chatgpt-local-coder
by colin-dmme
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Port for the MCP server. | 3000 |
| SHELL_TIMEOUT | No | Max seconds for run_command. | 120 |
| WORKSPACE_PATH | No | Your project root (like cd before claude). Auto-loads CLAUDE.md / AGENTS.md into MCP instructions. | cwd |
| FULL_DISK_ACCESS | No | Access any path on the machine. | true |
| OPENAI_TUNNEL_ID | No | OpenAI Secure Tunnel ID (optional). | |
| CHATGPT_AUTO_APPROVE | No | Tool annotations to reduce ChatGPT popups. | true |
| MCP_SESSION_RECOVERY | No | Auto-recover stale sessions after restart. | true |
| OPENAI_TUNNEL_API_KEY | No | OpenAI Secure Tunnel Runtime API key (optional). |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessSyncing