lachy3433/contextfetch-mcp

MCP server for ContextFetch: neural web search and clean, LLM-ready Markdown for AI agents from $0.75 per 1,000 searches. Works with zero signup: no key needed for the free tier.
## Install
Claude Code (one line, keyless):
bash
claude mcp add contextfetch -- npx -y @contextfetch/mcp
With a paid key:
bash
claude mcp add contextfetch -e CONTEXTFETCHAPIKEY=yourkey -- npx -y @contextfetch/mcp
Cursor: add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project):
json
"mcpServers": {
"contextfetch": {
"command": "npx",
"args": ["-y", "@contextfetch/mcp"],
"env": { "CONTEXTFETCHAPIKEY": "yourkey" }
Windsurf: add to ~/.codeium/windsurf/mcpconfig.json:
json
"mcpServers": {
"contextfetch": {
"command": "npx",
"args": ["-y", "@contextfetch/mcp"],
"env": { "CONTEXTFETCHAPIKEY": "yourkey" }
To use the free tier, drop the env block (or leave CONTEXTFETCHAPIKEY empty). The same JSON works in Claude Desktop's claudedesktopconfig.json and in any other MCP client that launches stdio servers.
Requires Node.js 18 or newer.
## Tools
| Tool | Arguments | What it does | Cost |
| contextfetchsearch | query, numresults (1-25, default 5), includedomains?, excludedomains? | Web search. Each result comes back as title, URL and only the passages relevant to your query (cross-encoder pruned Markdown). | 1 credit |
| contextfetchextracturl | url, query? | Any public page (docs, articles, GitHub files, arXiv) as clean Markdown with tables kept. With query, returns only the relevant passages. | 1 credit |
| contextfetchfindsimilar | url, numresults (1-25, default 5) | Pages similar to a URL, excluding its own domain. | 1 credit |
| contextfetchresearch | query, subqueries? (up to 5), numresultsperquery (1-10, default 5) | Server-side research: runs the sub-queries concurrently, dedupes pages by URL, ranks them all against query with the cross-encoder and returns one Markdown evidence pack (numbered [n] sources with their query-pruned passages, quoted verbatim; nothing generated), headed by the sub-queries, source count, tokens and credits used. | 1 credit per sub-query (max 5) |
| contextfetchdeepresearch | query, subqueries? (up to 3), numresultsperquery (1-25, default 5; at most 10 used) | The earlier name of contextfetchresearch, kept for existing setups: same server-side evidence pack, up to 3 sub-queries. | 1 credit per sub-query (max 3) |
| contextfetchanswer | query, numresults (1-10, default 5) | Extractive answer: the best-scoring passages of the top pages, quoted verbatim with [n] markers and a numbered source list. No text is generated, so it suits factual lookups more than open-ended questions. | 1 credit |
| contextfetchcrawl | url, maxdepth (0-3, default 1), limit (1-50, default 10), query?, includepaths?, excludepaths? (regexes on the URL path) | Crawls one site from url (same-site links, robots.txt obeyed) and returns each page as Markdown with its depth. With query, pages are ranked by relevance and pruned to the relevant passages. | 1 credit per page returned |
| contextfetchmap | url, limit (1-5,000, default 100), includepaths?, excludepaths? | Lists a site's URLs from its sitemaps and the start page's links without fetching the pages. | 1 credit |