mcpbeat Sign in

webfetch MCP Server

local only

webfetch runs on your own machine — the client starts it, so there is no endpoint to ping. 94 installs a week from pypi. Last commit 23 Jul 2026.

Self-hosted web search for LLM agents: search -> fetch -> rank pipeline with semantic caching

Installs per day peak 33 · avg 16 · -18% w/w
a month agotoday
94
Installs / week
pypi · webfetch-llm
55
Stars
0 open issues
23 Jul 2026
Last commit
0 releases in 90 days
MIT
License
Python

What the code does

We read the source, 22 h ago · rules 3dff92dd89df

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Builds a database query by concatenation webfetch/receipts.py:149, [пакет] webfetch/receipts.py:149
    from webfetch.update_check import available_update
    notice = available_update()
    if notice:
        print("\n" + notice)
        __import__(module)

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add webfetch -- uvx webfetch-llm
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "webfetch": {
      "args": [
        "webfetch-llm"
      ],
      "command": "uvx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.webfetch]
command = "uvx"
args = ["webfetch-llm"]
.cursor/mcp.json
{
  "mcpServers": {
    "webfetch": {
      "args": [
        "webfetch-llm"
      ],
      "command": "uvx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "webfetch": {
      "args": [
        "webfetch-llm"
      ],
      "command": "uvx"
    }
  }
}

This one needs environment variables set before it will start: BRAVE_API_KEY (Optional - adds Brave to the multi-engine fusion. DDG works with no keys at all.), SERPER_API_KEY (Optional - adds Serper (Google results) to the multi-engine fusion.), TAVILY_API_KEY (Optional - adds Tavily to the multi-engine fusion.), WEBFETCH_PROVIDER (Optional - search strategy: multi (RRF fusion of available engines, default), fallback (priority failover), or a single engine name like ddg.). The author declared them in the registry entry; get the values from the project itself.

Alternatives to webfetch

same job, measured the same way
Wayforth
by wayforthofficial

Search engine and payment rail for AI agents. 2,300+ services, semantic ranking.

161 installs/wk local only
Linkup
by mcparmory

Search the web and fetch pages with sourced results, optimized for AI agents

223 installs/wk local only
Agentsearch MCP
by isaiahdupree

LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.

3 tools answering
Webshift
by annibale-x

Rust MCP server for denoised web search — fetch, clean, and rerank web content for AI agents.

local only
Webshift
by x-hannibal

Rust MCP server for denoised web search — fetch, clean, and rerank web content for AI agents.

local only
Webshift
by x-monk

Rust MCP server for denoised web search — fetch, clean, and rerank web content for AI agents.

local only
SearchForge
by divyanshu-iitian

Free open-source web search and page reading for LLMs, AI agents, and RAG.

local only
Web Search
by groundroute

Web search for AI agents — one tool across 6 engines, routed to the cheapest + cached.

answering

webfetch — questions

Answers built from our own checks of this server.

Why is there no uptime for webfetch?
webfetch runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package webfetch-llm was installed 94 times last week.
How do I connect webfetch?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls webfetch-llm straight from pypi; nothing to host, nothing to sign up for.
How many people use webfetch?
The pypi package webfetch-llm was installed 94 times in the last week. Week over week that is -18%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is webfetch open source?
Yes — it is published under the MIT licence, written in Python and 55 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.