agy-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGY_MCP_WORKTREE_DEFAULT | No | Set to '0' to disable automatic worktree mode in execute mode. Default is '1' (enabled). | 1 |
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 |
|---|---|
| agyA | Run agy --print synchronously and return the assistant text + metadata. Compatible drop-in for the legacy |
| agy_continueA | Continue an existing agy session. Identical to |
| agy_startA | Start an agy session in the background. Returns an envelope with status='running' and a job_id you can poll via agy_status / agy_read / agy_cancel. |
| agy_statusB | Return the JobRecord (status, exit code, error, timestamps) for a job_id. |
| agy_readA | Read events from a job's event log. |
| agy_resultA | Return the captured output for a finished background job. Pass |
| agy_cancelA | Signal a running job to stop. Returns |
| agy_sessionsA | List recent jobs, newest first. |
| agy_doctorA | Run capability + auth + session-store probes. Returns a structured report (no secrets) suitable for surfacing to a user via MCP. Pass |
| agy_install_skillA | Install the agy-mcp collaboration skill bundle into one or more agent platforms. |
| agy_purgeA | Delete session-store job directories whose mtime is older than |
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 11 tools
Each tool has a clearly distinct purpose: agy/agy_continue/agy_start differentiate synchronous, resume, and background execution; agy_status/read/result/cancel/sessions cover distinct monitoring and control operations; and agy_doctor/install_skill/purge are separate admin utilities. Even the similar agy_read and agy_result are unambiguously separated by event log vs. captured output.
All tools share the agy_ prefix and snake_case, creating a predictable namespace. However, the pattern mixes imperative verbs (start, read, cancel) with nouns (status, result, sessions), and the bare `agy` tool breaks the verb_noun convention. Despite this, the naming remains readable and internally consistent.
With 11 tools, the server is well-scoped for its purpose, covering synchronous execution, background job lifecycle, monitoring, and admin functions without redundancy or bloat. This falls comfortably within the ideal 3-15 range.
The tool set provides comprehensive coverage of session and job lifecycle: run, continue, start, status, read, result, cancel, list, and purge. Minor gaps exist, such as no direct single-job delete or skill uninstall, but these are not critical to the core workflow and can be worked around.