celery-flower-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FLOWER_URL | No | Base URL of your Flower instance | http://localhost:5555 |
| FLOWER_PASSWORD | No | Basic auth password | |
| FLOWER_USERNAME | No | Basic auth username | |
| FLOWER_API_TOKEN | No | Bearer token (takes priority over basic auth) |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_workersC | List all Celery workers. |
| shutdown_workerB | Shut down a Celery worker. |
| restart_worker_poolC | Restart a worker's process pool. |
| grow_worker_poolC | Grow a worker's process pool by n processes. |
| shrink_worker_poolB | Shrink a worker's process pool by n processes. |
| autoscale_worker_poolB | Set autoscale bounds for a worker's pool. |
| add_queue_consumerC | Make a worker start consuming from a queue. |
| cancel_queue_consumerC | Make a worker stop consuming from a queue. |
| list_tasksC | List tasks with optional filters. |
| list_task_typesA | List all registered task types. |
| get_task_infoC | Get detailed information about a task by its ID. |
| get_task_resultC | Get the result of a task. |
| apply_taskA | Execute a task synchronously and wait for the result. |
| async_apply_taskC | Execute a task asynchronously and return its task ID. |
| send_taskB | Send a task via send_task (does not require task to be registered on the worker). |
| abort_taskC | Abort a running task. |
| revoke_taskC | Revoke a task, optionally terminating it if running. |
| set_task_timeoutC | Change soft and hard time limits for a task on a worker. |
| set_task_rate_limitC | Change the rate limit for a task on a worker. |
| get_queue_lengthsA | Get the current length of all Celery queues. |
| healthcheckA | Check whether the Flower instance is healthy. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 21 tools
Most tools are distinct (e.g., list_workers vs. shutdown_worker), but some overlap exists: create_task vs. apply_task vs. async_apply_task could be confused, and get_task_result vs. get_task_info are similar. However, descriptions clarify the differences.
The majority follow a clear verb_noun pattern (list_*, get_*, set_*, create_, apply_*, etc.). There are minor deviations like 'healthcheck' (instead of check_health) and 'autoscale_worker_pool' (verb+noun with no underscore), but overall consistent.
21 tools is on the higher side but justified given the breadth of Celery/Flower management (workers, tasks, queues, health). The count is within the heavy range but not excessive for a complex domain.
The surface covers worker management (list, shutdown, restart, scale), task lifecycle (apply, send, revoke, abort, get results), and queue control (add/cancel consumer, get lengths). Missing: task retry or purge, but most essential operations are present.