Schema | external-agent-mcp

external-agent-mcp

Describes the environment variables required to run the server.

Name	Required	Description
`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.

Features and capabilities supported by this server

Capability	Details
`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.

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/parkavenue9639/external-agent-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server