Agentfetch
Wraps multiple web fetchers (Trafilatura, Jina Reader, FireCrawl, pypdf) behind a single MCP interface that routes requests based on URL type and keeps you under token budgets. Exposes four tools: fetch_url for single pages with token caps and caching, estimate_tokens to check size before committing context, fetch_multiple for up to 20 concurrent requests, and search_and_fetch for web search plus automatic result retrieval. Handles JS-heavy sites through FireCrawl, extracts PDFs locally, and falls back through a cost hierarchy when one fetcher fails. The routing is automatic, so you call one tool instead of wiring up four separate scrapers and a Redis layer yourself. Useful when your agent needs web content but you want to avoid blowing context windows on 50,000-token blog posts.
- tools
- 4
- auth
- Secret needed
- transport
- STDIO
- env vars
- 3
- last updated
- Apr 28, 2026
Tools
4 toolsPublic tool metadata for what this MCP can expose to an agent.
fetch_urlFetch a URL → clean Markdown + metadata + token count + cache info
Fetch a URL → clean Markdown + metadata + token count + cache info
No parameter schema in public metadata yet.
estimate_tokensGet a token count *before* fetching, so agents don't blow context windows on huge pages
Get a token count *before* fetching, so agents don't blow context windows on huge pages
No parameter schema in public metadata yet.
fetch_multipleFetch up to 20 URLs concurrently
Fetch up to 20 URLs concurrently
No parameter schema in public metadata yet.
search_and_fetchWeb search + fetch top N results in one round-trip
Web search + fetch top N results in one round-trip
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
JINA_API_KEYsecretJina Reader API key. Free tier ~1M tokens/mo at jina.ai/reader.
FIRECRAWL_API_KEYsecretFireCrawl API key for JS pages. 500 free credits at firecrawl.dev. Optional.
REDIS_URLRedis connection URL for response caching. Optional.
Readme
agentfetch-mcp
Web intelligence for AI agents — an MCP server that fetches URLs with token estimation, smart caching, and intelligent routing built in.
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.
This repository contains the open-source MCP server. For the hosted API + dashboard + billing, see www.agentfetch.dev.
What it does
Details
- Repository
- github.com/bch1212/agentfetch-mcp
- Categories
- Documents & Knowledge, Search & Web Crawling
- Package
agentfetch-mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
More from bch1212
Related Documents & Knowledge MCP servers
View all
Filewashcassilup/filewash-apiPrivacy-first file tools for AI agents — PDF & image ops, metadata scrubbing, background removal.0stars
Company Gicompany-gibraltar/company-gi-mcpGibraltar company tools: corporate tax, compliance deadlines, and PDF form generation.0starsCompany Gibraltarcompany-gibraltar/company-gibraltar-mcpGibraltar company tools: corporate tax, compliance deadlines, and PDF form generation.0stars
Ebenova Legal Docsdgtalquantumleap-ai/legal-docs-mcpGenerate 27 legal document types across 18 jurisdictions via Ebenova API.0stars
Forage - MCP Server for AI Agentsernestalabs/web-intelligence-mcpWeb intelligence, verified B2B contacts, and a persistent knowledge graph for AI agents.0stars