MCP Advisor

MIT License
46
  • Apple
  • Linux

Integrations

  • Provides access to MCP servers listed in the Model Context Protocol GitHub repository, allowing AI assistants to discover available services

  • Uses Mermaid for rendering architecture and data flow diagrams to visualize the MCP Advisor system architecture

  • Incorporates Shields.io badges in the README to display MCP status and links to MCP servers

MCP Advisor

MCP Advisor & Installation

Experience MCP Advisor

What is this?

MCP Advisor is a discovery & recommendation service that helps you explore Model Context Protocol servers. It acts as a smart guide that helps AI assistants find and understand available MCP services out there based on natural language queries, making it easier to discover and utilize the right tools for specific tasks.

Features

  • Smart Search: Find MCP services using natural language queries
  • Rich Metadata: Get detailed information about each service
  • Real-time Updates: Always up-to-date with the latest MCP services
  • Easy Integration: Simple to integrate with any MCP-compatible AI assistant
  • Vector Search: Powered by OceanBase for high-performance semantic search
  • Modular Architecture: Clean separation of concerns for maintainability and extensibility

Architecture

Data Flow

Quick Start

Usage

  1. Clone the repository

or

  1. Use npx

Installation

For Claude Desktop, edit your claude_desktop_config.json file:

MacOS/Linux
code ~/Library/Application\ Support/Claude/claude_desktop_config.json
Windows
code $env:AppData\Claude\claude_desktop_config.json

Transport Options

MCP Advisor supports two transport methods:

1. Stdio Transport (Default)

Use this for command-line tools and direct integrations.

Add to your AI assistant's MCP configuration to enable service discovery capabilities:

{ "mcpServers": { "mcp-advisor": { "command": "npx", "args": [ "-y", "/path/to/repo/build/index.js" ] } } }
2. SSE Transport (HTTP Server)

Use this for remote servers or web-based integrations. Start the server with:

# Start with SSE transport on port 3000 TRANSPORT_TYPE=sse SERVER_PORT=3000 ENABLE_FILE_LOGGING=true node build/index.js

Environment variables for SSE configuration:

  • TRANSPORT_TYPE: Set to sse to use SSE transport (default is stdio)
  • SERVER_PORT: HTTP server port (default: 3000)
  • SERVER_HOST: HTTP server host (default: localhost)
  • SSE_PATH: SSE endpoint path (default: /sse)
  • MESSAGE_PATH: Messages endpoint path (default: /messages)

Connect to the server using:

  • SSE endpoint: http://localhost:3000/sse
  • Messages endpoint: http://localhost:3000/messages?sessionId=<SESSION_ID>
  • Health check: http://localhost:3000/health
3. REST Transport
TRANSPORT_TYPE=rest SERVER_PORT=3000 ENABLE_FILE_LOGGING=true node build/index.js

Examples

Example Queries

Here are some example queries you can use with MCP Advisor:

"Find an MCP server for natural language processing" "MCP server for financial data analysis" "Recommendation engine MCP server for e-commerce" "MCP server with image recognition capabilities" "Weather data processing MCP server" "Document summarization MCP server"

Example Response

[ { "title": "NLP Toolkit", "description": "Comprehensive natural language processing toolkit with sentiment analysis, entity recognition, and text summarization capabilities.", "github_url": "https://github.com/example/nlp-toolkit", "similarity": 0.92 }, { "title": "Text Processor", "description": "Efficient text processing MCP server with multilingual support.", "github_url": "https://github.com/example/text-processor", "similarity": 0.85 } ]

Troubleshooting

Common Issues

  1. Connection Refused
    • Ensure the server is running on the specified port
    • Check firewall settings
    • Verify the host address is correct
  2. No Results Returned
    • Try a more general query
    • Check network connectivity to the registry API
    • Verify API endpoints are correctly configured
  3. SSE Connection Drops
    • Increase client timeout settings
    • Check server logs for error messages
    • Ensure proper CORS configuration if connecting from a browser
  4. Performance Issues
    • Consider adding more specific search terms
    • Check server resources (CPU/memory)
    • Implement caching if making frequent similar queries

Logs

For detailed troubleshooting, check the logs in the logs directory. Enable debug logging with:

DEBUG=true node build/index.js

Environment Variables

MCP Advisor can be configured using the following environment variables:

VariableDescriptionDefaultRequired
TRANSPORT_TYPETransport method (stdio, sse, rest)stdioNo
SERVER_PORTHTTP server port for SSE/REST transport3000No
SERVER_HOSTHTTP server host for SSE/REST transportlocalhostNo
SSE_PATHSSE endpoint path/sseNo
MESSAGE_PATHMessages endpoint path/messagesNo
ENDPOINTREST endpoint path/restNo
DEBUGEnable debug loggingfalseNo
ENABLE_FILE_LOGGINGEnable logging to filesfalseNo
LOG_LEVELLog level (debug, info, warn, error)infoNo

API Documentation

REST API Endpoints

GET /health

Health check endpoint.

Response:

{ "status": "ok", "version": "1.0.0" }
GET /sse

Server-Sent Events endpoint for establishing a connection.

Query Parameters:

  • None

Response:

  • Establishes an SSE connection
POST /messages

Endpoint for sending messages to an established SSE connection.

Query Parameters:

  • sessionId (string, required): The session ID of the SSE connection

Request Body:

{ "jsonrpc": "2.0", "method": "callTool", "params": { "name": "recommend-mcp-servers", "arguments": { "query": "financial data analysis" } }, "id": "1" }

Response:

{ "jsonrpc": "2.0", "result": { "content": [ { "title": "Financial Analytics MCP", "description": "Comprehensive financial data analysis toolkit", "github_url": "https://github.com/example/financial-mcp", "similarity": 0.95 } ] }, "id": "1" }
POST /rest

REST API endpoint for direct requests (when using REST transport).

Request Body:

{ "jsonrpc": "2.0", "method": "callTool", "params": { "name": "recommend-mcp-servers", "arguments": { "query": "financial data analysis" } }, "id": "1" }

Response: Same as /messages endpoint.

Test

with inspector

npx @modelcontextprotocol/inspector

License

MIT License - See LICENSE file for details.

You must be authenticated.

A
security – no known vulnerabilities
A
license - permissive license
A
quality - confirmed to work

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

A discovery and recommendation service that helps AI assistants find Model Context Protocol servers based on natural language queries.

  1. MCP Advisor & Installation
    1. Experience MCP Advisor
  2. What is this?
    1. Features
      1. Architecture
        1. Data Flow
      2. Quick Start
        1. Usage
        2. Installation
        3. Transport Options
      3. Examples
        1. Example Queries
        2. Example Response
      4. Troubleshooting
        1. Common Issues
        2. Logs
      5. Environment Variables
        1. API Documentation
          1. REST API Endpoints
        2. Test
          1. License

            Related MCP Servers

            • A
              security
              A
              license
              A
              quality
              An enhanced Model Context Protocol server that enables AI assistants to interact with ClickUp workspaces, supporting task relationships, comments, checklists, and workspace management through natural language.
              Last updated -
              40
              203
              TypeScript
              MIT License
            • -
              security
              A
              license
              -
              quality
              A Model Context Protocol server enabling AI agents to access and manipulate ServiceNow data through natural language interactions, allowing users to search for records, update them, and manage scripts.
              Last updated -
              9
              Python
              MIT License
            • -
              security
              A
              license
              -
              quality
              A Model Context Protocol server that enables AI agents to query Erick Wendel's talks, blog posts, and videos across different platforms using natural language.
              Last updated -
              55
              TypeScript
              MIT License
            • -
              security
              F
              license
              -
              quality
              A Model Context Protocol server that enables AI assistants to interact with Coolify instances through natural language, allowing management of servers, applications, databases, and deployments.
              Last updated -
              85
              2
              TypeScript

            View all related MCP servers

            ID: lzlc6tbjx6