io.github.nkapila6/mcpsurfr

mcpsurfr

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

151 1 tool GitHub PyPI

No known CVEs

MIT license

Actively maintained

Last commit 5d ago

Works with most clients

Transport: stdio, sse, http

1 tool

Grade F

MCPpedia last refreshed this data 2d ago

Edit this pageView history

io.github.nkapila6/mcpsurfr is an MCP server that local web search with multi-engine deep research and on-device re-ranking. No API keys. Its tool list has not been published yet over stdio, sse and http, requires no API key, and scores 62/100 on MCPpedia's security, maintenance and efficiency rubric.

Step 1

Install in your client

Config is the same across clients - only the file and path differ.

Supported in Claude Desktopstdio, sse, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "mcpsurfr": {
      "args": [
        "--from",
        "git+https://github.com/nkapila6/mcpsurfr",
        "mcpsurfr"
      ],
      "command": "uvx"
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/io-github-nkapila6-mcpsurfr)](https://mcppedia.org/s/io-github-nkapila6-mcpsurfr)

Read me

What io.github.nkapila6/mcpsurfr does

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

Test This Server

Run this in your terminal to verify the server starts. Then let us know if it worked - your result helps other developers.

uvx 'mcpsurfr' 2>&1 | head -1 && echo "✓ Server started successfully"

After testing, let us know if it worked:

Loading README…

Scored, not listed

Why this score

Five weighted categories - click any category to see the underlying evidence.

Score breakdown

62/100across 5 weighted dimensions

How we score →

0255075100

−38

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked mcpsurfr against OSV.dev.

Inventory

Tools (1)

Click any tool to inspect its schema.

Community

Reviews

Be the first to review

Have you used this server?

Share your experience - it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is io.github.nkapila6/mcpsurfr safe to use?: io.github.nkapila6/mcpsurfr has no known CVEs as of the latest MCPpedia security scan. Authentication requirements were not detected automatically - check the project's documentation before connecting in a shared environment. Licensed under MIT.
How do I install io.github.nkapila6/mcpsurfr?: io.github.nkapila6/mcpsurfr supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What can io.github.nkapila6/mcpsurfr do?: io.github.nkapila6/mcpsurfr provides 1 tool: env. See the full tools list on the server page for descriptions and parameters.
What AI clients work with io.github.nkapila6/mcpsurfr?: io.github.nkapila6/mcpsurfr is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.
Is io.github.nkapila6/mcpsurfr actively maintained?: io.github.nkapila6/mcpsurfr is actively maintained - last commit was 5 days ago. It has 151 GitHub stars.

Similar servers

Others in search

View all →

Crw95

Open-source web scraper for AI agents with scrape, crawl, and map tools

1.3k 3

Tavily Mcp95

MCP server for advanced web search using Tavily

2.5k 4

Socraticode MCP Server95

MCP server for enterprise local codebase indexing, semantic search, and code dependency graphs.

3.4k 4

Modelcontextprotocol94

The official MCP server implementation for the Perplexity API Platform

2.6k 4

MCP Security Weekly

Get CVE alerts and security updates for io.github.nkapila6/mcpsurfr and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

flowchart LR Q["query + keywords"] --> S["ddgs several engines, no keys"] S --> R["re-rank on device"] R --> F["fetch top pages main text, PDFs"] F -->|search| P["best passages ~1k tokens"] F -->|rag_search_ddgs deep_research| W["full pages shared budget"]

Frequently Asked Questions

Is io.github.nkapila6/mcpsurfr safe to use?

io.github.nkapila6/mcpsurfr has no known CVEs as of the latest MCPpedia security scan. Authentication requirements were not detected automatically - check the project's documentation before connecting in a shared environment. Licensed under MIT.

How do I install io.github.nkapila6/mcpsurfr?

io.github.nkapila6/mcpsurfr supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.

What can io.github.nkapila6/mcpsurfr do?

io.github.nkapila6/mcpsurfr provides 1 tool: env. See the full tools list on the server page for descriptions and parameters.

What AI clients work with io.github.nkapila6/mcpsurfr?

io.github.nkapila6/mcpsurfr is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.

Is io.github.nkapila6/mcpsurfr actively maintained?

io.github.nkapila6/mcpsurfr is actively maintained - last commit was 5 days ago. It has 151 GitHub stars.

Local web search for your LLM over MCP. No API keys, and results are ranked on your machine.
Formerly mcp-local-rag.

flowchart LR
    Q["query + keywords"] --> S["ddgs<br>several engines, no keys"]
    S --> R["re-rank<br>on device"]
    R --> F["fetch top pages<br>main text, PDFs"]
    F -->|search| P["best passages<br>~1k tokens"]
    F -->|rag_search_ddgs<br>deep_research| W["full pages<br>shared budget"]

What's in it:

No API keys. Searches go through ddgs. Its auto mode asks several engines at once and skips blocked ones.
Ranked locally. A small MobileBERT model on plain numpy re-ranks results, so only the best pages get fetched.
Clean text. Pages are fetched with browser impersonation, and only the main content is kept: no menus, cookie banners or footers. Code blocks and tables keep their lines. PDFs are read too (text layer, first 50 pages), and docs sites that publish markdown copies of their pages (llms.txt) are read from those. The same page under two URLs comes back once.
Passages instead of pages. search returns just the paragraphs that answer the question, about a tenth of the tokens, and deep_research can do the same per search term. When nothing matches well, search can ask you whether you want the full pages instead.
Reads the sites that block scrapers. Stack Overflow and the other Stack Exchange sites, Wikipedia, GitHub, Hacker News, PyPI, npm and crates.io go through their free APIs: questions with the accepted answer first, articles by section, READMEs and raw files, HN threads with their comments, and packages with their latest version, release date and README.
Titles and dates. Every page and passage carries its title, and its publish date when the page or news

... View full README on GitHub