Schema | Agent Collaboration Orchestrator

Agent Collaboration Orchestrator

Describes the environment variables required to run the server.

Name	Required	Description
`SANDBOX_ROOT`	No	Codex 允许访问的协同工作空间根目录。
`EXECUTOR_MODEL`	No	默认模型名称，会写入任务 prompt 供执行器参考。
`CODEX_EXECUTOR_ARGS`	No	Codex 启动参数模板。默认通过 stdin 传入 prompt。
`EXECUTOR_TIMEOUT_MS`	No	Codex 子任务超时时间，默认 30 分钟。
`CODEX_EXECUTOR_COMMAND`	No	Codex 执行入口，例如 codex.cmd、codex.exe、node、powershell 或自定义中转脚本。

Features and capabilities supported by this server

Capability	Details
`tools`	{}

Functions exposed to the LLM to take actions

Name	Description
submit_taskB	Submit a development task to the executor agent
get_task_statusC	Get the status of a task
get_task_logC	Get execution logs for a task
get_result_reportA	Get the final result report for a completed task
request_revisionC	Request revision for a task
cancel_taskB	Cancel a running or pending task
list_artifactsB	List files and artifacts produced by a task
list_tasksB	List task summaries for TRAE desktop/mobile progress views
get_mobile_dashboardB	Get a compact dashboard with task counts, recent tasks, and pending permission requests
list_permission_requestsB	List permission requests created after Codex fails due to sandbox or approval restrictions
resolve_permission_requestA	Approve or reject a pending permission request. Approval creates a retry task with the requested sandbox.
diagnose_environmentB	Check the MCP environment configuration

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/muanlin/agent-collaboration-orchestrator'

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