Detrix MCP Server

Agent: → reads the source, spots dead unit-conversion code → wakes the service via Detrix → observes txn.Amount, txn.Unit, total (no line number —

Local serverstdioPython

What is the Detrix MCP server?

Agent: → reads the source, spots dead unit-conversion code → wakes the service via Detrix → observes txn.Amount, txn.Unit, total (no line number — find_variable locates it in the running container). That is what the detrix mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The tools it exposes

The server publishes 8 tools. What each one is for:

  • Production-safe — Output pollution, perf risk
  • Events — Ephemeral stream
  • Cleanup — Manual (easy to forget, ships to prod)
  • Language — Install
  • Rust — detrix-rs = "1.2.0" in Cargo.toml
  • Multi-language — Python (debugpy), Go (delve), Rust (lldb-dap)
  • Extensible — New frontends via open API; new language support by implementing a language adapter — Adding Languages
  • Auth — Multi-tenant access control: per-user static tokens or JWT/JWKS, role-based authorization (Admin/User), per-agent metric isolation — [Auth

Getting it running

detrix-py on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.

How it compares

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Detrix's toolset — Production-safe, Events, Cleanup and 5 more — is a fair guide to whether it matches your workflow. It is maintained by flashus; 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We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
Production-safeOutput pollution, perf risk
EventsEphemeral stream
CleanupManual (easy to forget, ships to prod)
LanguageInstall
Rustdetrix-rs = "1.2.0" in Cargo.toml
Multi-languagePython (debugpy), Go (delve), Rust (lldb-dap)
ExtensibleNew frontends via open API; new language support by implementing a language adapter — [Adding Languages](docs/ADD_LANGUAGE.md)
AuthMulti-tenant access control: per-user static tokens or JWT/JWKS, role-based authorization (Admin/User), per-agent metric isolation — [Auth Guide](docs/AUTH.md)

How to install the Detrix MCP server

{
  "mcpServers": {
    "detrix": {
      "command": "uvx",
      "args": ["detrix-py"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Detrix to Production-safe.
  • Use Detrix to Events.
  • Use Detrix to Cleanup.

Frequently asked questions

It connects Detrix to MCP-compatible AI assistants such as Claude and Cursor, exposing 8 tools (Production-safe, Events, Cleanup, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Detrix directly.