MCP Registry Server

Registers and retrieves MCP servers via semantic search for quick discovery and access.
  • javascript

0

GitHub Stars

javascript

Language

7 months ago

First Indexed

3 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": {
    "mcp-mirror-kbb99_mcp-registry-server": {
      "command": "node",
      "args": [
        "./path/to/build/mcp-registry-server/dist/index.js"
      ]
    }
  }
}

You can discover MCP servers with a semantic search-capable registry server. It helps you find available MCP endpoints quickly and connect your client to the right service without guessing URLs or commands.

How to use

Start the registry server locally and keep it running so your MCP client can query it. Use the MCP client tooling to perform a retrieval operation by supplying a query string that describes what you’re looking for. The client will return matching MCP server entries you can connect to.

How to install

Prerequisites you need before installing: Node.js and npm, and git. Install Node.js and npm from your operating system’s package manager or official website, then install git if it is not already present.

Clone the registry server repository, install dependencies, and build the project.

Installation steps

git clone https://github.com/KBB99/mcp-registry-server.git
cd mcp-registry-server
npm install
npm run build

Run and configure for Claude Desktop

Run the server to verify it works, then configure Claude Desktop to use it.

node ./dist/index.js

Claude Desktop configuration example

{
  "mcpServers": {
    "mcp_registry": {
      "command": "node",
      "args": [
        "./path/to/build/mcp-registry-server/dist/index.js"
      ]
    }
  }
}

Available tools

retrieve_mcps

Perform retrieval operations against the MCP registry. Inputs: query (string): The search query for retrieval.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational