MCP GitHub Project Manager
by cedrica81
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GITHUB_REPO | Yes | GitHub repository name. Can also be provided via the --repo command line option. | |
| AI_PRD_MODEL | No | AI model used for PRD generation (e.g. claude-opus-5). No defaults — configure what you want to use. | |
| GITHUB_OWNER | Yes | GitHub repository owner (username or organization) that owns the repository/project. Can also be provided via the --owner command line option. | |
| GITHUB_TOKEN | Yes | Your GitHub personal access token. Requires the 'repo' (full repository access), 'project' (project access), and 'write:org' (organization access) permissions. Can also be provided via the --token command line option. | |
| AI_MAIN_MODEL | No | AI model used for general tasks (e.g. claude-sonnet-4-20250514). No defaults — configure what you want to use. | |
| AI_PRD_API_KEY | No | API key for the PRD model role's provider. | |
| GOOGLE_API_KEY | No | Google Gemini API key (optional). Needed for AI-powered features. Create one in Google AI Studio. | |
| OPENAI_API_KEY | No | OpenAI API key (optional). Needed for AI-powered features. Create one on the OpenAI Platform. | |
| AI_MAIN_API_KEY | No | API key for the main model role's provider. | |
| AI_PRD_PROVIDER | No | Provider for the PRD model role (e.g. anthropic). | |
| AI_MAIN_BASE_URL | No | Base URL for the main model role's provider (e.g. https://openrouter.ai/api/v1 or http://localhost:11434/v1). | |
| AI_MAIN_PROVIDER | No | Provider for the main model role. Use 'openai-compatible' for OpenRouter, Together, Groq, Ollama, or any OpenAI-protocol endpoint. | |
| AI_FALLBACK_MODEL | No | AI model used as a fallback (e.g. gpt-4o-mini). No defaults — configure what you want to use. | |
| AI_RESEARCH_MODEL | No | AI model used for research (e.g. sonar-pro). No defaults — configure what you want to use. | |
| ANTHROPIC_API_KEY | No | Anthropic Claude API key (optional). Needed for AI-powered features (ai_generate, ai_analyze, ai_plan). Create one in the Anthropic Console. | |
| PERPLEXITY_API_KEY | No | Perplexity API key (optional). Used for research and analysis tasks. | |
| AI_FALLBACK_API_KEY | No | API key for the fallback model role's provider. | |
| AI_FALLBACK_BASE_URL | No | Base URL for the fallback model role's provider (e.g. http://localhost:11434/v1). | |
| AI_FALLBACK_PROVIDER | No | Provider for the fallback model role (e.g. openai-compatible). |
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
ResponsivenessResponsive