Registry and hosting platform for MCP (Model Context Protocol) servers, making it easy to discover, deploy, and connect tools to AI agents.
A directory and hosting platform for AI tool connectors — find and deploy integrations that let AI access external tools.
Smithery is a registry and hosting platform for Model Context Protocol (MCP) servers — the emerging standard for connecting AI agents to external tools and data sources. As MCP adoption grows across AI agent frameworks, Smithery solves the discovery and deployment problem by providing a centralized hub where developers can find, publish, and host MCP servers.
The platform features a searchable catalog of MCP servers covering categories like databases, APIs, development tools, file systems, communication platforms, and more. Each server listing includes documentation, usage instructions, configuration details, and community ratings. Developers can discover pre-built MCP servers instead of building tool integrations from scratch.
Smithery's hosted deployment option is particularly valuable — instead of self-hosting MCP servers, developers can deploy them to Smithery's infrastructure with one click and get a hosted endpoint ready for agent connection. This dramatically reduces the operational overhead of maintaining tool integrations for AI agents.
The platform supports multiple transport protocols including stdio and SSE (Server-Sent Events), with configuration templates for popular agent frameworks like Claude Desktop, Cursor, VS Code, and Windsurf. Smithery also provides an SDK for building and publishing custom MCP servers, with built-in authentication and rate limiting for hosted deployments.
As the MCP ecosystem grows — with Anthropic, OpenAI, Google, and others adopting the protocol — Smithery is positioned as the NPM/PyPI equivalent for agent tool integrations. It's becoming essential infrastructure for the AI agent development workflow.
Was this helpful?
Searchable catalog of MCP servers with documentation, ratings, and usage stats — discover pre-built tool integrations instead of building from scratch.
Use Case:
Deploy MCP servers to Smithery's infrastructure without managing your own hosting, getting instant endpoints for agent connection.
Use Case:
Configuration templates for Claude Desktop, Cursor, VS Code, Windsurf, and other MCP-compatible agent environments.
Use Case:
SDK and CLI for building, testing, and publishing custom MCP servers to the registry for community or private use.
Use Case:
Built-in auth and rate limiting for hosted MCP servers, ensuring secure and controlled access to tool integrations.
Use Case:
Supports stdio and SSE transports with automatic protocol negotiation for maximum compatibility across agent frameworks.
Use Case:
Free
month
Check website for pricing
Ready to get started with Smithery?
View Pricing Options →Discovering pre-built tool integrations for AI agents
Hosting MCP servers without infrastructure management
Publishing custom MCP servers for team or community use
Rapid agent prototyping with ready-to-use tools
We believe in transparent reviews. Here's what Smithery doesn't handle well:
Model Context Protocol (MCP) is a standard for connecting AI agents to tools and data sources. It replaces custom integrations with a universal protocol, similar to how USB standardized device connections.
Any framework that supports MCP can use Smithery servers. This includes Claude, Cursor, VS Code with Copilot, and frameworks with MCP client support like LangChain and Google ADK.
Smithery hosts pre-built servers so you don't have to build or maintain them. For custom needs, you can still build and publish your own through Smithery's SDK.
No. Smithery is an independent platform. MCP was created by Anthropic but is an open protocol that anyone can implement and build on.
Weekly insights on the latest AI tools, features, and trends delivered to your inbox.
People who use this tool also find these helpful
Anthropic's open protocol for connecting AI models to external tools and data sources securely.
Model Context Protocol server for secure file system operations and directory management.
Model Context Protocol server for GitHub integration with repository management and code analysis.
Model Context Protocol server for SQLite database operations and data analysis.
Sales intelligence platform with lead generation, email automation, and CRM integration.
Self-managing workflow orchestration platform that adapts and optimizes business processes automatically.
See how Smithery compares to Composio and other alternatives
View Full Comparison →AI Agent Builders
Composio is a tool integration platform that connects AI agents to 250+ external services including Gmail, Slack, Salesforce, GitHub, Jira, and dozens more. It handles authentication (OAuth, API keys), permission scoping, and provides ready-made function definitions that AI agents can call to take real-world actions. Rather than building custom API integrations for each service, developers use Composio's unified interface to give their agents the ability to send emails, create tickets, update CRMs, and perform other actions across the software stack.
Integrations
Anthropic's open protocol for connecting AI models to external tools and data sources securely.
Search & Discovery
Independent web index API for search and summarization.
No reviews yet. Be the first to share your experience!
Get started with Smithery and see if it's the right fit for your needs.
Get Started →Take our 60-second quiz to get personalized tool recommendations
Find Your Perfect AI Stack →Explore 20 ready-to-deploy AI agent templates for sales, support, dev, research, and operations.
Browse Agent Templates →