toolhive-catalog
ToolHive's registry catalog of MCP servers
claude mcp add --transport stdio stacklok-toolhive-catalog node server.js \ --env PORT="8080 (or desired port)"
How to use
ToolHive's ToolHive Catalog MCP server acts as a registry that exposes the catalog of ToolHive/MCP servers. It provides metadata about available servers, their endpoints, tools offered, and how to integrate them into ToolHive workflows. You can query the catalog to discover servers, inspect their capabilities, and understand the required authentication or transport settings. Use the exposed endpoints to fetch server.json entries, validate entries locally, and build or refresh your local registry cache. The catalog is intended to help AI assistants select appropriate tools (e.g., data querying, web content retrieval, code analysis) and understand how to communicate with each server through the MCP protocol.
How to install
Prerequisites:
- Node.js v18 or newer
- npm or yarn
- Git
Step 1: Clone the repository (or obtain the server files from the registry source)
- git clone https://github.com/your org/toolhive-catalog.git
- cd toolhive-catalog
Step 2: Install dependencies
- npm install
Step 3: Configure environment (optional)
- Create a .env file to override defaults, e.g. PORT=8080, API_KEY=your-key
Step 4: Run the server
- npm run start
- or node server.js
Step 5: Verify the server is running
Note: If you deploy in a container environment, ensure the port is mapped correctly and any required env vars (e.g., authentication tokens) are provided at runtime.
Additional notes
Tips and considerations:
- The catalog entries should follow the MCP server.json schema. Validate entries with the provided catalog validation tool (task catalog:validate).
- If you add or modify servers, rebuild the registry files (task catalog:build) before submitting an update.
- Ensure container-based servers expose standard transport types (stdio, sse, or streamable-http) and that remote servers use a supported transport (prefer streamable-http).
- Document any required environment variables in the server.json _meta block so users know what to configure at runtime.
- Regularly audit entries for accuracy (tools list, tier/status, and endpoints) to maintain catalog trust.
Related MCP Servers
mcp-language
mcp-language-server gives MCP enabled clients access semantic tools like get definition, references, rename, and diagnostics.
sandbox
A Model Context Protocol (MCP) server that enables LLMs to run ANY code safely in isolated Docker containers.
hop
Fast, elegant SSH connection manager with a TUI dashboard and MCP server
mcp-catalog -example
Go MCP server example for AI-agent workflows with tools, resources, and prompts.
mcp-kit
MCP (Model Context Protocol) Kit for Go - A Complete MCP solutions for ready to use
mcp4go
A comprehensive Go SDK for the Model Context Protocol (MCP) - simplifying AI application development by abstracting away protocol complexities.