch a single URL and return clean markdown by default. Set generateJson=true to also extract structured data with AI. Set useBrowser=true for SPAs and JS-heavy sites (slower and more expensive — only when needed). Returns markdown unless generateJson is true, in which case it returns the structured JSON.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `url` (`string`, required): The URL to scrape.
- `country` (`string`, optional): Two-letter country code for the proxy egress location (e.g. "us", "de", "in"). Defaults to "us". Default: `us`.
- `forceFresh` (`boolean`, optional): Skip the cache and refetch. Defaults to false; cached results are typically good for 24h. Default: `false`.
- `generateJson` (`boolean`, optional): Have AI extract structured JSON from the page in addition to / instead of markdown. Use for product pages, listings, articles, anywhere the caller wants typed fields. Default: `false`.
- `sessionId` (`string`, optional): Optional saved-browser-session ID for login-protected pages. Pair with useBrowser=true.
- `sessionName` (`string`, optional): Optional saved-browser-session name (alternative to sessionId).
- `useBrowser` (`boolean`, optional): Render the page with a stealth headless browser. Required for SPAs and dynamic content; otherwise prefer the default (fetch-based) for speed and lower cost. Default: `false`.

Example input: `{"url":"<url>"}`

### `anakinmcp_search`

Search · Read-only

Run an AI web search and return result URLs, titles, and snippets. Synchronous — returns immediately, no polling. Use this when the agent needs to discover pages relevant to a query before scraping. Returns a results array with url/title/snippet/date for each hit.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `prompt` (`string`, required): The search query in natural language.
- `limit` (`integer`, optional): Maximum number of results to return. Default: `5`.

Example input: `{"prompt":"<prompt>"}`

### `anakinmcp_session_list`

SessionList · Read-only

List your saved browser sessions — encrypted login states captured via the Anakin dashboard or Browser API. Each session's id is what you pass as sessionId to scrape/crawl, monitor_create, or browser_task to work with login-protected pages. Optionally filter by the website domain the session belongs to. If no session exists for a site, the user must create one interactively in the dashboard (log in once; 2FA/captchas included) — that flow cannot run from here.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `domain` (`string`, optional): Filter to sessions for one website domain, e.g. "amazon.com".

Example input: `{}`

### `anakinmcp_agentic_search`

AgenticSearch · Write

Run multi-source deep research. The pipeline searches the web, scrapes the most relevant citations, and uses an LLM to structure the combined data into a unified answer. Async — typically 1–5 minutes. Use this when one URL or a flat search result will not answer the question (comparative analysis, multi-jurisdictional research, market intelligence). Returns a summary plus structured_data conforming to the inferred or supplied schema.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `prompt` (`string`, required): The research question or task in natural language.
- `schema` (`object`, optional): Optional JSON Schema describing the desired output shape. If omitted, the engine infers a schema from the prompt.
- `useBrowser` (`boolean`, optional): Use the headless browser when scraping cited pages (more reliable for JS-heavy sources). Defaults to true. Default: `true`.

Example input: `{"prompt":"<prompt>"}`

### `anakinmcp_browser_task`

BrowserTask · Write

Run a natural-language task in a real cloud browser driven by an AI agent: it navigates, clicks, types, scrolls, and extracts on your behalf ("find the cheapest 65-inch TV on this site and list its specs", "fill the contact form with …"). Use when scrape cannot do the job (multi-step flows, interactions, complex navigation) and no Wire action covers the site (check wire_discover first — Wire actions are faster and cheaper). Async; runs up to ~5 minutes and this tool polls to completion. For login-protected tasks pass session_id from session_list — never put passwords in the prompt. Supply output_schema to get structured JSON back. It does not execute payments or transfer funds; such tasks are refused. Returns the task result plus run metadata (steps taken, duration, run_id).

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `prompt` (`string`, required): The task in natural language. Be specific about the goal and what to return. Never include passwords or secrets — use session_id for authenticated sites.
- `max_steps` (`integer`, optional): Cap on agent steps (navigation/click/type actions).
- `output_schema` (`object`, optional): JSON Schema for the result — the agent returns structured data conforming to it.
- `session_id` (`string`, optional): Saved browser-session ID (from session_list) so the task runs logged in.
- `timeout_ms` (`integer`, optional): Task timeout in milliseconds (server caps runs at ~330s regardless).
- `url` (`string`, optional): Navigate here before starting. Omit to let the agent follow URLs named in the prompt.

Example input: `{"prompt":"<prompt>"}`

### `anakinmcp_crawl`

Crawl · Write

Bulk-fetch markdown across a site. Use this when an agent needs the contents of many pages at once (catalog ingestion, site-wide RAG corpus). Pair with includePatterns / excludePatterns to scope which URLs are fetched. Returns an array of pages each with markdown and per-page status.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `url` (`string`, required): Starting URL.
- `country` (`string`, optional): Two-letter proxy egress country code. Default: `us`.
- `depth` (`integer`, optional): Link-hops from the starting URL to follow. Default: `1`.
- `excludePatterns` (`array`, optional): Glob/regex patterns. URLs matching any pattern are skipped.
- `includePatterns` (`array`, optional): Glob/regex patterns. Only URLs matching at least one pattern are fetched.
- `maxPages` (`integer`, optional): Hard cap on pages fetched. Defaults to 10. Default: `10`.
- `sessionId` (`string`, optional): Optional saved-browser-session ID for login-protected sites.
- `sessionName` (`string`, optional): Optional saved-browser-session name.
- `useBrowser` (`boolean`, optional): Render each page in a headless browser (for SPAs). Default: `false`.

Example input: `{"url":"<url>"}`

### `anakinmcp_monitor_control`

MonitorControl · Write

Control an existing website monitor: "pause" stops scheduled checks, "resume" restarts them (may hit the plan's active-monitor cap), "run_now" triggers an immediate out-of-schedule check (billed like a normal check), and "delete" permanently removes the monitor and its history. Use monitor_list to find the id.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `action` (`string`, required): What to do with the monitor. One of: `pause`, `resume`, `run_now`, `delete`.
- `id` (`string`, required): The monitor ID (from monitor_list or monitor_create).

Example input: `{"action":"pause","id":"<id>"}`

### `anakinmcp_monitor_create`

MonitorCreate · Write

Create a scheduled website monitor that checks a URL every intervalMinutes (min 15) and records a change when the content differs — optionally alerting a webhook or email. scope "page" (default) watches one URL; "site" crawls the site each run and tracks pages added/removed/changed; "wire" runs a Wire action each check and diffs its JSON. watchMode "full_page" (2 credits/check) compares the whole page; "specific_data" (3 credits/check) extracts only the fields in outputSchema with AI — ideal for price/stock/status tracking. aiMode (+1 credit/check) filters out trivial noise and summarizes real changes. Active-monitor caps per plan: Free 5, Pro 20, Scale 100.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `intervalMinutes` (`integer`, required): Check frequency in minutes. Minimum 15.
- `url` (`string`, required): The URL to watch (root URL for site scope; the Wire site's URL for wire scope).
- `aiGoal` (`string`, optional): Natural-language description of which changes count as meaningful (used with aiMode), e.g. "only when the price drops or it goes out of stock".
- `aiMode` (`boolean`, optional): AI meaningful-change filtering: ignores trivial noise (ads, timestamps) and summarizes real changes. +1 credit per check. Default: `false`.
- `alertEmails` (`string`, optional): Comma-separated email recipients for change alerts.
- `alertWebhookUrl` (`string`, optional): Webhook URL that receives signed change alerts.
- `country` (`string`, optional): Two-letter proxy country code. Defaults to "us". Default: `us`.
- `excludePatterns` (`array`, optional): Site scope: glob patterns to skip.
- `expiresAt` (`string`, optional): Optional end date (ISO 8601 timestamp or YYYY-MM-DD); the monitor auto-pauses when it passes.
- `includePatterns` (`array`, optional): Site scope: glob patterns or hand-picked same-site URLs to track.
- `isActive` (`boolean`, optional): Start running immediately. Defaults to true. Default: `true`.
- `maxDepth` (`integer`, optional): Site scope: crawl depth (1–5). Defaults to 2.
- `maxPages` (`integer`, optional): Site scope: max pages crawled per run.
- `outputSchema` (`object`, optional): JSON Schema of the fields to track. Required when watchMode is "specific_data".
- `scope` (`string`, optional): What to monitor: one page (default), a whole site, or a Wire action. One of: `page`, `site`, `wire`. Default: `page`.
- `sessionId` (`string`, optional): Saved browser-session ID for monitoring login-protected pages (see session_list).
- `useBrowser` (`boolean`, optional): Render checks with a stealth headless browser (needed for JS-heavy pages). Forced true when sessionId is set. Default: `false`.
- `watchFormat` (`string`, optional): Format compared in full_page mode. Defaults to markdown. One of: `markdown`, `html`, `cleaned_html`. Default: `markdown`.
- `watchMode` (`string`, optional): Compare the whole page (default) or only the fields in outputSchema, extracted with AI. One of: `full_page`, `specific_data`. Default: `full_page`.
- `wireActionId` (`string`, optional): Wire scope (required there): the Wire action run each check, e.g. "amazon.search_products" (see wire_discover).
- `wireCatalogSlug` (`string`, optional): Wire scope: catalogue slug of the Wire site.
- `wireCredentialId` (`string`, optional): Wire scope: credential ID when the action needs auth (see wire_identities).
- `wireParams` (`object`, optional): Wire scope: parameters passed to the action each check.
- `wireWatchPaths` (`array`, optional): Wire scope: JSON paths to diff instead of the whole response.

Example input: `{"intervalMinutes":1,"url":"<url>"}`

### `anakinmcp_wire_build`

WireBuild · Write

Request a brand-new Wire action for a website that isn't in the catalog yet. Describe the site (`website_url`) and what the action should do or extract (`goal`); Wire generates and auto-tests a scraper, then publishes it. Asynchronous (returns status "pending") and charges credits, refunded automatically if the build fails. Only use this after wire_discover / wire_catalog confirm no existing action covers the site.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `goal` (`string`, required): Natural-language description of what the action should do or extract. Be specific — the builder synthesizes the scraper from this.
- `website_url` (`string`, required): The site to build an action for. The domain is extracted automatically.
- `catalog_id` (`string`, optional): Optional — attach to an existing catalog instead of creating one.
- `force` (`boolean`, optional): Build even if similar actions already exist for the domain (otherwise the request is rejected with ACTION_EXISTS). Default: `false`.
- `visibility` (`string`, optional): Action visibility. Defaults to private. One of: `private`, `public`. Default: `private`.

Example input: `{"goal":"<goal>","website_url":"<website_url>"}`

### `anakinmcp_wire_catalog`

WireCatalog · Write

Browse the Wire catalog. With no arguments, lists every supported website and its action count. Pass a catalog slug (e.g. "walmart", "amazon", "linkedin") to get that site's full action list with exact parameter schemas, each action's type (read/write), auth mode (none/optional/required), and credit cost — plus the login fields for credentials-mode sites.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `slug` (`string`, optional): Catalog slug to inspect (e.g. "walmart"). Omit to list all catalogs.

Example input: `{}`

### `anakinmcp_wire_discover`

WireDiscover · Write

Find Wire actions for a task from a natural-language intent. Wire is a catalog of pre-built automation actions across hundreds of websites (Amazon, Walmart, LinkedIn, Airbnb, Zillow, and others). Actions are of two kinds: READ actions that extract data and WRITE actions that perform interactions. Returns ranked candidate actions, each with its action_id, type ("read" or "write"), required/optional params, credit cost, and whether auth is needed.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `q` (`string`, required): The intent in natural language, e.g. "top phones on walmart", "search airbnb listings in Lisbon", "a linkedin profile's work history".
- `limit` (`integer`, optional): Maximum number of candidate actions to return. Default: `5`.

Example input: `{"q":"top phones on walmart"}`

### `anakinmcp_wire_identities`

WireIdentities · Write

List your saved Wire identities and their credentials. An identity is a named account on a site; each credential's id is the credential_id you pass to wire_read_action / wire_write_action to run actions whose auth_mode is "required". Optionally filter by catalog_id. Use this to find an existing credential before running an auth-required action (and check its status is "active", not "expired").

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `catalog_id` (`string`, optional): Optional — restrict to identities for a single catalog.

Example input: `{}`

### `anakinmcp_wire_login`

WireLogin · Write

Sign in to a credentials-mode site and get a credential_id usable immediately with wire_read_action / wire_write_action. Provide the catalog `slug` and login `params` (the fields that catalog's login schema defines, e.g. email/password — see wire_catalog's login_input_schema). The password is never stored, only the encrypted session. Only needed for actions whose auth_mode is "required", and only for catalogs that support password sign-in; cookie-based sites use the dashboard connect flow instead.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `catalog_slug` (`string`, required): The catalog to sign in to (e.g. "neb").
- `identity_name` (`string`, optional): Optional name for the identity. Derived from params in password mode; required when using a 1Password locator.
- `params` (`object`, optional): Login fields defined by the catalog (e.g. { email, password }). Use wire_catalog's login_input_schema to learn the field names.
- `source_id` (`string`, optional): Optional 1Password identity-source ID (alternative to params).
- `source_ref` (`object`, optional): Optional 1Password item locator { vault_id, item_id, fields } (use with source_id instead of params).

Example input: `{"catalog_slug":"neb"}`

### `anakinmcp_wire_read_action`

WireReadAction · Write

Run a Wire READ action — one whose type is "read" (it EXTRACTS data and does not change state on the target site): search listings, fetch a category's products, get a product's price/specs/reviews, read a profile, pull dashboard metrics. Discover action_ids first with wire_discover or wire_catalog. This tool transparently polls the async job to completion and returns the extracted data.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `action_id` (`string`, required): The action to run (from wire_discover / wire_catalog).
- `credential_id` (`string`, optional): Required when the action's auth_mode is "required"; honored when "optional"; ignored when "none". Get one from wire_identities or wire_login.
- `identity_id` (`string`, optional): Optional identity selector — the server resolves a credential from it (alternative to credential_id).
- `params` (`object`, optional): The action's input parameters. Shape depends on the action — use its parameter schema from discovery. Omit for actions that take none.

Example input: `{"action_id":"<action_id>"}`

### `anakinmcp_session_delete`

SessionDelete · Destructive

Permanently delete a saved browser session and its encrypted login data. Irreversible — the user must log in again through the dashboard to recreate it, and any monitors or requests referencing this sessionId will lose authenticated access. Find ids with session_list.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `id` (`string`, required): The session ID to delete (from session_list).

Example input: `{"id":"<id>"}`

### `anakinmcp_wire_write_action`

WireWriteAction · Destructive

Run a Wire WRITE action — one whose type is "write" (it performs a state-changing interaction on the target site): submit a form, add an item to a cart, post or send content, update account settings. Discover action_ids first with wire_discover or wire_catalog and confirm the action's type is "write"; `params` must match that action's parameter schema. Most write actions need auth — pass a `credential_id` from wire_identities or wire_login. This tool transparently polls the async job to completion and returns its result. It does not execute payments or transfer funds; such actions are refused. For data extraction that does not change state (type "read") use wire_read_action instead.

Read only: no. Destructive: yes. Idempotent (safe to retry): no.

Inputs:

- `action_id` (`string`, required): The action to run (from wire_discover / wire_catalog). Must be an action whose type is "write".
- `credential_id` (`string`, optional): Required when the action's auth_mode is "required"; honored when "optional"; ignored when "none". Get one from wire_identities or wire_login.
- `identity_id` (`string`, optional): Optional identity selector — the server resolves a credential from it (alternative to credential_id).
- `params` (`object`, optional): The action's input parameters. Shape depends on the action — use its parameter schema from discovery. Omit for actions that take none.

Example input: `{"action_id":"<action_id>"}`

## Related

Other AI connectors ([all 116](/agentkit/connectors/?category=ai)):

- [Chorus](/agentkit/connectors/chorus/): Scalekit connector, Username and password, 9 tools
- [Gong](/agentkit/connectors/gong/): Scalekit connector, OAuth, 49 tools
- [Jiminny](/agentkit/connectors/jiminny/): Scalekit connector, Access token, 27 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 |