Senior Consult

Connects your AI agent to expert models for architectural guidance, code reviews, and complex problem solving.

typescript

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": {
    "silkyland-senior-consult-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "senior-consult-mcp"
      ],
      "env": {
        "ZAI_API_KEY": "xyz-key",
        "CLAUDE_MODEL": "claude-sonnet-4-5",
        "DEEPSEEK_MODEL": "deepseek-reasoner",
        "GEMINI_API_KEY": "YOUR_API_KEY",
        "OPENAI_API_KEY": "sk-your-openai-key",
        "DEEPSEEK_API_KEY": "YOUR_API_KEY",
        "ANTHROPIC_API_KEY": "YOUR_API_KEY",
        "OPENAI_COMPATIBLE_API_KEY": "xyz-key"
      }
    }
  }
}

Senior Consult MCP connects your AI agent to top-tier models for architectural guidance, code reviews, and complex problem solving. It lets you consult specialized models for high-stakes decisions without changing context, improving accuracy and efficiency.

How to use

You interact with Senior Consult MCP through your MCP client. Start by configuring the MCP server in your client settings so it can run locally or connect to a remote endpoint. Once set up, you can ask for high‑level architecture guidance, have code reviewed for security and quality, request design recommendations, and clear or refine conversation memory when needed.

How to install

Prerequisites: you need Node.js and npm installed on your system. You also need git if you plan to clone the repository.

Option A. npx (Recommended) runs without a local install.

# Run directly without installation
npx -y senior-consult-mcp

Option B. Global installation so you can invoke the MCP server from anywhere.

npm install -g senior-consult-mcp

Option C. Local development to customize and run from source.

git clone https://github.com/silkyland/senior-consult-mcp.git
cd senior-consult-mcp
npm install
npm run build
npm start

Configuration to run with your MCP client

Create or edit your MCP settings to include the server you are running. Use the following pattern to run via npx and pass your API keys and any model overrides you need.

{
  "mcpServers": {
    "senior-consult": {
      "command": "npx",
      "args": ["-y", "senior-consult-mcp"],
      "env": {
        "ANTHROPIC_API_KEY": "your-key",
        "DEEPSEEK_API_KEY": "your-key",
        "GEMINI_API_KEY": "your-key",
        "CLAUDE_MODEL": "claude-sonnet-4-5",
        "DEEPSEEK_MODEL": "deepseek-reasoner"
      }
    }
  }
}

Operational tips

You can issue prompts like “Ask senior to review this authentication flow for security issues” or “Get architecture advice on microservices vs monolith for our scale.” You can also request a code review to identify memory leaks or security concerns. The system uses memory-aware history to keep context concise and relevant.

Additional notes

When you want to run locally, you can also pass environment keys to enable multiple providers such as Claude, GPT, Gemini, DeepSeek, and Z.ai. You can override default models and endpoints if you have specific requirements or proprietary environments.

Available tools

ask_senior

General technical consultation with senior expertise across architectures, languages, and platforms.

code_review

Security, performance, and quality checks on code and design.

architecture_advice

System design guidance to inform architectural decisions.

reset_history

Clear conversation memory and reset context for fresh interaction.

Built by

VeilStrat

AI signals for GTM teams