GitHub MCP Agent
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_MODEL | No | Model id for the provider | |
| LLM_API_KEY | Yes | Any provider key: Google, OpenAI, DeepSeek, Groq, Cloudflare, etc. | |
| GITHUB_TOKEN | Yes | GitHub personal access token for authenticating REST API calls | |
| GROQ_API_KEY | No | Groq API key (alternative to LLM_API_KEY) | |
| LLM_BASE_URL | No | OpenAI-compatible base URL (for custom provider or Cloudflare override) | |
| LLM_PROVIDER | No | Provider name: openai, google, deepseek, cloudflare, anthropic, groq, openrouter, mistral, xai, together, or custom | |
| GOOGLE_API_KEY | No | Google API key (alternative to LLM_API_KEY) | |
| OPENAI_API_KEY | No | OpenAI API key (alternative to LLM_API_KEY) | |
| DEEPSEEK_API_KEY | No | DeepSeek API key (alternative to LLM_API_KEY) | |
| CLOUDFLARE_ACCOUNT_ID | No | Cloudflare account ID used to build the Workers AI URL |
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