Skip to main content
Glama
WhatWeb MCP Server

WhatWeb MCP Server

by devkindhq

WhatWeb MCP Server: web technology fingerprinting for AI agents

WhatWeb MCP server lets Claude Code, Cursor, and any MCP client fingerprint websites and identify their CMS, web server, frameworks, and analytics tools. It runs WhatWeb in a hardened Docker container and returns a structured report in one tool call.

Sales and prospecting teams use it to qualify leads; security teams use it for recon.

The server publishes three tools: whatweb_scan (scan a target at five aggression levels), get_scan_results (fetch a previous scan by ID), and list_active_scans (see what is running). Scans run in a sandboxed container with a non-root user, memory and CPU limits, and flag-injection validation on every target.

Quickstart (Docker)

The image is multi-arch (linux/amd64 and linux/arm64), so the same tag works on Apple Silicon, x86 servers, and ARM cloud instances.

docker pull devkind/whatweb-mcp:latest

Ready-paste config for Claude Code or Cursor, saved as .mcp.json in your project root (or ~/.cursor/mcp.json):

{
  "mcpServers": {
    "whatweb": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "--memory=512m", "--cpus=0.5", "--pids-limit=100", "devkind/whatweb-mcp:latest"]
    }
  }
}

Then ask your agent: "What technologies does example.com run?"

Install in your client

Requirements:

  • Docker

  • Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, or any other MCP client

  • No API keys

Standard config works in most MCP clients:

{
  "mcpServers": {
    "whatweb": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "--memory=512m",
        "--cpus=0.5",
        "--pids-limit=100",
        "devkind/whatweb-mcp:latest"
      ]
    }
  }
}

Follow the MCP install guide and add the standard config above to your claude_desktop_config.json.

Run:

claude mcp add whatweb -- docker run -i --rm --memory=512m --cpus=0.5 --pids-limit=100 devkind/whatweb-mcp:latest

Or add the standard config above to .mcp.json in your project root, or install the Claude Code plugin.

Click the button to install:

Or install manually:

Go to Cursor Settings -> MCP -> Add new MCP Server. Name it "WhatWeb MCP", use command type with the command docker run -i --rm --memory=512m --cpus=0.5 --pids-limit=100 devkind/whatweb-mcp:latest.

Follow the MCP install guide and use the standard config above. You can also install with the VS Code CLI:

code --add-mcp '{"name":"whatweb","command":"docker","args":["run","-i","--rm","--memory=512m","--cpus=0.5","--pids-limit=100","devkind/whatweb-mcp:latest"]}'

Follow the Windsurf MCP documentation and use the standard config above.

Go to Advanced settings -> Extensions -> Add custom extension. Name it "WhatWeb MCP", use type STDIO, and set the command to docker run -i --rm --memory=512m --cpus=0.5 --pids-limit=100 devkind/whatweb-mcp:latest. 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: pentest-mcp-server

Example tool call and output

{ "tool": "whatweb_scan", "arguments": { "target": "https://example.com", "aggression": "normal" } }
{
  "scan_id": "a1b2c3d4",
  "target": "https://example.com",
  "status": "completed",
  "http_status": 200,
  "stats": { "total_technologies": 3 },
  "technologies": [
    { "name": "nginx", "version": "1.25.3", "string": null },
    { "name": "WordPress", "version": "6.4.3", "string": "wp-content" },
    { "name": "jQuery", "version": "3.7.1", "string": "jquery.js" }
  ],
  "error": null
}

Aggression levels map to WhatWeb's -a flag: stealthy/passive (1, one request), polite (2), normal (3), aggressive (4, potentially intrusive, so use only on targets you are authorized to test).

How it works

The container installs WhatWeb from the official upstream repository on an Alpine Ruby base, then runs a Python MCP server (mcp SDK, stdio transport). Each scan shells out with an argument array (no shell interpolation), writes WhatWeb's JSON log to an ephemeral /app/output, and parses it into typed results. Up to 100 scan results are kept in memory for follow-up questions in the same session. Tests cover target validation, JSON parsing, result-store bounds, and a live MCP stdio JSON-RPC handshake. Run them with pytest. Also installable from source without Docker: pip install -r requirements.txt && python3 server.py (requires WhatWeb on your PATH).

Network access and data

  • The plugin starts the server with docker run, so Docker downloads the devkind/whatweb-mcp:latest image from Docker Hub on first use. Later runs use the local copy until you run docker pull devkind/whatweb-mcp:latest. Docker must be installed and running.

  • Each scan sends HTTP requests from your machine to the target you give, with the user agent WhatWeb/0.6.4. WhatWeb follows up to 10 redirects, also to other hosts. The aggressive level sends many more requests than stealthy.

  • The tool result carries the target's HTTP status, the detected technologies, their versions and the matched strings.

  • The server sends no telemetry and calls no other service. It writes logs to stderr only.

  • The server keeps up to 100 scan results in memory and writes each WhatWeb JSON log inside the container. --rm deletes the container and its logs when the session ends.

Claude Code plugin

The repository root is a Claude Code plugin. It adds the WhatWeb MCP server and the tech-detector skill. The skill teaches Claude when to scan a site, how to call whatweb_scan, and how to turn the technology list into a stack summary and analysis angles for lead qualification and competitor research.

Install it now (Claude Code 2.1.275 or later):

/plugin install whatweb --marketplace devkindhq/whatweb-mcp

On older Claude Code versions, use the claude mcp add command in Install in your client. To use only the skill in another agent, copy skills/tech-detector/ into your project's .claude/skills/ (or ~/.claude/skills/) directory.

Roadmap

  • Official MCP Registry listing (io.github.devkindhq/whatweb-mcp)

  • Docker MCP Registry listing

  • Batch scanning (multiple targets in one call)

  • Optional CSV/JSON export tool

  • Scheduled re-scans with diffing (alert when a target's stack changes)

Built by

Built by Devkind. Maintained by Kazim Ali.

License

MIT. See CONTRIBUTING.md and SECURITY.md. WhatWeb itself is licensed by its upstream authors. Scan only targets you are authorized to scan.

Qualifying leads by their tech stack?

Once you know what a site runs, Devkind can help you build on it. We work with Shopify, Swell and headless commerce stacks, and build custom MCP servers and AI agent workflows. 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…

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Provides Claude Desktop with access to Kali Linux penetration testing tools via a privileged Docker container, enabling network scanning (nmap), web vulnerability scanning (nikto), and custom command execution.
      11
      -
    • F
      license
      Not graded
      quality
      D
      maintenance
      Wraps common web penetration testing tools in a Docker container and exposes them as Claude tools for educational use in controlled lab environments.
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      MCP server for website reconnaissance. Gives Claude the ability to fingerprint tech stacks, audit security headers, map endpoints, analyze SSL certificates, enumerate DNS records, and scan ports.
      13,303 npm
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides agent-readiness audits of public websites via Cloudflare's scanner, enabling users to run scans, save reports, and enforce safety boundaries from natural language.
      MIT