Skip to main content
Glama

AI Consultant MCP Server

A Model Context Protocol (MCP) server that enables AI agents to consult with multiple AI models through OpenRouter. Features intelligent model auto-selection, conversation history, caching, and robust error handling.

What is this?

This MCP server allows your AI assistant (like Claude Desktop) to consult with various AI models (GPT, Gemini, Grok, etc.) through a single interface. It automatically selects the best model for your task or lets you choose a specific one.

Related MCP server: Senior Consult MCP

Quick Start

Installation from npm

npm install -g ai-consultant-mcp

Prerequisites

You'll need an OpenRouter API key. Get one at OpenRouter.

Configuration

Edit your MCP client configuration file:

For Claude Desktop:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "ai-consultant": {
      "command": "npx",
      "args": ["-y", "ai-consultant-mcp"],
      "env": {
        "OPENROUTER_API_KEY": "your-openrouter-api-key"
      }
    }
  }
}

For other MCP clients:

Configure according to your client's documentation, using npx -y ai-consultant-mcp as the command.

Option 2: Running locally (Development)

  1. Clone the repository:

git clone https://github.com/filipkrayem/ai-consultant-mcp.git
cd ai-consultant-mcp
  1. Install dependencies:

npm install
  1. Build the project:

npm run build
  1. Configure your MCP client:

{
  "mcpServers": {
    "ai-consultant": {
      "command": "node",
      "args": ["/absolute/path/to/ai-consultant-mcp/dist/index.js"],
      "env": {
        "OPENROUTER_API_KEY": "your-openrouter-api-key"
      }
    }
  }
}

Environment Variables

  • OPENROUTER_API_KEY (required): Your OpenRouter API key

  • VERBOSE_LOGGING (optional): Set to true or 1 to enable detailed logging. Default: false

Available Models

  • gemini-2.5-pro: Google's Gemini 2.5 Pro - general purpose tasks and quick questions

  • gpt-5-codex: OpenAI's GPT-5 Codex - coding tasks, debugging, and refactoring

  • grok-code-fast-1: xAI's Grok Code Fast 1 - code review, complex reasoning, and analysis

Features

  • 🤖 Multiple AI models - Access GPT, Gemini, Grok, and more through one interface

  • 🎯 Smart model selection - Automatically picks the best model for your task

  • 💬 Conversation history - Maintain context across multiple questions

  • ⚡ Response caching - Reduces API calls and costs

  • 🔄 Automatic retries - Handles transient failures gracefully

  • 🛡️ Circuit breaker - Prevents cascading failures

  • 📊 Token tracking - Monitor usage for each consultation

Usage

Once configured, your AI assistant can use these tools:

  • consult_ai - Ask questions to AI models (auto-selects or specify a model)

  • list_models - See all available models and their capabilities

Simply ask your AI assistant to consult with AI models. For example:

  • "Consult this change with Grok and Codex"

  • "Have Grok review your code first"

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

MIT

Available Tools

2 tools
consult_aiA

Consult with an AI model via OpenRouter. You can either specify a model or let the system auto-select based on your task. For sequential multi-model consultation, use the 'models' parameter to specify multiple models.

Inputs: prompt (required), clear_history, conversation_id, model, +2 more.

list_modelsB

List all available AI models with their descriptions and best use cases

Inputs: no named parameters.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have completely distinct purposes: consult_ai is for executing AI consultations, while list_models is for retrieving model information. There is no overlap in functionality, making it impossible for an agent to confuse them.

    Naming Consistency5/5

    Both tools follow a consistent verb_noun pattern (consult_ai, list_models) with clear, descriptive names. The naming convention is uniform and predictable across the set.

    Tool Count2/5

    With only two tools, the server feels under-scoped for an 'AI Consultant' domain. While the tools cover consultation and model listing, there are likely missing operations like managing consultation history, configuring model parameters, or handling feedback, making the set feel incomplete for the stated purpose.

    Completeness2/5

    For an AI consultant server, the tool surface is severely incomplete. It lacks essential operations such as saving or retrieving past consultations, adjusting consultation settings, or providing feedback on model performance. The current tools only cover the most basic consultation flow, leaving significant gaps that will hinder agent workflows.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides seamless access to 200+ AI models through OpenRouter's unified API, featuring multi-model collaboration, vision support, intelligent benchmarking, and collective intelligence capabilities for enhanced decision-making.
      1,013 npm
      10
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Provides access to 400+ AI models from OpenRouter, enabling users to chat with models like GPT-4, Claude, Gemini, and Llama, compare responses across multiple models, and retrieve model information with pricing details.
      4
      89 npm
      14
      MIT