Skip to content
MCP server

theHarvester MCP

Docker-run MCP server for finding public emails and subdomains of a domain

Runs locallyStatus and history
Install
Pricing
Open source
Platforms
Linux, macOS, Windows
Runs
Locally
Version
1.0.0
Listing updated
3 days ago

About theHarvester MCP

theHarvester MCP is an open-source MCP server for security. It runs locally on your machine and is started by your AI client.

The server wraps the theHarvester OSINT tool. An agent asks for a harvest on a domain and the server fans out to public sources, returning structured JSON of emails, subdomains, hostnames, IPs and LinkedIn profiles. Harvests run asynchronously, so a result can be fetched later by its harvest ID.

Seven sources need no API key: crtsh, hackertarget, dnsdumpster, rapiddns, urlscan, otx and duckduckgo. Sources such as shodan, censys and virustotal need keys configured in theHarvester. Two environment variables set limits: THEHARVESTER_TIMEOUT, default 120 seconds per harvest, and THEHARVESTER_MAX_CONCURRENT, default 2.

It runs locally over stdio from a multi-arch Docker image, and the README positions it for lead generation and prospecting.

Install

Run in a terminal

claude mcp add theharvester-mcp -- docker run -i --rm docker.io/devkind/theharvester-mcp:1.0.0

Add to claude_desktop_config.json

{
  "mcpServers": {
    "theharvester-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "docker.io/devkind/theharvester-mcp:1.0.0"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "theharvester-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "docker.io/devkind/theharvester-mcp:1.0.0"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "theharvester-mcp": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "docker.io/devkind/theharvester-mcp:1.0.0"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "theharvester-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "docker.io/devkind/theharvester-mcp:1.0.0"
      ]
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "theharvester-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "docker.io/devkind/theharvester-mcp:1.0.0"
      ]
    }
  }
}

Configuration

  • THEHARVESTER_TIMEOUTPer-harvest timeout in seconds (default 120)
  • THEHARVESTER_MAX_CONCURRENTMaximum concurrent harvests (default 2)

Tools this server provides (4)

Taken from the project documentation; the running server may differ.

harvest
Run an OSINT harvest on a domain with free, all or chosen sources
get_harvest_results
Fetch a previous harvest by ID
list_active_harvests
Show currently running harvests
list_sources
List sources and which need API keys

What it does

Domain harvesting
Collects public emails, subdomains, hostnames and IPs.
Async results
Fetch earlier harvests later by ID.
Free sources
Seven sources work without any API key.
Source listing
Shows which sources need keys.
Tunable limits
Set per-harvest timeout and concurrency with environment variables.
Multi-arch image
One Docker image for amd64 and arm64 hosts.

Good for

  • Finding public contacts for a prospect domain
  • Mapping subdomains of a company's site
  • Checking which sources are available before a scan
  • Running recon on a domain from a coding assistant

Pricing

Open source

Prices change. Check devkind.com.au before you buy.

theHarvester MCP FAQ

Do I need API keys?

Not for the seven default free sources.

How do I run it?

Pull the Docker image and register it as a stdio command in your MCP client.

What are the defaults for timeout and concurrency?

120 seconds and 2 concurrent harvests.

Can I retrieve an earlier run?

Yes, with get_harvest_results and its ID.

Is theHarvester MCP free?

Yes. theHarvester MCP is open source, so you can use and self-host it for free.

How do I add theHarvester MCP to Claude Code?

Run this command in your terminal: claude mcp add theharvester-mcp -- docker run -i --rm docker.io/devkind/theharvester-mcp:1.0.0

What are the best alternatives to theHarvester MCP?

The closest alternatives to theHarvester MCP are REA, Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search and Agent Roast.

Alternatives to theHarvester MCP

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. MCP server for AI clients to scrape sites with HTTP and stealth browser sessions

    Runs locally
    • 17 tools
    • Open source
    • 104K GitHub stars
    • Web search and scraping
  3. MCP server that lets AI agents search, scrape and interact with web pages

    • 3 tools
    • Remote
    • Freemium
    • 7.8K GitHub stars
    • Web search and scraping
  4. SearXNG Search

    MCP server

    MCP server for web search and page reading through a SearXNG instance

    Runs locally
    • 3 tools
    • Open source
    • 1.4K GitHub stars
    • Web search and scraping
  5. Agent Roast

    MCP server

    Offline review that flags agent changes which weaken tests, assertions or CI

    Runs locally
    • Open source
    • 4 Hacker News points
    • Developer tools
  6. Midplane

    MCP server

    Postgres gateway for AI agents with table grants, column masking and approval for writes

    Runs locally
    • Open source
    • 5 GitHub stars
    • Databases