MCP GitHub Project Manager
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GITHUB_REPO | Yes | GitHub repository name. | |
| AI_PRD_MODEL | No | Optional. Model used for PRD generation. | |
| GITHUB_OWNER | Yes | GitHub repository owner (username or organization). | |
| GITHUB_TOKEN | Yes | Your GitHub personal access token. Requires `repo` (Full repository access), `project` (Project access), and `write:org` (Organization access) permissions. | |
| AI_MAIN_MODEL | No | Optional. Model used for general tasks. No default — configure the model you want to use. | |
| AI_PRD_API_KEY | No | Optional. API key for the PRD generation model role provider. | |
| GOOGLE_API_KEY | No | Optional. Google Gemini API key used as an AI provider. | |
| OPENAI_API_KEY | No | Optional. OpenAI API key used as an AI provider. | |
| AI_MAIN_API_KEY | No | Optional. API key for the main model role provider. | |
| AI_PRD_BASE_URL | No | Optional. Base URL for the PRD generation model role provider. | |
| AI_PRD_PROVIDER | No | Optional. Provider for the PRD generation model role. | |
| AI_MAIN_BASE_URL | No | Optional. Base URL for the main model role provider. | |
| AI_MAIN_PROVIDER | No | Optional. Provider for the main model role. Use `openai-compatible` for OpenRouter, Together, Groq, Ollama, or any OpenAI-protocol endpoint. | |
| AI_FALLBACK_MODEL | No | Optional. Model used as a fallback. | |
| AI_RESEARCH_MODEL | No | Optional. Model used for research tasks. | |
| ANTHROPIC_API_KEY | No | Optional. Anthropic Claude API key used by AI-powered features (`ai_generate`, `ai_analyze`, `ai_plan`). At least one AI provider key is needed for AI features; non-AI tools work without any. | |
| PERPLEXITY_API_KEY | No | Optional. Perplexity API key used for research and analysis tasks. | |
| AI_FALLBACK_API_KEY | No | Optional. API key for the fallback model role provider. | |
| AI_FALLBACK_BASE_URL | No | Optional. Base URL for the fallback model role provider. | |
| AI_FALLBACK_PROVIDER | No | Optional. Provider for the fallback model role. |
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
ActivityActive
ResponsivenessNo issues