
WhatWeb MCP
io.github.devkindhqPublished by GitHub account devkindhqv1.0.0Updated Nov 1, 2026
Website technology fingerprinting for AI agents, powered by WhatWeb. Multi-arch Docker.
Overview
Runs WhatWeb in a local Docker container so an assistant can fingerprint a website's CMS, server, frameworks and analytics tools.
- What you can do
- Scan a target URL at one of five aggression levels and get a structured report of detected technologies and versions
- Fetch the results of an earlier scan by its scan ID
- List scans that are currently running
- Keep up to 100 recent results in memory for follow-up questions in the same session
- When to use it
- Useful when you want an assistant to identify what a site is built on — for lead qualification, competitive research, or authorized security reconnaissance — without leaving the chat.
- Requirements
- Docker on the local machine (multi-arch image for amd64 and arm64) plus any MCP client such as Claude Code, Cursor, VS Code or Windsurf. No API keys. Optional environment variables WHATWEB_MAX_CONCURRENT (default 2) and WHATWEB_TIMEOUT (default 300 seconds). Can alternatively run from source with Python and WhatWeb on the PATH.
Installation
In SourceWeft
- Open WhatWeb MCP in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
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.
Ready-paste config for Claude Code or Cursor, saved as .mcp.json in your project root (or ~/.cursor/mcp.json):
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:
Claude Desktop
Follow the MCP install guide and add the standard config above to your claude_desktop_config.json.
Claude Code
Run:
Or add the standard config above to .mcp.json in your project root.
Cursor
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.
VS Code
Follow the MCP install guide and use the standard config above. You can also install with the VS Code CLI:
Windsurf
Follow the Windsurf MCP documentation and use the standard config above.
Goose
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".
LM Studio
Go to Program in the right sidebar -> Install -> Edit mcp.json. Use the standard config above.
Warp
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.
Example tool call and output
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).
Roadmap
- Official MCP Registry listing (
io.github.devkindhq/whatweb-mcp) - Docker MCP Registry and Smithery listings
- 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 [email protected].
Source: README.md at commit f7d85d2
Tools
0Version history
1- v1.0.0LatestNov 1, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts