Orchestration MCP
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| spawn_runB | Start a new external coding-agent run and return immediately. |
| get_runB | Get the current summary status for a known run. |
| poll_eventsB | Long-poll incremental events for a run after a known sequence number. |
| cancel_runB | Cancel a running external coding-agent run. |
| continue_runB | Send an additional input message to a run that is waiting for more input. |
| list_runsC | List runs known to the current orchestration MCP process. |
| get_event_artifactC | Read a sanitized event artifact by run_id, seq, and JSON Pointer field_path. |
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 7 tools
Each tool has a clearly distinct purpose with no overlap: cancel_run stops a run, continue_run sends input, get_event_artifact reads artifacts, get_run retrieves status, list_runs enumerates runs, poll_events monitors events, and spawn_run initiates runs. The descriptions make it easy to distinguish between status retrieval, event handling, run management, and input/output operations.
All tool names follow a consistent verb_noun pattern with snake_case, such as cancel_run, get_run, list_runs, and spawn_run. This uniformity makes the set predictable and easy to navigate, with no deviations in style or structure across the seven tools.
With 7 tools, the count is well-scoped for an orchestration server focused on managing external coding-agent runs. Each tool serves a specific function in the lifecycle of runs, from creation to monitoring and termination, without being overly sparse or bloated, fitting typical orchestration needs.
The tool set provides complete coverage for the orchestration domain: it supports the full lifecycle of runs with spawn_run (create), get_run and list_runs (read), continue_run (update input), and cancel_run (delete/terminate), plus event handling with poll_events and get_event_artifact. There are no obvious gaps, enabling agents to manage runs effectively from start to finish.