HTTrack MCP server
Commit Oct 2, 2026Enables AI agents to mirror websites into local archives and browse, read, or search the downloaded content via MCP.
Also known as TechVentures-Studio/httrack-mcp, httrack-mcp
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.0.3
- Last commit
- Oct 2, 2026
- License
- AGPL-3.0
What is HTTrack MCP?
HTTrack enables AI agents to mirror websites into local archives and browse, read, or search the downloaded content via MCP.
Summary generated from the project's README
About HTTrack MCP server
Mirroring entire websites into local archives for AI analysis is what this server enables. It wraps the HTTrack website copier to allow LLM agents to download web content into a shared directory and then interact with that data through the Model Context Protocol. Users run the server via Docker, which exposes an MCP interface over streamable HTTP on port 9050.
Agents use the mirror_site tool to start background downloads for specific URLs and can monitor progress using mirror_status. Once a site is archived, the agent can browse the directory structure with list_files, perform case-insensitive substring searches via search_files, or read specific text files like HTML, CSS, or JSON using read_file. To maintain context limits, the read_file tool caps content at 256 KB and refuses binary files.
The system supports parallel mirroring of different projects, though it prevents multiple concurrent requests for the same project. It manages all downloaded data within a local data directory mapped through a Docker volume.
What you can do with it
- 1Archive a website for offline researchAn AI agent can start a background download of a specific URL to create a local copy for later study.
- 2Search through downloaded site contentA developer can ask an agent to find specific strings or keywords across all text files in a mirrored project.
- 3Inspect website file structuresAn agent can list the files and directories within a specific project to understand the site architecture.
- 4Read specific web assetsAn AI can extract and read the contents of HTML or JSON files from the local archive to answer questions.
Written from the project's README. Every use case is checked against a quote from it.
How to install HTTrack MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall HTTrack MCP in Claude Code
$ claude mcp add httrack-mcp -- docker run -i --rm ghcr.io/techventures-studio/httrack-mcp-server:v1.0.3Install HTTrack MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"httrack-mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/techventures-studio/httrack-mcp-server:v1.0.3"
]
}
}
}Install HTTrack MCP in VS Code
.vscode/mcp.json
{
"servers": {
"httrack-mcp": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/techventures-studio/httrack-mcp-server:v1.0.3"
]
}
}
}Install HTTrack MCP in VS Code CLI
$ code --add-mcp '{"name":"httrack-mcp","type":"stdio","command":"docker","args":["run","-i","--rm","ghcr.io/techventures-studio/httrack-mcp-server:v1.0.3"]}'Install HTTrack MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"httrack-mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/techventures-studio/httrack-mcp-server:v1.0.3"
]
}
}
}Install HTTrack MCP in Codex
$ codex mcp add httrack-mcp -- docker run -i --rm ghcr.io/techventures-studio/httrack-mcp-server:v1.0.3Install HTTrack MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.httrack-mcp] command = "docker" args = ["run", "-i", "--rm", "ghcr.io/techventures-studio/httrack-mcp-server:v1.0.3"]
Install HTTrack MCP in Gemini CLI
$ gemini mcp add -s user httrack-mcp docker -- run -i --rm ghcr.io/techventures-studio/httrack-mcp-server:v1.0.3Install HTTrack MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"httrack-mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/techventures-studio/httrack-mcp-server:v1.0.3"
]
}
}
}Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachabletechventures-studio/httrack-mcp is public and reachablegithub.com/techventures-studio/httrack-mcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)AGPL-3.0spdx.org/licenses/AGPL-3.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-02github.com/techventures-studio/httrack-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubHTTrack MCP Server
A FastMCP (Model Context Protocol) server that wraps the classic HTTrack website copier, so AI agents can mirror websites into a shared archive and then browse, read, and search the downloaded content — all over MCP.
Copyright (C) 2026 Tech Ventures VCC. Licensed under the GNU Affero General Public License v3.0 (see LICENSE).
Why
HTTrack is battle-tested for offline website copying, but it has no scripting API — only a
GUI and a CLI. This server makes it agent-native: an LLM agent can call mirror_site to
start a download in the background, poll mirror_status, and later answer questions from
the archive via catalog, list_files, read_file, and search_files.
Tools
| Tool | Purpose |
|---|---|
mirror_site(url, project, depth, max_rate, filters) |
Start a background mirror into the archive (/data/<project>). One active mirror per project — a concurrent request for the same project returns already_running with the live job_id; different projects run in parallel. |
mirror_status(job_id) |
Job status (running / done / failed + log tail). Omit to list recent jobs; also accepts the project name. |
catalog() |
All projects: short name, short description (auto-derived from each site's <title>/meta description), source URL, status, page/file counts, size. |
list_files(project, subpath) |
Directory listing inside a project (name, type, size, modified). |
read_file(project, path, max_bytes) |
Read one text file (HTML/JS/CSS/txt/json/md). Refuses binaries; caps content at 256 KB to keep agent context sane. |
search_files(project, query, max_results) |
Case-insensitive substring search across a project's text files, capped results. |
Quick start
Prerequisites: Docker.
docker build -t httrack-mcp-server .
docker run -d --name httrack-mcp --restart unless-stopped \
-p 9050:8000 \
-v /path/to/your/archive:/data:rw \
httrack-mcp
The container exposes the MCP server over streamable HTTP at http://<host>:9050/mcp.
Register in an MCP client
Example for MCPHub-style gateways (streamable-http):
{
"httrack": {
"type": "streamable-http",
"url": "http://192.168.1.35:9050/mcp",
"enabled": true,
"description": "HTTrack site mirroring + archive browsing",
"owner": "admin"
}
}
Clients that speak streamable HTTP directly can connect to /mcp with no extra auth
(nobody is authenticated; run this on a trusted network, or put it behind your gateway's
auth). See HELP.md for full usage, examples, and troubleshooting.
Concurrency model
- One
httrackprocess per project, isolated by its own output directory — no shared state between projects, so multiple agents can mirror different sites in parallel. mirror_siteguards against double-mirroring the same project (in-process job table + a/procscan for httrack processes writing to that project directory).
CI
GitHub Actions runs on every PR and push: Python syntax check of server.py,
Dockerfile sanity assertions, and a Docker image build.
License
This program is free software: you can redistribute it and/or modify it under the terms of the GNU Affero General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
If you run a modified version of this server as a network service, AGPL §13 requires you to offer your users the corresponding source of that modified version.
Copyright (C) 2026 Tech Ventures VCC. HTTrack itself is GPL-licensed by Xavier Roche and contributors; this project only shells out to it and is not affiliated with it.
HTTrack MCP questions
How do I add HTTrack MCP to Claude Code?
Run claude mcp add httrack-mcp -- docker run -i --rm ghcr.io/techventures-studio/httrack-mcp-server:v1.0.3 in your terminal. Add --scope user to make it available in every project.
How do I add HTTrack MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Can I run multiple website mirrors at the same time?
Yes, different projects run in parallel as each project is isolated by its own output directory.
What happens if I try to mirror a project that is already being downloaded?
The server will return an 'already_running' status along with the live job ID.
Can the AI agent read binary files from the archive?
No, the read_file tool refuses binary files and only supports text files like HTML, JS, CSS, txt, json, and md.
Is there a limit to how much content the agent can read at once?
Yes, to keep the agent context manageable, content is capped at 256 KB.