Anakin MCP connector

1. Install the SDK

   Node.js

   npm install @scalekit-sdk/node

   Python

   pip install scalekit

   Full SDK reference: Node.js | Python

2. Set your credentials

   Add your Scalekit credentials to your .env file. 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>

3. Authorize and make your first call

   Node.js

   quickstart.ts

   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   
   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENV_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)
   process.stdout.write('Press Enter after authorizing...')
   await new Promise(r => process.stdin.once('data', r))
   
   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'anakinmcp_agentic_search',
     toolInput: { prompt: 'YOUR_PROMPT' },
   })
   console.log(result)

   Python

   quickstart.py

   import os
   from scalekit.client import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()
   
   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENV_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={"prompt":"YOUR_PROMPT"},
       tool_name="anakinmcp_agentic_search",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)

What you can do

Connect this agent connector to let your agent:

• Read wire — 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
• Identities wire — List your saved Wire identities and their credentials
• Discover wire — Find Wire actions for a task from a natural-language intent
• Catalog wire — Browse the Wire catalog
• Search agentic — Run an AI web search and return result URLs, titles, and snippets
• Scrape records — Fetch a single URL and return clean markdown by default

Tool list

Use the exact tool names from the Tool list below when you call execute_tool. If you’re not sure which name to use, list the tools available for the current user first.

anakinmcp_agentic_search#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.3 params▾

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.

NameTypeRequiredDescription

promptstringrequiredThe research question or task in natural language.

schemaobjectoptionalOptional JSON Schema describing the desired output shape. If omitted, the engine infers a schema from the prompt.

useBrowserbooleanoptionalUse the headless browser when scraping cited pages (more reliable for JS-heavy sources). Defaults to true.

anakinmcp_crawl#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.9 params▾

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.

NameTypeRequiredDescription

urlstringrequiredStarting URL.

countrystringoptionalTwo-letter proxy egress country code.

depthintegeroptionalLink-hops from the starting URL to follow.

excludePatternsarrayoptionalGlob/regex patterns. URLs matching any pattern are skipped.

includePatternsarrayoptionalGlob/regex patterns. Only URLs matching at least one pattern are fetched.

maxPagesintegeroptionalHard cap on pages fetched. Defaults to 10.

sessionIdstringoptionalOptional saved-browser-session ID for login-protected sites.

sessionNamestringoptionalOptional saved-browser-session name.

useBrowserbooleanoptionalRender each page in a headless browser (for SPAs).

anakinmcp_map#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.8 params▾

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.

NameTypeRequiredDescription

urlstringrequiredThe starting URL for discovery (typically a homepage or section root).

depthintegeroptionalHow many link-hops from the starting URL to follow.

includeExternalLinksbooleanoptionalAlso collect (but do not follow) external links.

includeSubdomainsbooleanoptionalInclude URLs on subdomains of the starting host.

limitintegeroptionalMaximum number of URLs to return overall.

limitPerLevelintegeroptionalMaximum URLs collected per depth level (controls breadth).

searchstringoptionalOptional keyword filter — only return URLs whose path/title matches.

useBrowserbooleanoptionalRender with a headless browser (for SPAs).

anakinmcp_scrape#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.7 params▾

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.

NameTypeRequiredDescription

urlstringrequiredThe URL to scrape.

countrystringoptionalTwo-letter country code for the proxy egress location (e.g. "us", "de", "in"). Defaults to "us".

forceFreshbooleanoptionalSkip the cache and refetch. Defaults to false; cached results are typically good for 24h.

generateJsonbooleanoptionalHave 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.

sessionIdstringoptionalOptional saved-browser-session ID for login-protected pages. Pair with useBrowser=true.

sessionNamestringoptionalOptional saved-browser-session name (alternative to sessionId).

useBrowserbooleanoptionalRender the page with a stealth headless browser. Required for SPAs and dynamic content; otherwise prefer the default (fetch-based) for speed and lower cost.

anakinmcp_search#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.2 params▾

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.

NameTypeRequiredDescription

promptstringrequiredThe search query in natural language.

limitintegeroptionalMaximum number of results to return.

anakinmcp_wire_catalog#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.1 param▾

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.

NameTypeRequiredDescription

slugstringoptionalCatalog slug to inspect (e.g. "walmart"). Omit to list all catalogs.

anakinmcp_wire_discover#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.2 params▾

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.

NameTypeRequiredDescription

qstringrequiredThe intent in natural language, e.g. "top phones on walmart", "search airbnb listings in Lisbon", "a linkedin profile's work history".

limitintegeroptionalMaximum number of candidate actions to return.

anakinmcp_wire_identities#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").1 param▾

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").

NameTypeRequiredDescription

catalog_idstringoptionalOptional — restrict to identities for a single catalog.

anakinmcp_wire_read_action#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.4 params▾

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.

NameTypeRequiredDescription

action_idstringrequiredThe action to run (from wire_discover / wire_catalog).

credential_idstringoptionalRequired when the action's auth_mode is "required"; honored when "optional"; ignored when "none". Get one from wire_identities or wire_login.

identity_idstringoptionalOptional identity selector — the server resolves a credential from it (alternative to credential_id).

paramsobjectoptionalThe action's input parameters. Shape depends on the action — use its parameter schema from discovery. Omit for actions that take none.