Agentfetch MCP Server

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. It runs locally over stdio via the published package.

People connecting web scraping tools to Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-06-06 · ★ 3 · #54 OF 78 MAINTAINED WEB SCRAPING · VERIFIED 2026-08-25

MIT · Python servers · how we verify → /methodology

01 · Install Agentfetch

before you install - you'll need

Set JINA_API_KEY before connecting. FIRECRAWL_API_KEY, REDIS_URL are optional or environment-specific per the README.

Claude Code

claude mcp add bch1212-agentfetch-mcp -- uvx agentfetch-mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "bch1212-agentfetch-mcp": {
      "command": "uvx",
      "args": [
        "agentfetch-mcp"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

pypi package agentfetch-mcp - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.bch1212 is GitHub-verified and matches the repo owner

03 · What Agentfetch can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

v1.0.1 · 2026-06-06

AgentFetch MCP discovery release.\n\n- PyPI package: agentfetch-mcp v1.0.1\n- Glama listing: Already listed in awesome-mcp-servers\n- Hosted API:

04 · Who maintains Agentfetch

agentfetch is maintained by bch1212. We track 11 MCP servers from bch1212 - 11 actively maintained, 5 combined GitHub stars, oldest repo from Apr 2026.

05 · Facts

repository: github.com/bch1212/agentfetch-mcp
category: web scraping - ranked #54 of 78 actively-maintained web scraping servers as of 2026-08-25.
release cadence: 1 release in the last 90 days (latest 2026-06-06)
registry: io.github.bch1212/agentfetch (active, first published 2026-04-28)
packages: pypi:agentfetch-mcp

06 · Agentfetch FAQ

What is Agentfetch?

Is Agentfetch still maintained?

Yes - as of 2026-08-25, its last commit was 2026-06-06 and it shipped 1 release in the last 90 days. We re-verify nightly.

How do I install Agentfetch?

Run `uvx agentfetch-mcp`. The README documents 3 environment variables (JINA_API_KEY, FIRECRAWL_API_KEY, REDIS_URL) to set first. Set JINA_API_KEY before connecting. FIRECRAWL_API_KEY, REDIS_URL are optional or environment-specific per the README. You can also paste the ready-made client config above.

Does Agentfetch run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Agentfetch

Alternatives to Agentfetch

Maintained web scraping servers if Agentfetch isn't the fit.

Pairs well with

Servers that cover what Agentfetch doesn't - only shown when the pairing reason fits the companion.

More web scraping MCP servers · Parkour MCP · Searchts · Amazon Scraper API · Jobseek · Crawleo MCP

More Python MCP servers · Beever Atlas · OpenSTAAD MCP Server · FAOSTAT MCP · Genefoundry · RDL MCP Server · see all