# MCP Retrieval

MCP Retrieval — a Go MCP server with three tools: DuckDuckGo search, Bing Images, and page scraping into Markdown. No API keys required.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 23 repo stars
- Author: Role1776
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Role1776/mcp-retrieval
- Updated: 2026-10-24
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/mcp-retrieval

## What it does

The server hands the model three read-only tools. `web_search` runs queries against DuckDuckGo Lite, `web_search_images` pulls pictures from Bing Images, and `web_scrape` downloads pages and extracts the main article into Markdown. Each tool takes a list of queries or URLs and runs them in parallel. Results come back as structured JSON; clients that ignore `structuredContent` get the same data mirrored into a text block by the SDK.

Under the hood the `retrieval-go` library does the fetching. It impersonates real browsers at the TLS layer via uTLS, with optional rotation of browser fingerprints and proxies to stay ahead of bot protection. Two transports are available: `stdio` by default, plus `http` for remote deployments. Both expose the same toolset.

You run it as a Docker container — `ghcr.io/role1776/mcp-retrieval:0.1.10` — configured with `MCP_TRANSPORT`, `MCP_NAME`, `MCP_PATH`, `SERVER_PORT`, and `SERVER_READ_TIMEOUT`. Queries cap at 512 characters, URLs at 2048 and only `http`/`https`. Deduplication happens per query, not across the whole call: the same link found by two queries shows up in both results.

## Requirements
- Needs: Docker
- 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` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add --env MCP_TRANSPORT=<MCP_TRANSPORT> --env MCP_NAME=<MCP_NAME> --env MCP_PATH=<MCP_PATH> --env SERVER_PORT=<SERVER_PORT> --env SERVER_READ_TIMEOUT=<SERVER_READ_TIMEOUT> --transport stdio mcp-retrieval -- docker run -i --rm -e MCP_TRANSPORT -e MCP_NAME -e MCP_PATH -e SERVER_PORT -e SERVER_READ_TIMEOUT ghcr.io/role1776/mcp-retrieval:0.1.10
```
Replace <…> with your own values. 18 more environment variables are in the server README

### Codex

**Platform CLI**
```bash
codex mcp add mcp-retrieval --env MCP_TRANSPORT=<MCP_TRANSPORT> --env MCP_NAME=<MCP_NAME> --env MCP_PATH=<MCP_PATH> --env SERVER_PORT=<SERVER_PORT> --env SERVER_READ_TIMEOUT=<SERVER_READ_TIMEOUT> -- docker run -i --rm -e MCP_TRANSPORT -e MCP_NAME -e MCP_PATH -e SERVER_PORT -e SERVER_READ_TIMEOUT ghcr.io/role1776/mcp-retrieval:0.1.10
```
Replace <…> with your own values. 18 more environment variables are in the server README

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "mcp-retrieval": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "-e",
                "MCP_TRANSPORT",
                "-e",
                "MCP_NAME",
                "-e",
                "MCP_PATH",
                "-e",
                "SERVER_PORT",
                "-e",
                "SERVER_READ_TIMEOUT",
                "ghcr.io/role1776/mcp-retrieval:0.1.10"
            ],
            "env": {
                "MCP_TRANSPORT": "<MCP_TRANSPORT>",
                "MCP_NAME": "<MCP_NAME>",
                "MCP_PATH": "<MCP_PATH>",
                "SERVER_PORT": "<SERVER_PORT>",
                "SERVER_READ_TIMEOUT": "<SERVER_READ_TIMEOUT>"
            }
        }
    }
}
```
Replace <…> with your own values. 18 more environment variables are in the server README

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "mcp-retrieval": {
            "type": "stdio",
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "-e",
                "MCP_TRANSPORT",
                "-e",
                "MCP_NAME",
                "-e",
                "MCP_PATH",
                "-e",
                "SERVER_PORT",
                "-e",
                "SERVER_READ_TIMEOUT",
                "ghcr.io/role1776/mcp-retrieval:0.1.10"
            ],
            "env": {
                "MCP_TRANSPORT": "<MCP_TRANSPORT>",
                "MCP_NAME": "<MCP_NAME>",
                "MCP_PATH": "<MCP_PATH>",
                "SERVER_PORT": "<SERVER_PORT>",
                "SERVER_READ_TIMEOUT": "<SERVER_READ_TIMEOUT>"
            }
        }
    }
}
```
Replace <…> with your own values. 18 more environment variables are in the server README

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e MCP_TRANSPORT=<MCP_TRANSPORT> -e MCP_NAME=<MCP_NAME> -e MCP_PATH=<MCP_PATH> -e SERVER_PORT=<SERVER_PORT> -e SERVER_READ_TIMEOUT=<SERVER_READ_TIMEOUT> mcp-retrieval docker run -i --rm -e MCP_TRANSPORT -e MCP_NAME -e MCP_PATH -e SERVER_PORT -e SERVER_READ_TIMEOUT ghcr.io/role1776/mcp-retrieval:0.1.10
```
Replace <…> with your own values. 18 more environment variables are in the server README

## When to use it
- run web search for an agent without signing up for an API
- pull clean article text from a URL into the model context
- fetch images for several queries in one call
- avoid basic bot detection when hitting search engines
- deploy the server over HTTP instead of stdio

## Example prompts
- Search the web for recent pages about MCP servers and return five snippets.
- Scrape this article and give me the text without links, capped at 10000 characters.
- Find images for "Claude Code architecture" from the past week.

## Similar
- [Argus Retrieval](https://affpapa.org/en/nevibecode/mcp/argus-retrieval.md) — MCP server · ★ 9 repo stars
- [DuckDuckGo & Felo AI Search](https://affpapa.org/en/nevibecode/mcp/duckduckgo-felo-ai-search.md) — MCP server · 12697 installs
- [pinkpixel-dev-web-scout-mcp](https://affpapa.org/en/nevibecode/mcp/pinkpixel-dev-web-scout-mcp.md) — MCP server · ★ 152 repo stars
- [Private Web Search](https://affpapa.org/en/nevibecode/mcp/private-web-search.md) — MCP server
- [freeUnlimited-websearch](https://affpapa.org/en/nevibecode/skills/freeunlimited-websearch.md) — skill · 585 installs
- [Litescrape](https://affpapa.org/en/nevibecode/mcp/litescrape.md) — MCP server · ★ 1 repo stars

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
