An MCP server that lets an AI agent validate its work against a fail-closed checklist before claiming it is done, then records decisions in a hash-chained receipts ledger. It exposes tools to fetch the required gate, evaluate evidence, append receipts, and verify the ledger chain.
From the registry: Fail-closed quality gate and hash-chained receipt ledger for AI agent workflows.

$ pip install mcp-agent-gatePlease install the `agent-gate` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Python 3.11+** — Python 3.11 or newer is required to run the server. (https://www.python.org/)
- **Install the agent-gate package** — Install the MCP server package from PyPI. Run: `pip install mcp-agent-gate`
Canonical MCP server config (stdio transport):
- command: `python`
- args: ["-m","agent_gate.server"]
- optional environment variables:
- `AGENT_GATE_LEDGER`: Optional path to the receipts ledger file. If not set, receipts persist to the default user ledger location. (example: `<path-to-receipts-jsonl>`)
Note: Default receipts ledger path is ~/.agent-gate/receipts.jsonl when AGENT_GATE_LEDGER is not set.
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.AGENT_GATE_LEDGEROverrides the default path for the persisted receipts ledger.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.