# stackdoctor MCP server

> Lets an AI client diagnose Python backend stacks by analyzing Postgres, Celery, Redis, and logs in a single tool call.

- Repository: https://github.com/lepri89/stackdoctor
- Page: https://hostedmcp.org/servers/lepri89/stackdoctor
- Transport: —
- Stars: 0
- License: MIT

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `CELERY_BROKER_URL` | no | no |  |
| `CELERY_RESULT_BACKEND` | no | no |  |
| `DATABASE_URL` | no | no |  |
| `LOG_SOURCES` | no | no |  |
| `REDIS_URL` | no | no |  |
| `STACKDOCTOR_ENV_FILE` | no | no |  |
| `STACKDOCTOR_TEST_DATABASE_URL` | no | no |  |
| `STACKDOCTOR_TEST_REDIS_URL` | no | no |  |

## FAQ

### Is stackdoctor safe to use on production?

Yes, it is strictly read-only. It never writes, deletes, restarts, or revokes anything, and Postgres sessions are forced to read-only mode.

### How does it handle sensitive data?

The server redacts secrets from every response to ensure security.

### What backend technologies does it support?

It supports diagnosing Python backend stacks including Postgres, Celery, Redis, and various log sources.