69
/ 100
1 month ago
glama

agentfetch

An open-source web retrieval MCP server that fetches, crawls, and searches the web, returning clean markdown for AI agents. It integrates with Claude MCP, LangChain, and other frameworks for agentic web access.

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.

Install from

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
🔐
You'll be asked for 4 credentials: ANTHROPIC_API_KEY, BRAVE_SEARCH_API_KEY, SERPAPI_KEY, GOOGLE_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// required environment variables
This server reads these from process.env. You'll be asked to provide them before it can run.
configREDIS_URLRedis connection for caching + job queue
configSEARXNG_URLSearXNG instance for search (falls back to DuckDuckGo + Google + Bing)
🔐 secretANTHROPIC_API_KEYFor Claude-powered agent_extract
configANTHROPIC_MODELclaude-3-haiku-20240307 Claude model name for extraction
configOLLAMA_URLOllama endpoint for local LLM extraction
configAGENTFETCH_CACHE_TTL300 In-memory LRU cache TTL (seconds)
configOLLAMA_MODELllama3.2 Ollama model name
configAGENTFETCH_ROBOTS_CHECKfalse Enable robots.txt compliance
configAGENTFETCH_CRAWL_DBagentfetch_crawl.db SQLite path for crawl job persistence
configAGENTFETCH_PROXY_LISTComma-separated proxy URLs or JSON array
configAGENTFETCH_PROXY_STRATEGYround-robin round-robin or random
configAGENTFETCH_STATIC_TIMEOUT15 HTTP fetch timeout (seconds)
configAGENTFETCH_BROWSER_TIMEOUT30 Playwright browser timeout (seconds)
configAGENTFETCH_COOKIES_FILEPath to cookies file (Netscape or JSON)
configAGENTFETCH_MAX_RETRIES2 Max retries for failed requests
configAGENTFETCH_DOMAIN_DELAY0.5 Delay between requests to same domain
configAGENTFETCH_CACHE_SIZE100 Max entries in in-memory LRU cache
configAGENTFETCH_MIN_PROSE_RATIO0.4 Minimum alpha-char ratio for quality check
configAGENTFETCH_MIN_WORDS10 Minimum word count for quality check
configAGENTFETCH_JA3_PROFILEJA3 TLS profile override for curl_cffi
configAGENTFETCH_STEALTHtrue Enable browser stealth evasions in Playwright
configAGENTFETCH_STEALTH_BASIC_FALLBACKtrue Fall back to non-stealth browser if stealth fails
🔐 secretBRAVE_SEARCH_API_KEYBrave Search API key (enables brave engine, preferred over DuckDuckGo)
🔐 secretSERPAPI_KEYSerpAPI key (enables serpapi engine, preferred over Google scraping)
🔐 secretGOOGLE_API_KEYGoogle Custom Search API key (used by google engine when both key and CX are set)
configGOOGLE_CXGoogle Custom Search CX (required with GOOGLE_API_KEY)
configAGENTFETCH_SEARCH_RETRIES
configAGENTFETCH_SEARCH_TIMEOUT
// full audit trail
The full breakdown of what we checked, the deductions that landed, the network hosts, the dependency advisories, and concrete fix guidance is available to verified publishers.
// improvement guidance — verified publishers only
We have 5 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/sid1art-agentfetch-181krs)](https://m8ven.ai/mcp/sid1art-agentfetch-181krs)
commit: f07c5f6fa73392def0a3305c4e972e34a9977fab
code hash: b2b8ba872beed5bbc42afd85d0736ac783a2538172d3e2d14bbfdddb4761e653
verified: 6/18/2026, 10:28:56 AM
view raw JSON →