Cxpak MCP Server

cxpak indexes your codebase using tree-sitter across 43 languages, builds a typed dependency graph, and produces token-budgeted context bundles that

Remote serverstreamable-httpPython

What is the Cxpak MCP server?

cxpak indexes your codebase using tree-sitter across 43 languages, builds a typed dependency graph, and produces token-budgeted context bundles that give LLMs a briefing packet instead of a flashlight in a dark room. It understands your. Exposed over MCP by the cxpak mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

Its toolset

Everything the assistant can do here goes through one of these:

  • Usage — The container runs as a non-root user; the embedding model weights (~30 MB, downloaded on first use) live under /home/cxpak/.cxpak — mount a named
  • Intelligence — The Intelligence tool exposed by this server
  • Conventions — Extracts a quantified convention profile from what your team actually does: naming, imports, error handling, dependencies, testing, visibility
  • Onboarding — Generates a dependency-ordered reading guide: files topologically sorted, grouped into phases by module, ordered by PageRank. Each file lists key

Adding it to your client

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

When to reach for it

This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Cxpak's toolset — Usage, Intelligence, Conventions and 1 more — is a fair guide to whether it matches your workflow. It is maintained by barnett-studios; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Caveats

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the cxpak mcp server does with a few real requests.

Available tools

ToolWhat it does
UsageThe container runs as a non-root user; the embedding model weights (~30 MB, downloaded on first use) live under /home/cxpak/.cxpak — mount a named volume there to persist them across runs.
IntelligenceThe Intelligence tool exposed by this server.
ConventionsExtracts a quantified convention profile from what your team actually does: naming, imports, error handling, dependencies, testing, visibility, function length, git health. Each pattern has counts, percentages, and stren
OnboardingGenerates a dependency-ordered reading guide: files topologically sorted, grouped into phases by module, ordered by PageRank. Each file lists key symbols to focus on and an estimated reading time.

How to install the Cxpak MCP server

{
  "mcpServers": {
    "cxpak": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "ghcr.io/barnett-studios/cxpak"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Cxpak to Usage.
  • Use Cxpak to Intelligence.
  • Use Cxpak to Conventions.

Frequently asked questions

It connects Cxpak to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (Usage, Intelligence, Conventions, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Cxpak directly.