BUER is a local MCP server that monitors AI coding agents by analyzing code changes, dependency graphs, git state, and test results. It can inject pre-edit structural context and trigger alerts when it detects loops, scope drift, or test tampering.
From the registry: Guardrail for AI coding agents: catches loops, regressions, and test-tampering.
$ git clone https://github.com/zengxzh/buer.git && cd buer && pip install -e .https://github.com/zengxzh/buerPlease install the `buer` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Python 3.10 or newer** — BUER requires Python 3.10 or later.
- **Clone the repository** — Install BUER from source by cloning the repository, then installing it with pip. Run: `git clone https://github.com/zengxzh/buer.git && cd buer && pip install -e .` (https://github.com/zengxzh/buer)
Canonical MCP server config (HTTP transport):
- url: `http://127.0.0.1:7777`
Note: BUER runs as a local HTTP server, started with: buer-server --host 127.0.0.1 --port 7777 --db .buer/store.sqlite. The README documents HTTP endpoints such as /buer/session-start, /buer/post-edit, /buer/post-read, /buer/post-bash, /buer/stop, and /v1/metrics. No MCP stdio command/config snippet or MCP client config shape is provided in the README, only the local server runtime. BUER also requires a local .buer/ directory for persistent state and automatically manages .gitignore protection for it.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.