- Home
- MCP servers
- Agile Team
Agile Team
- typescript
0
GitHub Stars
typescript
Language
5 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"danielscholl-agile-team-mcp-server": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/danielscholl/agile-team-mcp-server@main",
"agile-team"
],
"env": {
"OLLAMA_HOST": "http://localhost:11434",
"GROQ_API_KEY": "<YOUR_GROQ_KEY>",
"DEFAULT_MODEL": "openai:gpt-4o-mini",
"GEMINI_API_KEY": "<YOUR_GEMINI_KEY>",
"OPENAI_API_KEY": "<YOUR_OPENAI_KEY>",
"DEEPSEEK_API_KEY": "<YOUR_DEEPSEEK_KEY>",
"ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_KEY>",
"DEFAULT_TEAM_MODELS": "[\"openai:gpt-4.1\",\"anthropic:claude-3-7-sonnet\",\"gemini:gemini-2.5-pro\"]",
"DEFAULT_DECISION_MAKER_MODEL": "openai:gpt-4o-mini"
}
}
}
}You have a scalable MCP server that orchestrates multiple LLM providers through specialized Agile team personas. It lets you wrap models, manage provider/model names, work with prompts from files, and run team-based workflows with built-in personas like Business Analyst, Product Manager, Spec Writer, and Team Decision Maker.
How to use
Connect to the Agile Team MCP Server with an MCP client to access a suite of tools and personas. You can run prompts across multiple providers, discover available models, load prompts from files, and let multiple models collaborate as a team. Use the Team Decision Maker to evaluate competing solutions and pick the best approach. Use the specialized personas to generate briefs, PRDs, specs, and product plans, then consolidate results into cohesive documents.
How to install
Prerequisites: ensure you have Node tooling and Python available in your environment. You will install the MCP server locally, then connect with an MCP client.
Step 1: Clone the project and navigate to the directory.
Step 2: Install dependencies and prepare the runtime.
Step 3: Run the server and verify tests to confirm a healthy setup.
# Clone and install
git clone https://github.com/danielscholl/agile-team-mcp-server.git
cd agile-team-mcp-server
uv sync
# Install
uv pip install -e .
# Run tests to verify installation
uv run pytest
Configuration and usage notes
Configure your client to connect via the provided MCP entry point. You can also configure environment keys to enable multiple providers and default models. See the example configuration for Claude.app if you need a ready-made setup.
Security and environment setup
Store API keys securely in your environment configuration. Do not expose keys in logs or publicly accessible files. Use your preferred secret management strategy for keys such as OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY, GROQ_API_KEY, and DEEPSEEK_API_KEY. Ensure OLLAMA_HOST points to your local or remote hosting endpoint if you leverage local model runners.
Troubleshooting tips
If you cannot connect, verify that the MCP server is running and that your MCP client is configured to use the agile-team entry. Check that the required environment keys are present and correct. If a provider model cannot be discovered, confirm you have network access and valid API keys for the providers you intend to use.
Example configuration you can apply
The following configuration enables the Agile Team MCP Server as a stdio-based MCP server using uvx. It includes development keys and defaults to a mixed model lineup.
{
"mcpServers": {
"agile-team": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/danielscholl/agile-team-mcp-server@main",
"agile-team"
],
"env": {
"OPENAI_API_KEY": "<YOUR_OPENAI_KEY>",
"ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_KEY>",
"GEMINI_API_KEY": "<YOUR_GEMINI_KEY>",
"GROQ_API_KEY": "<YOUR_GROQ_KEY>",
"DEEPSEEK_API_KEY": "<YOUR_DEEPSEEK_KEY>",
"OLLAMA_HOST": "http://localhost:11434",
"DEFAULT_MODEL": "openai:gpt-4o-mini",
"DEFAULT_TEAM_MODELS": "[\"openai:gpt-4.1\",\"anthropic:claude-3-7-sonnet\",\"gemini:gemini-2.5-pro\"]",
"DEFAULT_DECISION_MAKER_MODEL": "openai:gpt-4o-mini"
}
}
}
}
Available tools
list_mcp_assets
Get a comprehensive overview of server capabilities including tools, personas, providers, and workflows.
list_providers_tool
Lists all supported LLM providers and their shortcut prefixes.
list_models_tool
Lists available models for a specific provider.
prompt_tool
Send prompts to one or multiple models and receive responses.
prompt_from_file_tool
Process prompts from files and retrieve responses.
prompt_from_file2file_tool
Process prompts from a file and write responses to a designated output file.
persona_dm_tool
Team-based decision making by combining multiple models and a decision maker model.
persona_ba_tool
Business Analyst persona for creating briefs, requirements, and analyses.
persona_pm_tool
Product Manager persona for product plans, roadmaps, and requirements.
persona_sw_tool
Spec Writer persona for developer-ready specifications and validation steps.