mcpbeat Sign in

mcpsurfr MCP Server

local only

mcpsurfr runs on your own machine — the client starts it, so there is no endpoint to ping. 778 installs a week from pypi. Last commit 29 Oct 2026.

Local web search with multi-engine deep research and on-device re-ranking. No API keys.

Installs per day peak 643 · avg 25
a month agotoday
778
Installs / week
pypi · mcpsurfr
150
Stars
18 open issues
29 Oct 2026
Last commit
from GitHub
MIT
License
Python

Nothing serious here today

Today is the operative word: we check mcpsurfr every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

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 mcpsurfr -- uvx mcpsurfr
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "mcpsurfr": {
      "command": "uvx",
      "args": [
        "mcpsurfr"
      ]
    }
  }
}
~/.codex/config.toml
[mcp_servers.mcpsurfr]
command = "uvx"
args = ["mcpsurfr"]
.cursor/mcp.json
{
  "mcpServers": {
    "mcpsurfr": {
      "command": "uvx",
      "args": [
        "mcpsurfr"
      ]
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "mcpsurfr": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mcpsurfr"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: MCPSURFR_MAX_CHARS (Text budget per call for the full-page tools, shared across pages (~4 chars per token)).

Alternatives to mcpsurfr

same job, measured the same way
My Websearch
by wtznicy

MyWebSearch - multi-engine web search MCP server, CLI and local daemon. No API keys required.

1 618 installs/wk local only
Web Search
by hec-ovi

Keyless multi-engine web search, fetch, and clean-Markdown read for AI agents. No API keys.

92 installs/wk local only
Free Search
by sweetcornna

No-API-key web search, page fetching and document reading across many engines. Local-first.

3 084 installs/wk local only
YaCy peer-to-peer search
by pad01g

Web search, crawling and ranking evaluation on your own YaCy peer: no API key, no central service.

local only
DeepSeek Search Everywhere
by radoxtech

Web search, page fetching and multi-source research via the DeepSeek Search & Fetch API.

2 054 installs/wk local only
Searchpin — Free Web Search for AI Agents
by telly6

Free web search for AI agents — multi-engine parallel search, smart ranking, no sign-up, no limits

132 installs/wk local only
Search Memory
by kefyusuf

Free web search and long-term memory for AI assistants. No API keys; data stays local.

561 installs/wk local only
Anyfetch
by aliasmode

Web search and web fetch with no API keys. Reads the sites that refuse AI agents.

155 installs/wk local only

mcpsurfr — questions

Answers built from our own checks of this server.

Why is there no uptime for mcpsurfr?
mcpsurfr 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 mcpsurfr was installed 778 times last week.
How do I connect mcpsurfr?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls mcpsurfr straight from pypi; nothing to host, nothing to sign up for.
How many people use mcpsurfr?
The pypi package mcpsurfr was installed 778 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is mcpsurfr open source?
Yes — it is published under the MIT licence, written in Python, 150 stars on GitHub and 18 open issues. The source link is on this page, so you can read exactly what it does with your data before you connect it.