Context.dev MCP server for AI agents
Let Claude, ChatGPT or your own agent read Context.dev: 3 typed functions through one MCP server. No Context.dev API key needed.
- Site
- context.dev
- Functions
- 3
- Sign-in
- Not needed
- Works with
- MCP, HTTP, Node, Python
Connect
Just Context.dev
An MCP server for Context.dev 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/context_devEvery site
One MCP server for Context.dev 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 3
crawlCrawls a public website through Context.dev's documented API and returns its Markdown page records and crawl metadata.Arguments
Name Type Required urlstringYes maxPagesnumberNo Returns
ContextDevResponsetype ContextDevResponse = Record<string, unknown>;HTTP endpoint
POST https://api.bowmark.ai/v1/sites/context_dev/crawlCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.context_dev.crawl({ url: "<url>" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.context_dev.crawl({"url": "<url>"}))curl -X POST https://api.bowmark.ai/v1/sites/context_dev/crawl \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"url":"<url>"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.context_dev.crawl({ url: "<url>" });retrieveBrandRetrieves Context.dev's company and brand profile for a domain, including available logo, color, company, and social fields.Arguments
Name Type Required domainstringYes Returns
ContextDevResponsetype ContextDevResponse = Record<string, unknown>;HTTP endpoint
POST https://api.bowmark.ai/v1/sites/context_dev/retrieveBrandCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.context_dev.retrieveBrand({ domain: "context.dev" });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.context_dev.retrieveBrand({"domain": "context.dev"}))curl -X POST https://api.bowmark.ai/v1/sites/context_dev/retrieveBrand \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"domain":"context.dev"}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.context_dev.retrieveBrand({ domain: "context.dev" });searchSearches the live web through Context.dev's documented API and returns its ranked result records, optionally with Context.dev's page content.Arguments
Name Type Required querystringYes numResultsnumberNo Returns
ContextDevResponsetype ContextDevResponse = Record<string, unknown>;HTTP endpoint
POST https://api.bowmark.ai/v1/sites/context_dev/searchCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.context_dev.search({ query: "Context.dev API", numResults: 1 });import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.context_dev.search({"query": "Context.dev API", "numResults": 1}))curl -X POST https://api.bowmark.ai/v1/sites/context_dev/search \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"args":{"query":"Context.dev API","numResults":1}}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.context_dev.search({ query: "Context.dev API", numResults: 1 });
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/context_dev/<function> - OpenAPI
/v1/sites/context_dev/openapi.json