trello-mcp
by enthouan
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | HTTP listen port for the Node process. Docker Compose keeps the container listener on `3000` and uses `TRELLO_MCP_HOST_PORT` for the published host port. | 3000 |
| LOG_LEVEL | No | Pino log level. | info |
| TRANSPORT | No | `http` or `stdio`. | http |
| TRELLO_TOKEN | Yes | Trello token for token auth. | |
| MCP_AUTH_TOKEN | No | If set, HTTP MCP requests to `/mcp` require `Authorization: Bearer <token>`. Leave unset for no HTTP bearer-token check. | |
| TRELLO_API_KEY | Yes | Trello API key. | |
| TRELLO_MCP_NETWORK | No | Docker Compose bridge network name. | trello-mcp_network |
| TRELLO_MCP_HOST_PORT | No | Docker Compose host port mapped to the container's fixed internal `3000` listener. | 3000 |
| TRELLO_MCP_IMAGE_TAG | No | Published image tag; `latest` follows `main`, `X.Y` follows the newest patch in that minor release line, and `X.Y.Z` pins to an exact release. | latest |
| TRELLO_MCP_HOST_BIND_IP | No | Docker Compose host interface bind address. Keep `127.0.0.1` for local-only access; set `0.0.0.0` to publish on all host interfaces for intentional network/LAN exposure. | 127.0.0.1 |
| TRELLO_RETRY_MAX_ATTEMPTS | No | Total attempts for a Trello request when Trello returns HTTP `429`. Must be a positive integer. | 3 |
| TRELLO_RETRY_MAX_DELAY_MS | No | Maximum delay in milliseconds for any HTTP `429` retry wait. Must be a positive integer. | 2000 |
| TRELLO_RATE_LIMIT_CAPACITY | No | Token-bucket capacity for Trello requests before the client waits for a refill. Must be a positive integer. | 100 |
| TRELLO_RETRY_BASE_DELAY_MS | No | Exponential backoff base delay in milliseconds for HTTP `429` retries, with bounded jitter. Must be a positive integer. | 100 |
| TRELLO_ATTACHMENT_UPLOAD_ROOT | No | Absolute server-side directory that enables local file attachment uploads. Leave unset to disable local uploads. | |
| TRELLO_RATE_LIMIT_REFILL_INTERVAL_MS | No | Token-bucket refill interval in milliseconds. Must be a positive integer. | 10000 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed