# Robin: AI-Powered Dark Web OSINT

Dark web OSINT tool over Tor for AI agents. Queries onion search engines, scrapes content, and synthesizes investigation findings with an LLM.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed · ★ 7658
- Author: apurvsinghgautam
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/apurvsinghgautam/robin
- Updated: 2026-10-03
- HTML: https://affpapa.org/en/nevibecode/mcp/robin-ai-powered-dark-web-osint

## What it does

Robin gives coding agents access to Tor network searches. It refines queries, queries onion search engines, and extracts text from pages. The connected model filters noise and drafts a concise intelligence summary.

The tool runs inside Docker and relies on Tor running on the host system. Install Tor with `apt install tor` or `brew install tor` before running the container. Without an active Tor daemon, search operations will fail.

Model access works through API keys like `ANTHROPIC_API_KEY` or `OPENAI_API_KEY`, alongside local setups like Ollama and LM Studio. Saved reports go to `/app/investigations`. On Linux hosts, create the mount folder ahead of time because the container runs under UID 1000 and hits permission issues on root-owned directories.

## Requirements
- Needs: Docker

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add robin-ai-powered-dark-web-osint -- docker run -i --rm docker.io/apurvsg/robin:v3.1
```

### Codex

**Platform CLI**
```bash
codex mcp add robin-ai-powered-dark-web-osint -- docker run -i --rm docker.io/apurvsg/robin:v3.1
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "robin-ai-powered-dark-web-osint": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "docker.io/apurvsg/robin:v3.1"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "robin-ai-powered-dark-web-osint": {
            "type": "stdio",
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "docker.io/apurvsg/robin:v3.1"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add robin-ai-powered-dark-web-osint docker run -i --rm docker.io/apurvsg/robin:v3.1
```

## When to use it
- query onion search engines over Tor directly from your agent
- filter raw dark web search findings with language models
- extract page text and compile structured investigation reports
- generate pivot queries based on identified leads

## Example prompts
- Investigate recent mentions of example-domain across onion search engines
- Extract and summarize the text from the top onion search findings
- Suggest follow-up pivot queries based on the collected investigation data

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89408
- [mcp](https://affpapa.org/en/nevibecode/mcp/kubeshark-mcp.md) — MCP server · ★ 12109

---
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