Name: Agile Team MCP Server
Author: danielscholl

LABSCO SUMMARY

The decision maker is what separates this from a multiplexer.

Fanning a prompt out to three models is easy and leaves you with three answers to read; having a named model evaluate them against each other and produce one document is the part that saves time. The persona tools chain naturally — a brief becomes a PRD becomes a spec — with each stage able to run through the same team-and-adjudicator pattern.

What it is

A Python server that wraps six LLM providers behind one interface and layers agile personas on top — Business Analyst, Product Manager, Spec Writer, and a Decision Maker that reads several models' answers and chooses. The point is not one more chat wrapper; it is asking three models the same question and having a fourth adjudicate.

What you get

prompt_tool sends text to one or many models named provider:model; list_providers_tool and list_models_tool show what is available
Providers carry short prefixes: o for openai, a for anthropic, g for gemini, q for groq, d for deepseek, l for ollama — so a:claude-3-5-haiku works as well as the full name
prompt_from_file_tool reads the prompt from a file; prompt_from_file2file_tool also writes each response out, with output_path, output_dir and output_extension under your control
persona_dm_tool runs a prompt past a team of models and has persona_dm_model choose between their answers
persona_ba_tool, persona_pm_tool and persona_sw_tool apply the Business Analyst, Product Manager and Spec Writer personas — each takes use_decision_maker to run the same team-and-adjudicator pattern
Model suffixes tune behaviour: :4k and similar set a thinking token budget, :high raises reasoning effort on OpenAI
list_mcp_assets is a prompt that returns the whole capability overview — tools, providers, personas and workflows

Requirements

API keys for whichever providers you intend to use: OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY, GROQ_API_KEY, DEEPSEEK_API_KEY, and OLLAMA_HOST for a local Ollama. Run it through uvx --from git+https://github.com/danielscholl/agile-team-mcp-server@main agile-team, or clone and uv sync then uv pip install -e .. DEFAULT_MODEL, DEFAULT_TEAM_MODELS and DEFAULT_DECISION_MAKER_MODEL set what runs when you don't name models explicitly. Prompts come from files, so the paths you pass must be readable by the server.

Setup effort

Build from source — git clone https://github.com/danielscholl/agile-team-mcp-server.git

See installation options

USE CASES

Getting a decision instead of three opinions

Send the question to a team of models and let the decision maker pick.

persona_dm_tool

Turning a rough concept into a project brief

Run it through the Business Analyst persona and write the result to a file.

persona_ba_tool

Taking a brief through to a developer-ready spec

Chain the Product Manager and Spec Writer personas over the previous output.

persona_pm_toolpersona_sw_tool

Comparing how models handle the same prompt

Send one prompt to several and read the answers side by side.

prompt_tool

Batch-processing prompts you keep in files

Read from a file and write each response to its own output file.

prompt_from_file2file_tool

9 tools

Listed in project docs. Your client may show a different list.

list_providers_tool

list_models_tool

prompt_tool

prompt_from_file_tool

prompt_from_file2file_tool

persona_dm_tool

persona_ba_tool

persona_pm_tool

persona_sw_tool

INSTALLATION

Connect your client

Server setup

TERMINAL

# 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

MCP Clients

Claude Desktop

CLAUDE DESKTOP · JSON

{
  "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"
      }
    }
  }
}

Claude Code

CLAUDE CODE · JSON

{
  "mcpServers": {
    "agile-team-mcp-server": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/danielscholl/agile-team-mcp-server@main",
        "agile-team"
      ],
      "env": {
        "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"
      }
    }
  }
}

VS Code — uvx

Add this to .vscode/mcp.json. VS Code asks for each provider key when the server first starts; leave blank the providers you do not use.

VS CODE — UVX · JSON

{
  "inputs": [
    {
      "id": "openai_key",
      "type": "promptString",
      "description": "OpenAI API Key",
      "password": true
    },
    {
      "id": "anthropic_key",
      "type": "promptString",
      "description": "Anthropic API Key",
      "password": true
    },
    {
      "id": "gemini_key",
      "type": "promptString",
      "description": "Google Gemini API Key",
      "password": true
    },
    {
      "id": "groq_key",
      "type": "promptString",
      "description": "Groq API Key",
      "password": true
    },
    {
      "id": "deepseek_key",
      "type": "promptString",
      "description": "DeepSeek API Key",
      "password": true
    }
  ],
  "servers": {
    "agile-team": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/danielscholl/agile-team-mcp-server@main",
        "agile-team"
      ],
      "env": {
        "OPENAI_API_KEY": "${input:openai_key}",
        "ANTHROPIC_API_KEY": "${input:anthropic_key}",
        "GEMINI_API_KEY": "${input:gemini_key}",
        "GROQ_API_KEY": "${input:groq_key}",
        "DEEPSEEK_API_KEY": "${input: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"
      }
    }
  }
}

Any MCP client — In-repo

ANY MCP CLIENT — IN-REPO · JSON

{
  "mcpServers": {
    "agile-team": {
      "type": "stdio",
      "command": "uv",
      "args": [
        "run",
        "agile-team"
      ],
      "env": {}
    }
  }
}

Agile Team MCP Server

The decision maker is what separates this from a multiplexer.

What it is

What you get

Requirements

Setup effort

Getting a decision instead of three opinions

Turning a rough concept into a project brief

Taking a brief through to a developer-ready spec

Comparing how models handle the same prompt

Batch-processing prompts you keep in files

9 tools

What to know first

Tools you get

Requires

Where it runs

Connect your client

Server setup

MCP Clients

Claude Desktop

Claude Code

VS Code — uvx

Any MCP client — In-repo

Agile Team MCP Server

The decision maker is what separates this from a multiplexer.

What it is

What you get

Requirements

Setup effort

Getting a decision instead of three opinions

Turning a rough concept into a project brief

Taking a brief through to a developer-ready spec

Comparing how models handle the same prompt

Batch-processing prompts you keep in files

9 tools

What to know first

Tools you get

Requires

Where it runs

Connect your client

Server setup

MCP Clients

Claude Desktop

Claude Code

VS Code — uvx

Any MCP client — In-repo

Same category

Unichat

Second Opinion

Cursor Admin

BlockRun MCP