Skip to main content
Glama

Senior Consult MCP

Let your AI agent consult top-tier models for expert technical guidance.

An MCP server that connects your AI agent to expert models (Claude, GPT, Gemini, DeepSeek, Z.ai) for architectural advice, code reviews, and complex problem-solving.

Why?

Your AI agent is great, but sometimes it needs a second opinion. This MCP server lets it consult specialized models for high-stakes decisions without switching context.

Related MCP server: Ask-a-Friend

Tools

Tool

Description

ask_senior

General technical consultation

code_review

Security, performance & quality checks

architecture_advice

System design guidance

reset_history

Clear conversation memory

Quick Start

1. Configure MCP Client

Add to your MCP settings (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "senior-consult": {
      "command": "npx",
      "args": ["-y", "senior-consult-mcp"],
      "env": {
        "ANTHROPIC_API_KEY": "your-key"
      }
    }
  }
}

2. Use It

  • "Ask senior to review this authentication flow for security issues"

  • "Get architecture advice on microservices vs monolith for our scale"

  • "Code review this function for potential memory leaks"

Installation

Option A: npx (Recommended)

# No install needed - runs directly
npx -y senior-consult-mcp

Option B: Global

npm install -g senior-consult-mcp

Option C: Local Development

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

Environment Variables

API Keys

Set at least one provider key:

ANTHROPIC_API_KEY=sk-ant-...      # Claude
OPENAI_API_KEY=sk-...             # GPT
GEMINI_API_KEY=...                # Gemini
DEEPSEEK_API_KEY=sk-...           # DeepSeek
ZAI_API_KEY=...                   # Z.ai (or ZHIPU_API_KEY)
OPENAI_COMPATIBLE_API_KEY=...     # Custom endpoint

Model Configuration (Optional)

Override default models:

# Claude
CLAUDE_MODEL=claude-sonnet-4-5
CLAUDE_URL=https://api.anthropic.com/v1/messages

# OpenAI
OPENAI_MODEL=gpt-4o
OPENAI_URL=https://api.openai.com/v1/chat/completions

# Gemini
GEMINI_MODEL=gemini-2.5-flash

# DeepSeek
DEEPSEEK_MODEL=deepseek-chat
DEEPSEEK_URL=https://api.deepseek.com/chat/completions

# Z.ai
ZAI_MODEL=glm-4-plus
ZAI_URL=https://open.bigmodel.cn/api/paas/v4/chat/completions

# Custom OpenAI-compatible
OPENAI_COMPATIBLE_MODEL=your-model
OPENAI_COMPATIBLE_URL=https://your-endpoint/v1/chat/completions

Full Example Config

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

Features

  • Multi-Provider - Claude, GPT, Gemini, DeepSeek, Z.ai, custom endpoints

  • Smart Memory - Token-aware history with auto-trimming

  • Optimized Prompts - Tuned for concise, actionable advice

  • Zero Config - Works out of the box with sensible defaults

Contributing

We welcome contributions! Here's how you can help:

Ways to Contribute

  • Report bugs - Open an issue with reproduction steps

  • Suggest features - Share ideas in discussions

  • Improve docs - Fix typos, add examples

  • Submit PRs - Bug fixes, new providers, optimizations

Development Setup

# Clone & install
git clone https://github.com/silkyland/senior-consult-mcp.git
cd senior-consult-mcp
npm install

# Build & test
npm run build

# Run locally
npm start

Pull Request Process

  1. Fork the repo

  2. Create feature branch (git checkout -b feature/awesome)

  3. Make changes & add tests

  4. Commit (git commit -m 'Add awesome feature')

  5. Push (git push origin feature/awesome)

  6. Open PR with clear description

Code Style

  • TypeScript strict mode

  • ESLint + Prettier

  • Meaningful commit messages

  • Tests for new features

License

MIT


Questions? Open an issue or start a discussion.

Like this project? Give it a star to show support!

Available Tools

4 tools
architecture_adviceB

Get architecture and design pattern recommendations from a senior AI.

Inputs: problem (required).

ask_seniorC

General purpose consultation with a senior AI developer mentor.

Inputs: question (required).

code_reviewC

Request a code review from a senior AI developer.

Inputs: code (required).

reset_historyB

Clear the conversation memory/history.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.1/5.0

    Scored across 4 tools

    Disambiguation3/5

    The tools have overlapping purposes that could cause confusion, particularly between 'architecture_advice' and 'ask_senior' which both involve consulting a senior AI. However, 'code_review' and 'reset_history' are clearly distinct, and descriptions help differentiate the general consultation from specific architecture advice.

    Naming Consistency4/5

    The naming follows a consistent snake_case pattern throughout, with clear verb_noun structures like 'get_architecture_advice' implied. Minor deviations exist, such as 'ask_senior' being less descriptive than others, but overall the conventions are readable and predictable.

    Tool Count4/5

    With 4 tools, the count is reasonable for a consultation server, covering core functions like advice, review, and history management. It's slightly lean but well-scoped, with each tool earning its place without feeling excessive or insufficient for the domain.

    Completeness3/5

    The tool set covers key consultation aspects like advice and code review, but there are notable gaps. For example, there's no tool for follow-up queries or iterative feedback, which could limit agent workflows. The surface is functional but not fully comprehensive for a senior consultation domain.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      D
      maintenance
      Enables AI agents to consult with multiple AI models (GPT, Gemini, Grok, etc.) through OpenRouter with intelligent auto-selection, conversation history, and caching. Allows your AI assistant to seek expert opinions from specialized models for different tasks like coding, analysis, or general questions.
      2
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI coding agents to request a second opinion from a different frontier model via a single tool call, with PII scrubbed before transit, live web search, and support for Claude, ChatGPT, Cursor, and Gemini.
      Apache 2.0
    • F
      license
      Not graded
      quality
      C
      maintenance
      Enables AI assistants to orchestrate multiple models from different providers within a single conversation, supporting collaborative code review, planning, debugging, and implementation workflows with full context continuity.
      -
    • F
      license
      Not graded
      quality
      Not graded
      maintenance
      Enables a primary AI coding assistant to delegate tasks in parallel to specialized sub-agents such as Gemini, Claude, Codex, and Cursor, sharing project context and synthesizing their outputs into a single response from within the IDE. It runs entirely on existing local CLI tools and subscriptions with no added cost or markup.
      -