# Infobroker

> Infobroker is a free MCP server for web search and scraping. One research server for web search, page extraction, citations and fact checking. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Free
- **Platforms:** CLI, macOS, Linux, Windows
- **Repository:** https://github.com/flukeatzerocool/infobroker
- **MCP Registry name:** io.github.flukeatzerocool/infobroker
- **Categories:** [web search and scraping](https://ai-powered.com/categories/web-search-and-scraping), [knowledge and memory](https://ai-powered.com/categories/knowledge-and-memory)
- **Listing updated:** 2026-11-18

## About

Infobroker routes a query to whichever source can answer it. The README counts twenty-one providers that need no setup, such as DuckDuckGo, Wikipedia and academic and archive sources, and five more that unlock with a key or self-hosting: Exa, Tavily, Yep, CORE and a SearXNG instance. If a provider fails, the request falls through a configurable chain.

Search can go deeper than links: a deep read fetches top results and ranks passages against the query, and an analyze option adds topic terms, entities and a dated timeline. Fetching a URL returns clean Markdown through Jina Reader, can answer a question from a page, and reports when a paywalled page is blocked, falling back to metadata or an archive snapshot.

A verification tool cross-checks independent sources to separate established claims from contested ones. It also includes a provider-inspection tool covering quotas, uptime and a privacy posture for each backend, and bundled client skills for turning research into writing. It needs Node.js 24 or later.

## Features

- **Unified search:** One call queries many providers and falls back when one fails.
- **Passage ranking:** Deep reads rank page passages against your question.
- **Clean page fetch:** Returns readable Markdown and flags blocked pages.
- **BibTeX citations:** Returns scholarly references ready to paste.
- **Claim verification:** Cross-references independent sources.
- **Provider inspection:** Shows quota, uptime and privacy posture per source.

## Good for

- Research a topic across web, academic and news sources
- Pull the passages from a long page that answer one question
- Generate BibTeX references for a set of papers
- Check whether a claim is established or contested
- Choose a privacy-friendly source for a sensitive query

## Install

### Claude Code (Terminal)

```sh
claude mcp add infobroker --env INFOBROKER_EXA_API_KEY='<INFOBROKER_EXA_API_KEY>' --env INFOBROKER_TAVILY_API_KEY='<INFOBROKER_TAVILY_API_KEY>' --env INFOBROKER_YEP_API_KEY='<INFOBROKER_YEP_API_KEY>' -- npx -y infobroker
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "infobroker": {
      "command": "npx",
      "args": [
        "-y",
        "infobroker"
      ],
      "env": {
        "INFOBROKER_EXA_API_KEY": "<INFOBROKER_EXA_API_KEY>",
        "INFOBROKER_TAVILY_API_KEY": "<INFOBROKER_TAVILY_API_KEY>",
        "INFOBROKER_YEP_API_KEY": "<INFOBROKER_YEP_API_KEY>"
      }
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "infobroker": {
      "command": "npx",
      "args": [
        "-y",
        "infobroker"
      ],
      "env": {
        "INFOBROKER_EXA_API_KEY": "<INFOBROKER_EXA_API_KEY>",
        "INFOBROKER_TAVILY_API_KEY": "<INFOBROKER_TAVILY_API_KEY>",
        "INFOBROKER_YEP_API_KEY": "<INFOBROKER_YEP_API_KEY>"
      }
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "infobroker": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "infobroker"
      ],
      "env": {
        "INFOBROKER_EXA_API_KEY": "<INFOBROKER_EXA_API_KEY>",
        "INFOBROKER_TAVILY_API_KEY": "<INFOBROKER_TAVILY_API_KEY>",
        "INFOBROKER_YEP_API_KEY": "<INFOBROKER_YEP_API_KEY>"
      }
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "infobroker": {
      "command": "npx",
      "args": [
        "-y",
        "infobroker"
      ],
      "env": {
        "INFOBROKER_EXA_API_KEY": "<INFOBROKER_EXA_API_KEY>",
        "INFOBROKER_TAVILY_API_KEY": "<INFOBROKER_TAVILY_API_KEY>",
        "INFOBROKER_YEP_API_KEY": "<INFOBROKER_YEP_API_KEY>"
      }
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "infobroker": {
      "command": "npx",
      "args": [
        "-y",
        "infobroker"
      ],
      "env": {
        "INFOBROKER_EXA_API_KEY": "<INFOBROKER_EXA_API_KEY>",
        "INFOBROKER_TAVILY_API_KEY": "<INFOBROKER_TAVILY_API_KEY>",
        "INFOBROKER_YEP_API_KEY": "<INFOBROKER_YEP_API_KEY>"
      }
    }
  }
}
```

## Tools

- `search_web`: Send a query to every capable provider, with deep read and analysis options.
- `fetch_page`: Fetch a URL as clean Markdown, optionally answering a question.
- `get_citations`: Return scholarly references as BibTeX.
- `inspect_providers`: Show configured sources, quota status and privacy posture.
- `verify_claims`: Run a multi-source verification pass on claims.

## FAQ

### Do I need API keys?

Most providers work without one; CORE needs a free key, and Exa, Tavily and Yep are optional keyed providers.

### How do I start it?

Run npx -y infobroker; Node.js 24 or later is required.

### Can I self-host search?

Yes, point INFOBROKER_SEARXNG_URL at a SearXNG instance for full query privacy.

### How many tools are there?

The README says seven tools across twenty-six providers.

### Is Infobroker free?

Yes. Infobroker is free to use.

### How do I add Infobroker to Claude Code?

Run this command in your terminal: claude mcp add infobroker --env INFOBROKER_EXA_API_KEY='<INFOBROKER_EXA_API_KEY>' --env INFOBROKER_TAVILY_API_KEY='<INFOBROKER_TAVILY_API_KEY>' --env INFOBROKER_YEP_API_KEY='<INFOBROKER_YEP_API_KEY>' -- npx -y infobroker

### What are the best alternatives to Infobroker?

The closest alternatives to Infobroker are Scrapling MCP Server, Codebase Memory, XERJ, Firecrawl MCP Server and Claude Code Ultimate Guide.

## Where this comes from

- Description: written from the project's README.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [Scrapling MCP Server](https://ai-powered.com/mcp/scrapling-mcp-server): Scrapling MCP Server is an open-source MCP server for web search and scraping.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Firecrawl MCP Server](https://ai-powered.com/mcp/firecrawl-mcp-server): Firecrawl MCP Server is a freemium MCP server for web search and scraping.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Douyin_TikTok_Download_API](https://ai-powered.com/mcp/douyin-tiktok-download-api): Douyin_TikTok_Download_API is an open-source MCP server for web search and scraping.
- [SearXNG Search](https://ai-powered.com/mcp/searxng-search): SearXNG Search is an open-source MCP server for web search and scraping.
- [Nautilus Compass Memory](https://ai-powered.com/mcp/nautilus-compass-memory): Nautilus Compass Memory is an open-source MCP server for knowledge and memory.

---
Source: https://ai-powered.com/mcp/infobroker
