by toolsdk-ai
MCPSDK.dev(ToolSDK.ai)'s Awesome MCP Servers and Packages Registry and Database with Structured JSON configurations. Supports OAuth2.1, DCR...
# Add to your Claude Code skills
git clone https://github.com/toolsdk-ai/toolsdk-mcp-registryThe Enterprise MCP Registry & Gateway. A unified infrastructure to discover, secure, and execute Model Context Protocol (MCP) tools. Exposes local processes (STDIO) and remote servers (StreamableHTTP) via a unified HTTP API with built-in Sandbox and OAuth 2.1 support.
š Browse 4547+ Tools Ā Ā ā¢Ā Ā š³ Self-hosted Ā Ā ā¢Ā Ā š¦ Use as SDK Ā Ā ā¢Ā Ā ā Add Server Ā Ā ā¢Ā Ā š„ Video Tutorial
[!IMPORTANT] Pro Tip: If a server is marked as
validated: true, you can use it instantly with Vercel AI SDK:const tool = await toolSDK.package('<packageName>', { ...env }).getAISDKTool('<toolKey>');Want validation? Ask AI: "Analyze the
make buildtarget in the Makefile and the scripts it invokes, and determine how an MCP server gets marked asvalidated: true."
Deploy your own private MCP Gateway & Registry in minutes. This provides the full feature set: Federated Search, Remote Execution, Sandbox, and OAuth.
No comments yet. Be the first to share your thoughts!
Start the registry immediately with default settings:
docker compose up -d
Did this save you time? Give us a Star on GitHub ā it helps others discover this registry!
Configuration:
MCP_SANDBOX_PROVIDER=LOCAL in .env file if you want to disable the sandbox (not recommended for production).[!TIP] Tip for Private Deployment: This registry contains 4547+ public MCP servers. If you only need a specific subset for your private environment, you can prune the
packages/directory. š See Package Management Guide for details.
That's it! Your self-hosted MCP registry is now running with:
Execute any MCP tool via HTTP API - perfect for AI automation, chatbot integrations, and serverless deployments:
curl -X POST http://localhost:3003/api/v1/packages/run \
-H "Content-Type: application/json" \
-d '{
"packageName": "@modelcontextprotocol/server-everything",
"toolKey": "echo",
"inputData": {
"message": "Hello from ToolSDK MCP Registry!"
},
"envs": {}
}'
The registry also acts as an MCP Gateway ā any registered package can be accessed as a standard Streamable HTTP endpoint, even if the original server is STDIO-only.
Endpoint: POST /mcp/<packageName>
Pass environment variables via x-mcp-env-* headers:
curl -X POST http://localhost:3003/mcp/@modelcontextprotocol/server-github \
-H "Content-Type: application/json" \
-H "x-mcp-env-GITHUB_PERSONAL_ACCESS_TOKEN: ghp_your_token" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
The server returns a mcp-session-id header ā include it in subsequent requests to reuse the session (sessions expire after 30 min).
This is useful for:
If you only need to access the list of MCP servers programmatically (without execution or gateway features), you can use the NPM package.
npm install @toolsdk.ai/registry
Perfect for building your own directory or analysis tools:
import mcpServerLists from '@toolsdk.ai/registry/indexes/packages-list.json';
Fetch the complete MCP server registry programmatically:
curl https://toolsdk-ai.github.io/toolsdk-mcp-registry/indexes/packages-list.json
// JavaScript/TypeScript - Fetch API
const mcpServers = await (
await fetch('https://toolsdk-ai.github.io/toolsdk-mcp-registry/indexes/packages-list.json')
).json();
// Use for AI agent tool discovery, LLM integrations, etc.
console.log(mcpServers);
# Python - For AI/ML projects
import requests
mcp_servers = requests.get(
'https://toolsdk-ai.github.io/toolsdk-mcp-registry/indexes/packages-list.json'
).json()
# Perfect for LangChain, CrewAI, AutoGen integrations
ToolSDK MCP Registry is an enterprise-grade gateway for Model Context Protocol (MCP) servers. It solves the challenge of securely discovering and executing AI tools in production environments.
@modelcontextprotocol/registry.graph TD
subgraph ClientSide ["Client Side"]
LLM["š¤ AI Agent / LLM"]
User["š¤ User / Developer"]
end
subgraph DockerEnv ["š³ Self-Hosted Infrastructure"]
subgraph RegistryCore ["Registry Core"]
API["š Registry API"]
Search["š Meilisearch"]
DB["š Registry Data"]
OAuth["š OAuth Proxy"]
end
subgraph RuntimeEnv ["Runtime Environment"]
Local["š» Local Exec"]
Sandbox["š”ļø Secure Sandbox"]
MCPServer["āļø MCP Server"]
end
end
User -->|Search Tools| API
LLM -->|Execute Tool| API
LLM -->|Auth Flow| OAuth
API <-->|Query Index| Search
API -->|Read Metadata| DB
API -->|Run Tool| Local
API -->|Run Tool| Sandbox
Local -->|Execute| MCPServer
Sandbox -->|Execute| MCPServer
This open-source project provides:
Some packages in this registry are marked as validated: true.
[!NOTE] What does
validated: truemean for you?
- You can load the MCP package directly via our ToolSDK NPM client and get ready-to-use tool adapters (e.g. Vercel AI SDK tools) without writing your own tool schema mapping.
- The registry index includes the discovered
toolsmetadata for validated packages, so you can pick atoolKeyand call it immediately.Where is this flag stored?
- See
indexes/packages-list.jsonentries (e.g. `{"validated": t