codex-subagents-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEBUG_MCP | No | Set to '1' to enable debug logging to stderr. | |
| CODEX_SUBAGENTS_DIR | No | Path to the agents directory. If not set, falls back to ./agents, ./.codex-subagents/agents, or dist/../agents. |
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 |
|---|---|
| delegateC | Run a named sub-agent as a clean Codex exec with its own persona/profile. |
| delegate_batchB | Run multiple sub-agents in parallel |
| list_agentsA | List available sub-agents from built-ins and custom agents dir. |
| validate_agentsB | Validate agent files and report errors/warnings per file. |
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 4 tools
Each tool has a clearly distinct purpose: delegate runs one sub-agent, delegate_batch runs many, list_agents shows available agents, and validate_agents checks agent files. There is no meaningful overlap; even delegate and delegate_batch are distinguishable by scope.
All tool names follow a consistent verb_noun pattern in snake_case: delegate, delegate_batch, list_agents, validate_agents. The pattern is uniform and predictable, making the set easy to navigate.
Four tools is well-scoped for managing and running sub-agents. Each tool addresses a distinct part of the workflow (single run, batch run, discovery, validation), leaving no unnecessary bulk or sparseness.
The core delegation lifecycle is covered: listing available agents, validating configuration, running individually, and running in batches. Minor gaps exist such as no explicit tool to fetch agent details or stop/abort runs, but these do not block the primary use case.