Deep Research Mcp Server

io.github.PerufitlifePublished by GitHub account Perufitlifev1.0.2Updated Oct 24, 2026

Web search, clean page reading & one-call research dossiers for AI agents. No API key.

VerifiedSTDIODesktop onlyWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

A local MCP server that gives an AI assistant web search, clean Markdown page reading, and one-call multi-source research dossiers without any API key.

What you can do
Search the web and get ranked results with title, URL and snippet for each hit. Fetch a URL and return its main content as clean, LLM-ready Markdown. Run a one-call research flow that searches, reads the top sources in parallel and returns a citation-ready dossier, skipping sources that fail to load and reporting how many were read.
When to use it
Useful when you want an assistant to research topics on the open web, gather and cite multiple sources, or read individual pages as clean text, without signing up for a search or scraping API.
Requirements
Runs as a local process over stdio, typically launched with npx from the npm package, so Node.js and network access are needed. No API key or environment variables are declared. Desktop clients such as Claude Desktop, Cursor or Windsurf are the intended hosts.
Before you install
It fetches arbitrary URLs and sends search queries to public metasearch services (SearXNG with a DuckDuckGo fallback), so queries and requested pages leave your machine. Some sites block automated fetches, and very fresh pages may not be indexed. A hosted Apify variant is also mentioned, which would involve a third-party service.

Installation

In SourceWeft

  1. Open Deep Research Mcp Server in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Deep Research MCP

An MCP server that gives Claude, Cursor, or any AI agent real web-research skills — web search, clean-Markdown page reading, and one-call research dossiers — with no OpenAI / Perplexity / Tavily key required. Your agent is the LLM, so it does the synthesis; this server does the hard part (finding sources, fetching them, and stripping pages down to clean, LLM-ready Markdown).

Tools

ToolWhat it does
web_searchSearch the web → ranked {title, url, snippet}.
read_urlFetch a URL → main content as clean Markdown.
deep_researchSearch → read the top N sources in parallel → a citation-ready dossier.

Install

Claude Desktop / Cursor / Windsurf

Add to your MCP config (claude_desktop_config.json, Cursor mcp.json, etc.):

json
{  "mcpServers": {    "deep-research": {      "command": "npx",      "args": ["-y", "deep-research-mcp-server"]    }  }}

Then ask your agent: "Use deep_research to compare the top open-source vector databases in 2026 and summarize with citations."

Why this over Tavily / Firecrawl?

  • No API key — search and page-reading run locally; your agent supplies the intelligence.
  • Agentic — deep_research orchestrates multi-source reading and returns a citation-ready dossier, not a single page.
  • Free & open — MIT licensed, npx and go.

Notes

  • Uses public metasearch (SearXNG) with a DuckDuckGo fallback; very fresh pages may not be indexed yet.
  • Some sites block automated fetches; deep_research skips failed sources and reports how many it read.

Also available as a hosted Apify Actor: apify.com/renzomacar/deep-research-mcp. Built by Renzo Madueño.

Source: README.md at commit 158a4f4

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.2LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.