MCP Research Friend MCP Server

A friendly MCP server for web research - fetch pages and search the web

Local serverstdio

What is the MCP Research Friend MCP server?

Connect MCP Research Friend to Claude, Cursor or any other MCP client and it stops being a tab you switch to. A friendly MCP server for web research - fetch pages and search the web. The mcp research friend mcp server is what makes that connection.

What the server does

A friendly helper for AI assistants that need to look things up on the web and manage a local research stash.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • friendly_web_fetch — Fetches a web page and returns its content. By default, returns markdown with links preserved — ideal for LLMs. Uses
  • friendly_search — The friendly_search tool exposed by this server
  • friendly_web_extract — Extracts content from a URL. Auto-detects whether the URL points to a PDF or a web page and handles each appropriately
  • friendly_web_ask — Fetches a URL (PDF or web page) and has an LLM answer questions about it. Auto-detects content type. The document is processed in a separate context
  • stash_open_inbox — Open the stash inbox folder in your file manager for easier drag-and-drop
  • stash_process_inbox — Process files in inbox/, classify them into topics, extract text, and store results. For long documents, classification uses sampled sections
  • reindex_stash — Regenerate summaries, re-allocate topics, and update store metadata for stashed documents. If ids is omitted or empty, all documents are reindexed
  • stash_list — The stash_list tool exposed by this server
  • stash_search — Search filenames and content across the stash. All search terms must be present (AND logic). Filename matches are listed first. Use quotes for exact
  • stash_extract — Extract content from a stashed document for reading. Use line numbers from stash_search results to jump directly to matches
  • stash_ask — Have an LLM answer questions about a stashed document. The document is processed in a separate context, keeping your main conversation compact

Installation

Installation goes through your MCP client rather than a global install: point it at playwright on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

Where it fits

This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. MCP Research Friend's toolset — friendly_web_fetch, friendly_search, friendly_web_extract and 8 more — is a fair guide to whether it matches your workflow. It is maintained by permacommons; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against MCP Research Friend's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 11 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch MCP Research Friend.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
friendly_web_fetchFetches a web page and returns its content. By default, returns markdown with links preserved — ideal for LLMs. Uses [Readability](https://github.com/mozilla/readability) to extract the main content (stripping navigation
friendly_searchThe friendly_search tool exposed by this server.
friendly_web_extractExtracts content from a URL. Auto-detects whether the URL points to a PDF or a web page and handles each appropriately.
friendly_web_askFetches a URL (PDF or web page) and has an LLM answer questions about it. Auto-detects content type. The document is processed in a separate context, keeping your main conversation compact.
stash_open_inboxOpen the stash inbox folder in your file manager for easier drag-and-drop.
stash_process_inboxProcess files in inbox/, classify them into topics, extract text, and store results. For long documents, classification uses sampled sections (start/middle/end plus a few random chunks) to improve topic accuracy.
reindex_stashRegenerate summaries, re-allocate topics, and update store metadata for stashed documents. If ids is omitted or empty, all documents are reindexed.
stash_listThe stash_list tool exposed by this server.
stash_searchSearch filenames and content across the stash. All search terms must be present (AND logic). Filename matches are listed first. Use quotes for exact phrases.
stash_extractExtract content from a stashed document for reading. Use line numbers from stash_search results to jump directly to matches.
stash_askHave an LLM answer questions about a stashed document. The document is processed in a separate context, keeping your main conversation compact.

How to install the MCP Research Friend MCP server

{
  "mcpServers": {
    "research-friend": {
      "command": "npx",
      "args": ["-y", "playwright"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use MCP Research Friend to friendly web fetch.
  • Use MCP Research Friend to friendly search.
  • Use MCP Research Friend to friendly web extract.

Frequently asked questions

It connects MCP Research Friend to MCP-compatible AI assistants such as Claude and Cursor, exposing 11 tools (friendly_web_fetch, friendly_search, friendly_web_extract, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with MCP Research Friend directly.