Fast, idiomatic Go MCP server for web search, image search, and page scraping to Markdown. Runs locally, no API keys, free.
An MCP server that gives an LLM three web tools: search, image search, and page scraping — no API keys required.
Tools · Quick start · Configuration · Retrieval engine · Architecture · Contributing
mcp-retrieval is a Model Context Protocol server written in Go. It exposes web retrieval capabilities to any MCP-compatible client (Claude Desktop, IDE agents, custom LLM apps) as three read-only tools. Under the hood it uses the retrieval-go library to search the web and fetch pages, returning results as clean Markdown ready to hand to a model.
The library needs no API keys: web search goes through DuckDuckGo Lite, image search through Bing Images, and page fetching runs the HTML through a readability extractor before converting it to Markdown. To stay reliable against bot protection it impersonates real browsers at the TLS level and can rotate both browser fingerprints and proxies — see Retrieval engine.
Both transports the MCP SDK supports are available and expose the identical tool set:
- stdio — the client launches the binary and talks over stdin/stdout (the default, ideal for desktop clients). - http — a long-running streamable HTTP server (useful for remote/shared deployments).
Tool Description :--- :--- websearch Runs one or more queries in parallel and returns per-query deduplicated, reranked snippets with links. websearchimages Runs one or more image queries in parallel and returns per-query deduplicated image results. webscrape Downloads one or more pages in parallel and returns the main article text as Markdown.
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/Role1776--mcp-retrieval.html)
MCP server for HasData's Web Scraping API: fetch any public URL through managed proxies, render JavaScript when needed, and get markdown, text, HTML or structured JSON. From 1 credit a call.
okf-memory/okf-agent-memoryGit-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zer
HasData/google-images-mcpMCP server for Google Images: image search with size, colour and type filters, 100 results a call with the source page and the full-resolution URL. 1,000 free credits every month.
Smitner-Studio/facetRender agent-written Markdown as a live local page, and send the human's click back to the agent as typed data. Human-in-the-loop approval gates for coding agents.
HasData/yelp-mcpMCP server for Yelp: business search, place details and the full review feed as JSON. Hosted, no Yelp Fusion key. 1,000 free credits every month.
HasData/glassdoor-mcpMCP server for Glassdoor: search job listings by keyword and location, read one posting in full with the employer rating and the salary figure with its provenance. 1,000 free credits every month.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.