theHarvester MCP Server
Uses DuckDuckGo as a free OSINT source when harvesting a domain, helping discover publicly available emails, subdomains, hostnames, IPs, and LinkedIn profiles.
Can use VirusTotal as an OSINT source for domain harvesting when a VirusTotal API key is configured in the underlying theHarvester installation.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
theHarvester MCP Server: OSINT email and subdomain discovery for AI agents
theHarvester MCP Server wraps theHarvester in a Model Context Protocol server so Claude Code, Cursor, or any MCP client can harvest public emails, subdomains, hostnames, IPs, and LinkedIn profiles for a domain on demand. Multi-arch Docker image, stdio transport, no API keys for the default free sources.
It is built for lead generation and prospecting: ask your agent "find public contacts for
example.com" and it calls the harvest tool, which fans out to sources like crtsh,
hackertarget, urlscan, and DuckDuckGo, then returns structured JSON. Harvests run asynchronously
with configurable concurrency and timeouts, and results stay retrievable by harvest ID.
Quick start
docker pull devkind/theharvester-mcpAdd to .mcp.json (Claude Code) or your MCP client config:
{
"mcpServers": {
"theharvester": {
"command": "docker",
"args": ["run", "--rm", "-i", "devkind/theharvester-mcp"]
}
}
}Then ask your agent: "Harvest example.com using free sources."
Install in your client
Requirements:
Docker
Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, or any other MCP client
No API keys for the default free sources
Standard config works in most MCP clients:
{
"mcpServers": {
"theharvester": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"devkind/theharvester-mcp"
]
}
}
}Follow the MCP install guide and add the standard config above to your claude_desktop_config.json.
Run:
claude mcp add theharvester -- docker run --rm -i devkind/theharvester-mcpOr add the standard config above to .mcp.json in your project root.
Click the button to install:
Or install manually:
Go to Cursor Settings -> MCP -> Add new MCP Server. Name it "theHarvester MCP", use command type with the command docker run --rm -i devkind/theharvester-mcp.
Follow the MCP install guide and use the standard config above. You can also install with the VS Code CLI:
code --add-mcp '{"name":"theharvester","command":"docker","args":["run","--rm","-i","devkind/theharvester-mcp"]}'Follow the Windsurf MCP documentation and use the standard config above.
Go to Advanced settings -> Extensions -> Add custom extension. Name it "theHarvester MCP", use type STDIO, and set the command to docker run --rm -i devkind/theharvester-mcp. Click "Add Extension".
Go to Program in the right sidebar -> Install -> Edit mcp.json. Use the standard config above.
Go to Settings -> AI -> Manage MCP Servers -> + Add to add an MCP Server. Use the standard config above, or use the slash command /add-mcp in the Warp prompt and paste it.
Related MCP server: FullEnrich MCP
Tools
Tool | What it does |
| Run an OSINT harvest on a domain (sources: |
| Fetch a previous harvest by ID |
| Show currently running harvests |
| List all available sources and which need API keys |
Seven sources work with no API key: crtsh, hackertarget, dnsdumpster, rapiddns, urlscan, otx, and duckduckgo. Sources like shodan, censys, and virustotal need keys configured in the theHarvester install.
Example call and output
Tool call: harvest with {"domain": "example.com", "sources": "free"}
{
"harvest_id": "a1b2c3d4",
"domain": "example.com",
"status": "completed",
"duration_seconds": 42.5,
"sources_used": ["crtsh", "hackertarget", "urlscan"],
"summary": {"emails": 3, "hosts": 27, "ips": 12, "linkedin": 2},
"emails": ["info@example.com", "support@example.com", "press@example.com"],
"hosts": ["www.example.com", "api.example.com", "mail.example.com"]
}Output is illustrative; real counts depend on the target domain and source availability. The
harvest tool accepts domain (required), sources (free, all, or a comma-separated
list), limit, and timeout; invalid domains are rejected before any network call.
Configuration
Environment variables: THEHARVESTER_TIMEOUT (default 120s), THEHARVESTER_MAX_CONCURRENT
(default 2), THEHARVESTER_OUTPUT_DIR (default /app/output).
Claude Code skill
This repo ships a skill at skills/harvester/SKILL.md. When the
repo is used as a Claude Code plugin source (or skills directory), the skill is auto-discovered
and teaches the agent when and how to run OSINT harvests — tool names (harvest,
get_harvest_results, list_active_harvests, list_sources), recommended sources, and the
report format to return.
Responsible use
theHarvester collects only publicly published information, but OSINT tooling attracts scrutiny. Use this server only on domains you own or have written permission to research, and for lawful purposes such as security assessment, asset inventory, and business prospecting against public business contact data. Respect each source's terms of service and applicable privacy and anti-spam law (GDPR, CAN-SPAM, PECA) when acting on harvested contacts. The maintainers are not responsible for misuse.
Roadmap
Official MCP Registry listing (
io.github.devkindhq/theharvester-mcp)Docker MCP Registry and Glama listings
Pinned theHarvester version releases alongside
latest(devkind/theharvester-mcp:<version>is built with theHarvester 4.11.1,latesttracks the newest release)CI workflow building and pushing the multi-arch image on tag (untested until the first tag)
License and contributing
MIT © Devkind. Issues and PRs welcome, see CONTRIBUTING.md and SECURITY.md.
Built by Devkind. Maintained by Kazim Ali.
Need OSINT and lead generation built into your stack?
Devkind builds custom MCP servers, AI agent workflows and commerce integrations. If you want this kind of harvesting wired into your CRM, enrichment or outreach tooling, talk to Devkind or email hello@devkind.com.au.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
The Google for AI agents — company intel, competitor tracking, market research via MCP. JSON output
Web scraping, extraction and search for AI agents. Hosted MCP with workspace API keys.
MCP tools for agents: web research, content extraction, email, DNS, and blockchain intelligence.
Scrape, crawl and search the web for AI agents via MCP.
Related MCP Servers
- -licenseNot gradedqualityNot gradedmaintenanceExposes popular OSINT and reconnaissance tools like Sherlock, SpiderFoot, and Holehe through MCP and HTTP APIs for AI assistants. Runs security research tools in sandboxed environments and returns normalized JSON results for investigation and analysis.1-

FullEnrich MCPofficial
AlicenseNot gradedqualityCmaintenanceEnables AI agents to search B2B people and companies, enrich contacts with verified emails and mobile phone numbers via waterfall enrichment across 25+ providers, and export results as CSV or JSON. Supports prospecting, org mapping, candidate sourcing, and outreach workflows through OAuth-authenticated remote access from any MCP-compatible client.14MIT- AlicenseNot gradedqualityNot gradedmaintenanceEnables AI agents and LLM clients to autonomously run deep username and email OSINT scans across thousands of platforms, recursively pivoting on exposed handles, profile links, and secondary addresses while enriching results with rich profile metadata. It also exposes a dynamic catalog so agents can discover available modules and categories before scoping targeted scans.MIT
- AlicenseNot gradedqualityBmaintenanceA universal data intelligence MCP server that enables AI agents to search, extract, structure, and analyze information from supported web sources. Provides machine-readable results for research, data processing, and automated workflows through a simple, reusable interface.158 npmMIT