Topos MCP server

the agent harness for structural code quality

Topos measures complexity, coupling, risky data flows, and agent cognitive load, then gives your agent a concrete target—from SLOP to PLATINUM.

<!-- mcp-name: io.github.Krv-Labs/topos -->

Install · What it checks · Under the hood · Docs · Issues

<!-- DEMO STUB — replace this comment only after recording the real release flow.

Show, in under 20 seconds:

1. an agent evaluates a repository;
2. Topos identifies the exact failing pillar and source hotspot;
3. the agent makes one focused refactor;
4. Topos verifies the medal improvement while the project tests stay green.

Prefer a checked-in, captioned GIF or SVG terminal recording with a stable repository-relative URL. Do not publish a synthetic or hand-written result. -->

<!-- STUDY STUB — keep hidden until the study, raw results, pinned repository SHAs, and reproduction method are public.

Candidate headline: "We evaluated public repositories at pinned commits. ."

Required link target: a durable methodology/results page containing the corpus selection rule, Topos version and configuration, machine details, raw JSON, known limitations, and a reproduction command. Avoid labeling repositories as "AI-generated" unless that provenance is explicit and independently verifiable. -->

Why Topos

Coding agents produce working code quickly. The harder question is whether the result is still easy to understand, safe to change, and well-fitted to the rest of the repository. Quality is the new currency.

Topos computes that signal from program structure—not from an LLM review or a style opinion—and returns concrete failure locations and next actions. It is fast enough to sit inside the agent loop: measure, edit, verify, repeat.

Tests check behavior. Topos checks whether the implementation is built to keep changing.

Grounded in category theory, written in Rust.

Install and Quick Start

One binary. Every supported agent harness. A clean way back out.

1. Install the CLI

Use the verified release installer:

Shortened. The full README is on GitHub.