Intro MCP server for AI agents
Let Claude, ChatGPT or your own agent read Intro: 2 typed functions through one MCP server. No Intro API key needed.
- Site
- intro.co
- Functions
- 2
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Intro
An MCP server for Intro alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.
https://api.bowmark.ai/mcp/site/intro_coEvery site
One MCP server for Intro and every other site Bowmark covers. Your agent looks up what it needs and calls it.
https://api.bowmark.ai/mcpSet it up in your clientBoth need a Bowmark API key. The quickstart gets you one and a first result in a few minutes.
Functions
Open a function to see its arguments, what it returns and how to call it.
Read 2
expertReads one intro.co expert's profile by handle or profile URL.Arguments
Name Type Required handlestringThe profile handle, e.g. "sophiaamoruso".No urlstringA profile URL, e.g. "https://intro.co/sophiaamoruso".No Returns
IntroCoExpertinterface IntroCoExpertSummary { id: number; name: string; /** Pass to expert({ handle }). */ handle: string | null; title: string; shortDescription: string; avatar: string | null; url: string; /** USD, for the default call length. */ sessionPrice: number | null; sessionMinutes: number | null; rating: number | null; ratingCount: number; verified: boolean; } interface IntroCoCallOption { minutes: number; /** USD. */ price: number; /** intro.co's raw Discount value for this length; unit not confirmed. */ discountRaw: number; active: boolean; } interface IntroCoExpert extends IntroCoExpertSummary { description: string; callOptions: IntroCoCallOption[]; sessionTopics: string[]; exampleQuestions: string[]; socials: { instagram: string | null; twitter: string | null; linkedin: string | null }; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/intro_co/expertCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.intro_co.expert({ handle: "sophiaamoruso" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.intro_co.expert({"handle": "sophiaamoruso"}))curl -X POST https://api.bowmark.ai/v1/sites/intro_co/expert \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"handle":"sophiaamoruso"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.intro_co.expert({ handle: "sophiaamoruso" });searchSearches intro.co's expert marketplace by keyword (a topic, skill or name.Arguments
Name Type Required querystringA topic, skill or name, e.g. "fundraising".Yes limitnumber1-100, default 20.No Returns
IntroCoSearchResultinterface IntroCoExpertSummary { id: number; name: string; /** Pass to expert({ handle }). */ handle: string | null; title: string; shortDescription: string; avatar: string | null; url: string; /** USD, for the default call length. */ sessionPrice: number | null; sessionMinutes: number | null; rating: number | null; ratingCount: number; verified: boolean; } interface IntroCoSearchResult { /** Total matches the site reports; experts holds at most limit of them. */ total: number; experts: IntroCoExpertSummary[]; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/intro_co/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.intro_co.search({ query: "fundraising" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.intro_co.search({"query": "fundraising"}))curl -X POST https://api.bowmark.ai/v1/sites/intro_co/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"fundraising"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.intro_co.search({ query: "fundraising" });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/intro_co/<function> - OpenAPI
/v1/sites/intro_co/openapi.json