Local Go MCP server: DuckDuckGo/Bing web + image search, readability scraping to Markdown.
To add MCP Retrieval to Claude, run the install command below. Restart Claude Code after adding it and its tools show up in your next conversation. It needs 23 environment variables, listed below.
Install
docker run -i --rm ghcr.io/role1776/mcp-retrieval:0.1.10Environment variables
MCP_TRANSPORTSet in your MCP configMCP_NAMESet in your MCP configMCP_PATHSet in your MCP configSERVER_PORTSet in your MCP configSERVER_READ_TIMEOUTSet in your MCP configSERVER_WRITE_TIMEOUTSet in your MCP configLOG_MODESet in your MCP configMAX_IDLE_CONNS_PER_HOSTSet in your MCP configMAX_QUERIESSet in your MCP configDEFAULT_RESULTSSet in your MCP configMAX_RESULTSSet in your MCP configDEFAULT_IMAGESSet in your MCP configMAX_IMAGESSet in your MCP configDEFAULT_TIMEOUT_MSSet in your MCP configMIN_TIMEOUT_MSSet in your MCP configMAX_TIMEOUT_MSSet in your MCP configDEFAULT_DOCUMENT_CHARSSet in your MCP configMAX_DOCUMENT_CHARSSet in your MCP configPROXY_SCHEMESet in your MCP configPROXY_HOSTSet in your MCP configPROXY_PORTSet in your MCP configPROXY_LOGINSet in your MCP configPROXY_PASSWORDSet in your MCP configWhat this does
MCP Retrieval exposes a set of tools to Claude over the Model Context Protocol. After you add it to claude_desktop_config.json (snippet above) and restart Claude Desktop, those tools become callable inside any conversation.
Requirements
This server needs the following environment variables to be set before it can run:
MCP_TRANSPORT MCP_NAME MCP_PATH SERVER_PORT SERVER_READ_TIMEOUT SERVER_WRITE_TIMEOUT LOG_MODE MAX_IDLE_CONNS_PER_HOST MAX_QUERIES DEFAULT_RESULTS MAX_RESULTS DEFAULT_IMAGES MAX_IMAGES DEFAULT_TIMEOUT_MS MIN_TIMEOUT_MS MAX_TIMEOUT_MS DEFAULT_DOCUMENT_CHARS MAX_DOCUMENT_CHARS PROXY_SCHEME PROXY_HOST PROXY_PORT PROXY_LOGIN PROXY_PASSWORD
Set these via the env object in your MCP config (see claude_desktop_config.json snippet above).
Frequently asked questions
How do I install MCP Retrieval?
The install section on this page carries the maker's install command for MCP Retrieval, as submitted. Restart your client afterwards and the tools appear in your next conversation.
Which clients work with MCP Retrieval?
This page carries setup and config for Claude Code. Any other MCP client that accepts a standard server config can connect to MCP Retrieval as well.
Does MCP Retrieval need an API key?
Yes. Before it can run, set these environment variables: MCP_TRANSPORT, MCP_NAME, MCP_PATH, SERVER_PORT, SERVER_READ_TIMEOUT, SERVER_WRITE_TIMEOUT, LOG_MODE, MAX_IDLE_CONNS_PER_HOST, MAX_QUERIES, DEFAULT_RESULTS, MAX_RESULTS, DEFAULT_IMAGES, MAX_IMAGES, DEFAULT_TIMEOUT_MS, MIN_TIMEOUT_MS, MAX_TIMEOUT_MS, DEFAULT_DOCUMENT_CHARS, MAX_DOCUMENT_CHARS, PROXY_SCHEME, PROXY_HOST, PROXY_PORT, PROXY_LOGIN, PROXY_PASSWORD. They go in the env block of your MCP config.
Imported from the Official MCP Registry. The details above come from the registry entry; the maker can claim this listing to correct them, add docs, and see its traffic.
Is this your MCP server?
Claim this listing to see its traffic, fix details yourself, and skip the review queue on future updates.
Add this badge to your README
Show visitors this server is listed in the ClaudeRules directory. The badge links straight to this listing.
[](https://clauderules.net/mcp/io-github-role1776-mcp-retrieval)<a href="https://clauderules.net/mcp/io-github-role1776-mcp-retrieval" target="_blank" rel="noopener noreferrer"><img src="https://clauderules.net/api/badge/io-github-role1776-mcp-retrieval" alt="Listed on clauderules.net" /></a>More Search MCP servers
microsoft/playwright-mcp
Official Microsoft Playwright MCP server, enabling LLMs to interact with web pages through structured accessibility snapshots
agent-infra/mcp-server-browser
📇 🏠 - Browser automation capabilities using Puppeteer, both support local and remote browser connection.
Serena MCP: the IDE for your agent
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.
mediar-ai/screenpipe
🎖️ 🦀 🏠 🍎 Local-first system capturing screen/audio with timestamped indexing, SQL/embedding storage, semantic search, LLM-powered history analysis, and event-triggered actions - enables building c
