external-agent-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RUFF_BIN | No | Path to ruff binary. Default: ruff | |
| CLAUDE_BIN | No | Path to claude binary. Default: /opt/homebrew/bin/claude | |
| GEMINI_BIN | No | Path to gemini binary. Default: /opt/homebrew/bin/gemini | |
| CURSOR_AGENT_BIN | No | Path to cursor binary. Default: /usr/local/bin/cursor | |
| EXTERNAL_AGENT_ALLOWED_ROOTS | No | Colon-separated list of allowed absolute directory paths. If unset, any existing absolute directory is allowed. |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| delegate_tasksA | Create one or more asynchronous external-agent jobs. Use job_status and job_result to inspect completion and artifacts. |
| job_statusA | Read asynchronous job status, including stdout/stderr tails. If no job_ids are supplied, returns recent jobs. |
| job_resultB | Read completed or in-progress job outputs, free-form result text, diff metadata, and artifact paths. |
| search_jobsA | Search historical external-agent jobs by metadata and lightweight previews. Use job_result for full artifacts. |
| cancel_jobsC | Cancel queued or running asynchronous jobs. |
| cleanup_jobsA | Remove terminal job logs/artifacts and associated sandbox worktrees. Non-terminal jobs require force=true. |
| analyze_codeA | Deprecated compatibility wrapper around delegate_tasks for one read-only analysis job. Prefer delegate_tasks + job_result. |
| agent_statusA | Check configured external CLI agent binaries and report provider capability metadata. |
| quality_fixB | Run deterministic allow-listed quality commands such as Ruff format and safe fixes over a bounded file set. |
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 9 tools
Most tools are clearly distinct, focusing on different aspects of job lifecycle (delegate, status, result, cancel, cleanup) and configuration. The deprecated analyze_code tool overlaps with delegate_tasks, creating minor ambiguity, but it's clearly marked deprecated.
All tool names follow a consistent snake_case verb_noun pattern (e.g., cancel_jobs, cleanup_jobs, delegate_tasks, job_status, quality_fix). There are no mixed conventions, making the set predictable for an agent.
With 9 tools, the server is well-scoped for its purpose of managing external agent jobs. Each tool serves a necessary function without superfluous additions, and the count balances coverage and simplicity.
The tool surface covers the main job lifecycle (create, status, result, cancel, cleanup) plus search, configuration check, and a specific quality fix. Minor gap: a dedicated list_jobs tool is missing, but job_status with no job_ids returns recent jobs, covering that need.