CompareGraph MCP server

CompareGraph

Many cloned repositories, one taxonomy, evidence on every cell.

<!-- sources: Cargo.toml (licence, rust-version); docs/catalog.json (18 tools); walker.rs language_for (29 languages); application/setup.rs (12 clients); .github/workflows/ci.yml -->

CompareGraph parses many cloned repositories into one SQLite graph. It scores each clone against a taxonomy (a "family" of features) and records, per clone and feature, a verdict with a citation to a file and line range. It is one Rust binary with a CLI and an MCP server. It reads clones and never runs them. It never calls a model.

Contents

• Why CompareGraph
• Install
• Quick start
• How good is it
• Languages
• How it works
• What you get
• CLI reference
• MCP tools
• Plugins and the second engine
• Families and the seven skills
• The vault

Why CompareGraph

You have many repositories and one question: who has what? Reading each by hand does not scale, a summary without a line number cannot be checked, and notes go stale when the code moves. Five properties, each one you can test:

an incremental build must equal build --full (equal on both large trees in the Plan 6 report).

1. Deterministic. The same clone and version give the same store_hash. comparegraph check rebuilds and compares, and

limitations[] list of what the engine cannot see.

1. An evidence class on every answer. Each envelope says observed, derived, inferred or unknown, plus a

otherwise the engine refuses. A moved citation shows as unknown* after check.

1. A claim needs a citation that resolves now. has and partial need --at path:start-end matching a stored node;

(symbols, paths, community terms, node kinds) all empty. Any hit refuses the claim and lists the candidates.

1. none needs proof of absence. Either --searched terms that find nothing, or the graph check: four channels

the reading; the engine only stores, checks and refuses.

1. No model in the engine. Scores, bands, descriptions and candidates are computed from stored facts. An agent may do

Shortened. The full README is on GitHub.