copilot-agents-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GH_TOKEN | No | Fallback GitHub token used if GITHUB_PERSONAL_ACCESS_TOKEN is not set. | |
| GITHUB_TOKEN | No | Last-resort fallback GitHub token used if GITHUB_PERSONAL_ACCESS_TOKEN and GH_TOKEN are not set. | |
| GITHUB_TOOLS | No | Same as the official GitHub MCP server: selects specific enabled tools. | |
| GITHUB_TOOLSETS | No | Same as the official GitHub MCP server: selects the enabled toolsets. | |
| GITHUB_READ_ONLY | No | Same as the official GitHub MCP server: restricts the server to read-only operations. | |
| COPILOT_AGENTS_LOG | No | If set, the watcher appends its standard error to this file. | |
| GITHUB_EXCLUDE_TOOLS | No | Same as the official GitHub MCP server: excludes specific tools. | |
| COPILOT_AGENTS_NOTIFY_URL | No | URL for the JSON POST notification sent when a task finishes. If not set, no POST is sent. | |
| COPILOT_AGENTS_STATE_PATH | No | State file path. Defaults to ~/.copilot-agents-mcp/state.json. | |
| GITHUB_PERSONAL_ACCESS_TOKEN | No | GitHub token with 'Agent tasks: read and write' permission on the repositories where tasks are launched. Used first. Required to launch/read agent tasks and list Copilot models; not required to list tools. | |
| COPILOT_AGENTS_POLL_INTERVAL_MS | No | Pause between task status reads, in milliseconds. Defaults to 15000. | |
| COPILOT_AGENTS_NOTIFY_AUTHORIZATION | No | Value of the Authorization header for the notification POST. If not set, the POST does not include this header. |
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 |
|---|---|
| create_agent_taskA | Lanza una tarea del agente de Copilot en la nube. El modelo se envía tal cual. Si ese modelo ya se vio rechazado, no llama a la API y lista los modelos vistos aceptados. |
| get_agent_taskB | Lee una vez el estado de una tarea del agente de Copilot. |
| list_copilot_modelsA | Lee /agents/swe/models y devuelve id, nombre, vendor, preview, el precio por tokens o el multiplier, y la promo si existe. |
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 3 tools
The three tools target clearly distinct actions: launching a task, reading task status, and listing available models. The only blur is that create_agent_task embeds a model-listing fallback behavior, which slightly overlaps with list_copilot_models, but an agent can still tell them apart.
All three names follow a snake_case verb_noun pattern (create_agent_task, get_agent_task, list_copilot_models), which is predictable. The minor deviation is that the noun changes between agent_task and copilot_models, and 'copilot' is redundantly embedded in one name.
Three tools is quite thin for a task-lifecycle server; launching and reading a task without any other lifecycle operations leaves little room for real workflows. The count is defensible for a narrow wrapper, but it sits at the borderline of feeling under-scoped.
The surface covers launch, single status read, and model listing, but there is no way to cancel/stop a task, list existing tasks, wait or poll for completion, or retrieve logs/artifacts. These gaps will likely force agents into dead ends during real task management.