kenda-ingestion-mcp

A small, read-only Model Context Protocol server that lets an AI host (e.g. Claude Code) answer questions about your Kenda token spend and waste straight from the terminal — "how much did I spend this week?", "which agent is wasting the most?".

It is a query surface only: it never captures or writes usage. It reads the token-authed /collector/* endpoints of the Kenda API using the endpoint + token from ~/.kenda/config.json (the same ingest token the Kenda collector writes), which resolve the token to its org server-side — so the terminal needs no browser/Auth0 session.

Tools

Tool	Endpoint	Returns
kenda_spend_summary	GET /collector/summary	Top-line spend, waste, and health for your org
kenda_waste_by_agent	GET /collector/agents	Per-agent spend and redundant (wasted) dollars

Install

pip install kenda-ingestion-mcp     # or: uvx kenda-ingestion-mcp

The console script kenda-mcp runs the stdio server.

Configure

The server reads ~/.kenda/config.json:

{
  "endpoint": "https://api.kenda.app",
  "token": "kenda_your-ingest-token"
}

Only endpoint and token are required for queries. Both are written for you by kenda-collect init (the Kenda collector) or the Claude Code plugin's /kenda-setup. Environment variables override the file (KENDA_ENDPOINT, KENDA_TOKEN) for CI and power users.

Use with Claude Code

Register it as an MCP server (.mcp.json):

{
  "mcpServers": {
    "kenda": {
      "command": "kenda-mcp"
    }
  }
}

Then ask Claude, from the terminal: "what did I spend this week?" or "which agent is wasting the most?".

Develop

python -m venv .venv && . .venv/bin/activate
pip install -e ".[dev]"
ruff check .
pytest

The HTTP query layer is pure stdlib and unit-tested (tests/test_query.py); the MCP transport is driven end-to-end with an in-memory client (tests/test_server.py). The mcp package is a runtime dependency, so both suites run in CI.

License

Proprietary — see LICENSE.