Token-budgeted web fetch for AI agents — auto-routes Jina, FireCrawl, Trafilatura, PDF.
Token-budgeted web fetch for AI agents — auto-routes Jina, FireCrawl, Trafilatura, PDF. The agentfetch mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 10 defined tools rather than through you.
AgentFetch sits between your agent and the open web. Instead of integrating Jina, FireCrawl, pypdf, and your own caching layer separately, agents call one MCP tool and AgentFetch handles routing, caching, token budgeting, and clean Markdown extraction automatically.
Everything the assistant can do here goes through one of these:
Pay-per — call pricing from $0.001/fetchfetch_url — Fetch a URL → clean Markdown + metadata + token count + cache infoestimate_tokens — Get a token count before fetching, so agents don't blow context windows on huge pagesfetch_multiple — Fetch up to 20 URLs concurrentlysearch_and_fetch — Web search + fetch top N results in one round-tripFeature — AgentFetchJINA_API_KEY — RecommendedFIRECRAWL_API_KEY — OptionalREDIS_URL — OptionalCACHE_TTL_SECONDS — OptionalYou will need 3 environment variables: JINA_API_KEY, FIRECRAWL_API_KEY, REDIS_URL. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
Plenty of search and retrieval servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Agentfetch's toolset — Pay-per, fetch_url, estimate_tokens and 7 more — is a fair guide to whether it matches your workflow. It is maintained by bch1212; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| Pay-per | call pricing from $0.001/fetch |
| fetch_url | Fetch a URL → clean Markdown + metadata + token count + cache info |
| estimate_tokens | Get a token count *before* fetching, so agents don't blow context windows on huge pages |
| fetch_multiple | Fetch up to 20 URLs concurrently |
| search_and_fetch | Web search + fetch top N results in one round-trip |
| Feature | AgentFetch |
| JINA_API_KEY | Recommended |
| FIRECRAWL_API_KEY | Optional |
| REDIS_URL | Optional |
| CACHE_TTL_SECONDS | Optional |
{
"mcpServers": {
"agentfetch": {
"command": "uvx",
"args": ["agentfetch-mcp"],
"env": {
"JINA_API_KEY": "your-value",
"FIRECRAWL_API_KEY": "your-value",
"REDIS_URL": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| JINA_API_KEY | Credential the server authenticates with. | Yes |
| FIRECRAWL_API_KEY | Credential the server authenticates with. | Yes |
| REDIS_URL | Endpoint or connection string the server talks to. | Yes |
The simplest web tool that matters — fetch any URL and get model-ready markdown back.
Industrial-strength web extraction — render, scrape, crawl and search entire sites into clean markdown.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Put 6,000+ pre-built scrapers at your assistant's fingertips through one MCP endpoint.