katra runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 13 Sep 2026.
A committed markdown dev log and task graph that agents read and write over MCP.
We read the source, 3 d ago · rules ccca72095570
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.
subprocess.run(
abs = filepath.Join(wd, abs)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
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.
Read-only MCP server: get_recent_commits over a local deploy log (Quellgeist triage).
Shared project wiki for AI agents: read and write pages, next actions, and activity logs over MCP.
Read-only MCP server over a local log-analysis backend; a client that computes no verdicts.
Read the MindForge engine over MCP: knowledge graph, project health, and audit log.
Airflow MCP — list DAGs/runs/task instances, tail logs, trigger and clear (write-gated)
Sendora's docs and API for coding agents: send test mail, read the log, set up webhooks.
Read, verify and export a tamper-evident log of what an AI agent did. Read-only.
Persistent memory for AI agents — log and recall conversation context over MCP.
Answers built from our own checks of this server.