Anakin MCP connector for AI agents

Tools your web agent reaches for on Anakin, scoped per user.

CALL ANY TOOL

Web automation end to end: search and scrape any page, crawl entire sites, and run pre-built Wire actions on catalog sites.

anakinmcp_map

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.

Parameters

Name

Type

Required

Description

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.

includeExternalLinks

boolean

Optional

Also collect (but do not follow) external links.

includeSubdomains

boolean

Optional

Include URLs on subdomains of the starting host.

limit

integer

Optional

Maximum number of URLs to return overall.

limitPerLevel

integer

Optional

Maximum URLs collected per depth level (controls breadth).

string

Optional

Optional keyword filter : only return URLs whose path/title matches.

useBrowser

boolean

Optional

Render with a headless browser (for SPAs).

anakinmcp_crawl

Crawl

anakinmcp_scrape

Scrape

anakinmcp_search

anakinmcp_wire_build

Wire build

anakinmcp_browser_task

Browser task

anakinmcp_wire_login

Wire login

anakinmcp_monitor_list

Monitor list

anakinmcp_wire_catalog

Wire catalog

anakinmcp_session_list

Session list

anakinmcp_wire_discover

Wire discover

anakinmcp_agentic_search

Agentic search

anakinmcp_monitor_create

Monitor create

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.

Parameters

Name

Type

Required

Description

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.

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".

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.

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.

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.

watchFormat

string

Optional

Format compared in full_page mode. Defaults to markdown.

watchMode

string

Optional

Compare the whole page (default) or only the fields in outputSchema, extracted with AI.

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.

anakinmcp_session_delete

Session delete

anakinmcp_monitor_changes

Monitor changes

anakinmcp_wire_identities

Wire identities

anakinmcp_monitor_control

Monitor control

anakinmcp_wire_read_action

Wire read action

anakinmcp_ai_visibility_search

Ai visibility search

anakinmcp_wire_write_action

Wire write action

anakinmcp_ai_visibility_sources

Ai visibility sources

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Anakin tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["anakinmcp"], toolNames: [
    "anakinmcp_search",
    "anakinmcp_scrape",
    "anakinmcp_wire_read_action"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "What do standing desks cost on Walmart?" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["anakinmcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Scrape this pricing page and return it as markdown." }],
  tools,
});

// Execute the tool call with the user's vaulted Anakin credential
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["anakinmcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Find Wire actions for tracking Amazon price changes." }],
  tools,
});

// Tool call runs with the user's vaulted Anakin credential
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["anakinmcp"] }, pageSize: 100,
});

const agent = new Agent({
  name: "anakin_web_agent",
  model: "gemini-2.5-pro",
  instruction: "Automate web research for the signed-in user.",
  tools,
});

await agent.run("Map competitor.com and list every URL under /blog.");

Try these prompts

Copy any prompt into your agent. Each maps directly to an Anakin tool. Click to copy, paste into your agent, done.

Deep research

Copy the prompt

Copied

Run a comparative analysis of the top 5 CRM vendors' pricing pages.

Copy the prompt

Copied

Research data residency rules across the EU, UK, and Switzerland.

Copy the prompt

Copied

Build a market overview of AI transcription startups with sources.

Scrape and crawl

Copy the prompt

Copied

Scrape this pricing page and return it as markdown.

Copy the prompt

Copied

Crawl the docs site and pull every page under /guides.

Copy the prompt

Copied

Map competitor.com and list every URL under /blog.

Wire actions

Copy the prompt

Copied

Find Wire actions for tracking Amazon price changes.

Copy the prompt

Copied

Pull the top 20 Walmart listings for standing desks.

Copy the prompt

Copied

Which sites in the Wire catalog support LinkedIn profile reads?

SEE HOW AUTH WORKS

Your users connect once. Their Anakin credentials stay vaulted, every call is scope-checked, and every action is logged.

Authorize

Your user connects

Anakin MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Anakin MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Anakin MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Anakin MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other automation connectors.

Engineering Teams

Slack triage

Polls Slack for new messages, classifies bugs and support requests with a LangGraph router, files GitHub issues or Zendesk tickets, and confirms in the thread.

Support and Ops Teams

Support ticket automation agent

Fetches new Zendesk tickets, drafts a reply from Notion knowledge base articles, digests what it cannot answer to Slack, and archives the rest, acting as the support agent rather than a shared API key.

Engineering Teams

DevOps assistant agent

Polls GitHub for failing checks and stale PRs, opens Linear issues for the ones that need work, and posts a daily digest to Slack. It acts as the engineer, not a shared service account.

Support and Ops Teams

Email-to-calendar agent

Reads scheduling intent out of Gmail threads, resolves the times everyone actually has free, and creates the event on the user's own Google Calendar. No shared service account.

Gmail

Google Calendar

View agent

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Anakin key looks fine in a demo. In production every scrape, crawl, and Wire action bills and logs as one account, and you cannot tell who ran the research or burned the credits. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared key
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Anakin today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Anakin as the user or through a shared key?

As the user. Scalekit resolves the credential of the person who triggered the agent at request time, so every search, scrape, and Wire action in your audit trail is attributed to a real user, not a shared service account.

Where is the Anakin API key stored?

In an AES-256 encrypted vault with per-tenant namespacing. Keys are resolved at request time, never enter LLM context, and can be rotated or revoked from one dashboard.

Can I limit what the agent does in Anakin?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example search and scrape without Wire write actions. Scalekit also enforces scope checks before every API call.

What happens when a user revokes access?

The credential is invalidated at the next tool call. The call fails closed, other users' connections are unaffected, and the revocation is logged in the audit chain.

Some Wire actions need a site login. How are those credentials handled?

Wire identities hold named site accounts inside Anakin, and the agent passes only a credential_id when it runs an auth-required action. Scalekit vaults the Anakin key itself, so neither raw site passwords nor the API key ever appear in LLM context.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit