Gpp runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 25 Aug 2026.
Project knowledge graph with history-checked belief staleness, changeset proposals, cost reporting
What the code does
We read the source, 19 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
ON CONFLICT(changeset_id) DO UPDATE SET
input_tokens = input_tokens + excluded.input_tokens,
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Alternatives to Gpp
same job, measured the same wayMCP server + Playwright reporter that builds a flakiness knowledge graph from test run history
Living knowledge graph for your repo: query with citations, remember/link facts, fact-check claims.
Distill AI coding sessions into weekly reports, ADRs and a knowledge graph - self-hosted
Harbor Registry MCP — projects, repos, artifacts, storage reports, cleanup (with dry-run).
Repository knowledge graph MCP server for codebase understanding and debugging.
Cross-project knowledge graph for MCP — map features across mobile, backend, and admin codebases.
AI agent project management — task boards, progress tracking, and cost reporting.
Public registry of code-knowledge graphs for AI agents with schema validation and drift detection.
Gpp — questions
Answers built from our own checks of this server.