Skip to main content
Glama
kky42

codex-as-mcp

by kky42
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PROVIDER_API_KEYYesAPI key for the third-party provider used by Codex CLI. Required if the provider's config uses an env_key.

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

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
spawn_agentB

Spawn a Codex agent to work inside the current working directory.

The server resolves the working directory via ``os.getcwd()`` so it inherits
whatever environment the MCP process currently has.

Args:
    prompt: All instructions/context the agent needs for the task.

Returns:
    The agent's final response (clean output from Codex CLI).
spawn_agents_parallelA

Spawn multiple Codex agents in parallel.

Each spawned agent reuses the server's current working directory
(``os.getcwd()``).

Args:
    agents: List of agent specs, each with a 'prompt' entry.
            Example: [
                {"prompt": "Create math.md"},
                {"prompt": "Create story.md"}
            ]

Returns:
    List of results with 'index', 'output', and optional 'error' fields.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.9/5.0

Scored across 2 tools

Disambiguation4/5

The two tools are clearly distinguished by singular vs. parallel operation, with descriptions explicitly stating that spawn_agents_parallel handles multiple agents at once. However, both share the core 'spawn agent' purpose, so they could be confused if the agent doesn't read carefully.

Naming Consistency5/5

Both tools use consistent snake_case with the verb 'spawn' followed by a noun, and the parallel tool adds a clear '_parallel' suffix. The naming pattern is predictable and easy to follow.

Tool Count3/5

With only two tools, the server feels minimal. While the focus is narrow (spawning Codex agents), two tools is on the thin side and could arguably be combined into one with a loop.

Completeness4/5

The server covers the fundamental operations: spawning a single agent or multiple in parallel. Minor gaps include lack of configuration options (e.g., working directory or model), but these are not essential for the core purpose.

Maintenance

ActivityInactive
ResponsivenessSlow

Resources