openai-mcp
by wagyourtail
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOCAL_LLM_MODEL | No | Default model name to use, used in quick single-provider env mode. | |
| LOCAL_LLM_CONFIG | No | Path to the configuration file for the MCP server. Example: ~/.config/openai-mcp/config.json. Written by `npm run configure`. | |
| LOCAL_LLM_BASE_URL | No | Base URL of the OpenAI-compatible or Ollama provider, used in quick single-provider env mode (no config file). | |
| LOCAL_LLM_API_KEY_ENV | No | Name of the environment variable holding the API key for the provider, used in quick single-provider env mode. | |
| LOCAL_LLM_RUN_COMMAND | No | Set to enable shell command execution via `run_command`. Omit to disable shell access entirely. | |
| LOCAL_LLM_DYNAMIC_TOOLS | No | Set to enable dynamic tools (register_tool/unregister_tool). Omit to disable dynamic tools entirely. | |
| LOCAL_LLM_PROVIDER_TYPE | No | Provider type (e.g., `ollama` or `openai`), used in quick single-provider env mode. |
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
ResponsivenessNo issues