The Kawa Code MCP server provides a communication layer for Kawa Code to track development intent and maintain context between developers and AI systems.
From the registry: Intent tracking, decision recording, and team coordination for AI coding assistants
Please install the `mcp-codeawareness` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Node.js >= 18** — Runtime for the MCP server (https://nodejs.org)
- **Kawa Code desktop app** — The MCP server is a thin adapter to the Kawa Code desktop app which must be running (https://kawacode.ai)
Optional prerequisites:
- GitHub CLI (gh) — Optional, enables richer history inference data tiers (https://cli.github.com/)
Canonical MCP server config (stdio transport):
- command: `node`
- args: ["/absolute/path/to/kawa.mcp/build/index.js"]
Note: Requires cloning the repo and running npm install + npm run build before use.
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.ANTHROPIC_API_KEYrequiredYour own Claude API key, passed as a parameter to the inference toolsReal-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
Validate oh-my-posh configurations and segment snippets against the official schema.