Codex Project-scoped MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {
"listChanged": true
} |
| prompts | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| project_mcp_statusA | Show which project mcp.json Local Project MCP discovered, which servers connected, and how many tools they expose. Does not return credentials. |
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 1 tool
With only one tool in the set, there is no possibility of confusion or misselection. The tool has a single, clearly bounded purpose: reporting discovered project MCP config and connection status.
The name project_mcp_status is clear, snake_case, and descriptive. However, it is a noun phrase without an action verb and a single sample cannot establish a predictable verb_noun pattern for the server.
One tool is thin for a server whose name implies project-scoped MCP management. The diagnostic is plausible on its own, but the surface feels under-scoped relative to what the server's title suggests.
The surface is read-only status only: no per-server detail, no listing of individual tool names beyond counts, no reload/refresh of discovered config, and no way to act on the reported state. An agent that needs to inspect or fix MCP configuration will hit a dead end.