MCP GitHub Project Manager
by Lievew939
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 | AI model to use for PRD generation (e.g. claude-opus-5). No default — configure what you want to use. | |
| GITHUB_OWNER | Yes | GitHub repository owner (username or organization). | |
| GITHUB_TOKEN | Yes | GitHub personal access token. Requires the repo, project, and write:org permissions. | |
| AI_MAIN_MODEL | No | AI model to use for general tasks (e.g. claude-sonnet-4-20250514). No default — configure what you want to use. | |
| AI_PRD_API_KEY | No | API key for the PRD generation model provider role. | |
| GOOGLE_API_KEY | No | Google Gemini API key for AI-powered features. Optional. | |
| OPENAI_API_KEY | No | OpenAI API key for AI-powered features. Optional. | |
| AI_MAIN_API_KEY | No | API key for the main model provider role. | |
| AI_PRD_PROVIDER | No | Provider for the PRD generation model role (e.g. anthropic). | |
| AI_MAIN_BASE_URL | No | Base URL for the main model provider (e.g. https://openrouter.ai/api/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 to use as fallback (e.g. gpt-4o-mini). No default — configure what you want to use. | |
| AI_RESEARCH_MODEL | No | AI model to use for research (e.g. sonar-pro). No default — configure what you want to use. | |
| ANTHROPIC_API_KEY | No | Anthropic Claude API key. AI keys are optional; without them, non-AI tools work fine but AI-powered features (ai_generate, ai_analyze, ai_plan) need at least one key. | |
| PERPLEXITY_API_KEY | No | Perplexity API key for AI-powered research and analysis tasks. Optional. | |
| AI_FALLBACK_API_KEY | No | API key for the fallback model provider role. | |
| AI_FALLBACK_BASE_URL | No | Base URL for the fallback model 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