📡 MCP Radar

bar181/bar-observatory

Deterministic, local-only audit reports for Claude Code AI agent sessions. Rust + SQLite. Zero network calls. MCP server for agents.

⭐ 18 stars
⑂ 0 forks
HTML
momentum ▲ 36.0
created 2026-08-12
on radar since 2026-08-14
star trend 3 → 18 since 2026-08-14
agent-monitoringagentic-aiai-agentsai-engineeringauditaudit-logclaude-codeclaude-code-plugindeterministicdeveloper-toolsllm-observabilitylocal-firstmcpmcp-serverobservabilityrustsqlitetelemetry
View on GitHub ↗Homepage ↗

About bar-observatory

BAR Observatory — Deterministic Audit Reports for Claude Code AI Agent Sessions

BAR Observatory (Base Agentic Reporter) is a free, open-source, local-only flight recorder and audit tool for Claude Code sessions. It reads what your AI coding agent actually did — every tool call, task, sub-agent dispatch, rework loop, and error — stores it in a local SQLite database, and renders a deterministic report in JSON, HTML, and Markdown. Same database in, byte-identical report out, every time. No LLM in the render path. No network calls. No API key. No account. (The optional bar interpret command is the one exception — it uses your own Claude Code session to write a plain-English summary. The deterministic report never depends on it and never calls a model itself.)

Don't ask the agent what happened. Check the record.

TL;DR — If you've ever finished a long Claude Code session and thought "what did it actually do in there, and can I prove it?", run one command against the transcript you already have on disk and get a report you can attach to a PR, hand to a reviewer, keep as part of your own review process, or let another AI agent query directly. You do not need to clone or build this repository to do any of that — see Zero-SDK, zero-clone below.

New to command lines? This page covers everything in depth, including some technical detail meant for engineers evaluating the tool. If you'd rather follow a slower, plain-language, click-along guide with no assumed background — including how to open a terminal in the first place — start with the plain-language guide instead, then come bac

From the project README.

Maintaining this server?

Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:

[![On MCP Radar](https://mcp.liqiwa.com/badge.svg)](https://mcp.liqiwa.com/s/bar181--bar-observatory.html)

Related MCP servers

menot-you/n-memory

Memory your agent can trust — every answer carries its source; when it doesn't know, it says so. Hermetic, local, MCP.

⭐ 5Rust
Koragraph/KoragraphMCP

The memory layer that gets better as you use it. What broke, why, what depended on what, even the "push this to Wednesday" kind of thing that never makes it into any doc. No one has to write it down.

⭐ 13JavaScript
Smitner-Studio/facet

Render agent-written Markdown as a live local page, and send the human's click back to the agent as typed data. Human-in-the-loop approval gates for coding agents.

⭐ 4Go
jarvis-intelligence/jarvis-index

Public distribution surface for jarvis — local-first code intelligence MCP server (SCIP navigation + Zoekt search). Installer, Claude Code / Codex / Cursor plugins, and prebuilt binaries.

⭐ 4HTML
omaekumiko2-create/kru

Local-first MCP password and credential manager for AI agents. Use passwords, API keys, SSH identities, and TOTP without exposing hidden plaintext to the model.

⭐ 88Rust
TedHaley/pensieve

Local search across your files, git repos and AI agent sessions on your Mac. An MCP server gives your agents the best context, a 3D map shows your work by topic, and git blame shows who knows what.

⭐ 65Python

📬 Get the weekly radar in your inbox

The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.