CodexPro
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
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| server_configA | Show CodexPro server configuration, safety modes, limits, and blocked paths. Does not reveal auth tokens. |
| codexpro_self_testA | Run one controlled, local-only CodexPro diagnostic. It checks modes, expected tools, workspace access, skills, git, safe bash policy, selected-only Pro context, and optional .ai-bridge write/edit without touching source files. |
| load_skillA | Load the bounded SKILL.md body for a discovered workspace, user, or plugin skill by name. Does not accept arbitrary paths; use after open_current_workspace/open_workspace shows skill_inventory. |
| open_current_workspaceA | Use this once at the start to open the configured default workspace without accepting a path. Do not call open_workspace after this unless switching roots. |
| open_workspaceA | Open a local project directory as a CodexPro workspace. Returns a workspace_id plus git status, AGENTS.md, skills, and a compact file tree. |
| treeA | List files and directories inside the workspace, excluding blocked paths. |
| searchA | Use this for targeted verification or code lookup. Prefer one specific final search instead of repeated broad verification searches. |
| readA | Read a specific text file with line numbers. Avoid rereading files after write/edit unless exact final content is needed. |
| writeB | Create or overwrite a meaningful text file inside the workspace. Returns a unified diff; do not create empty placeholder files. |
| editB | Apply a targeted exact text replacement inside a workspace text file. Returns a unified diff. |
| bashA | Run one allowlisted verification command in the workspace, such as tests, build, lint, typecheck, or a project script. Do not use for git status/diff or file inspection; use show_changes, tree, search, and read instead. Do not chain commands with &&, pipes, redirects, or shell file readers. |
| show_changesA | Summarize the current workspace changes in one review-oriented result with git status, diff stats, and optional diff. Use this instead of bash git status, bash git diff, git_status, or git_diff when reviewing work. |
| read_handoffA | Read the shared .ai-bridge planning files used for ChatGPT-to-agent coordination. |
| export_pro_contextA | Create .ai-bridge/pro-context.md with repo tree, git state, selected files, and handoff context for high-context ChatGPT planning without live MCP tool calls. |
| handoff_to_agentA | Write .ai-bridge/current-plan.md for Codex, OpenCode, Pi, or another local implementation agent. This only creates handoff files; it does not execute local agent commands. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| codexpro-tool-card | Compact visual renderer for CodexPro workspace orientation, source changes, and handoffs. |
TDQS
Scored across 15 tools
Each tool has a distinct purpose: workspace opening, file operations, verification, handoff, and diagnostics. Even similar tools like open_current_workspace/open_workspace and show_changes/bash are clearly differentiated through descriptions.
Mixed naming conventions: some tools use verb_noun (load_skill, show_changes), some are bare verbs (search, read, write, edit), and a few are nouns (tree, bash) or hyphenated identifiers (codexpro_self_test). Although most names are readable, the pattern is not uniform.
15 tools is well-scoped for a coding workspace MCP server. Each tool covers a distinct operation without redundancy, and the count is within the ideal 3-15 range.
The tool surface covers workspace discovery, file read/write/edit, search, verification, change review, and agent handoff. Minor gaps exist (e.g., no explicit file delete or config modification), but core workflows are fully supported.