Agent Jobs MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| cancel_jobB | Cancels an agent job by its ID. |
| create_jobB | Create a new Agent Job with the minimal set of fields. |
| get_jobB | Retrieves an agent job by its ID. |
| get_job_typeB | Retrieves an agent job type by its ID. |
| get_jobs_statsA | Get aggregated statistics for agent jobs without retrieving individual job data. Optimized for dashboards and monitoring with minimal network overhead. |
| list_jobsB | Retrieves a list of agent jobs, with optional filters and pagination. |
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 6 tools
Every tool has a clearly distinct purpose with no ambiguity. Each targets a specific resource or action: cancel_job, create_job, get_job, get_jobs_stats, get_job_type, and list_jobs are all well-defined and non-overlapping. An agent can easily distinguish between them based on their names and descriptions.
All tool names follow a consistent verb_noun pattern throughout, using snake_case uniformly. The verbs (cancel, create, get, list) are clear and predictable, making the set easy to navigate and understand without any deviations or mixed conventions.
With 6 tools, the server is well-scoped for managing agent jobs. Each tool earns its place by covering essential operations like creation, retrieval, listing, cancellation, statistics, and job type handling, without being too sparse or bloated for the domain.
The tool surface provides strong coverage for the agent jobs domain, including CRUD-like operations (create, get, list, cancel) and additional utilities (stats, job type). A minor gap exists in update operations (e.g., update_job), but agents can likely work around this by recreating jobs or using other methods.