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 | AI model used for PRD generation (e.g. claude-opus-5). | |
| GITHUB_OWNER | Yes | GitHub repository owner (username or organization). | |
| GITHUB_TOKEN | Yes | GitHub personal access token. Requires `repo` (full repository access), `project` (project access), and `write:org` (organization access) permissions. | |
| AI_MAIN_MODEL | No | AI model used for general tasks. No default — configure what you want to use (e.g. claude-sonnet-4-20250514). | |
| AI_PRD_API_KEY | No | API key specific to the PRD generation model role/provider. | |
| GOOGLE_API_KEY | No | Google Gemini API key. Optional — an additional AI provider. | |
| OPENAI_API_KEY | No | OpenAI API key. Optional — an alternative AI provider. | |
| AI_MAIN_API_KEY | No | API key specific to the main model role/provider. | |
| AI_PRD_PROVIDER | No | Provider for the PRD generation model role. | |
| 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 (e.g. anthropic, openai, openai-compatible). Use `openai-compatible` for OpenRouter, Together, Groq, Ollama, or any OpenAI-protocol endpoint. | |
| AI_FALLBACK_MODEL | No | AI model used as fallback (e.g. gpt-4o-mini). | |
| AI_RESEARCH_MODEL | No | AI model used for research tasks (e.g. sonar-pro). | |
| ANTHROPIC_API_KEY | No | Anthropic Claude API key. Optional — AI-powered features need at least one provider key, but non-AI tools work without any. | |
| PERPLEXITY_API_KEY | No | Perplexity API key. Optional — used for research and analysis tasks. | |
| AI_FALLBACK_API_KEY | No | API key specific to the fallback model role/provider. | |
| AI_FALLBACK_BASE_URL | No | Base URL for the fallback model provider (e.g. http://localhost:11434/v1 for local Ollama). | |
| AI_FALLBACK_PROVIDER | No | 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
ResponsivenessResponsive