An MCP server for auditing JavaScript/TypeScript repositories for AI governance guardrails. It identifies where LLM output reaches users or side-effectful actions and reports missing confidence handling, fallback, validation, or human review, with a CI-gating mode for red side-effectful cases.
From the registry: Audit AI/LLM features for governance guardrails: confidence, fallback, validation, human-in-loop.
Please install the `aiglare` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Node.js and npx** — Requires a Node.js environment with npx available to run the packaged MCP server.
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","@nugehs/aiglare","mcp"]
Note: The MCP server is built into the aiglare package and runs over stdio. No environment variables are documented for MCP usage.
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.