Smithery is the registry and hosted runtime for Model Context Protocol servers — discover, install and run MCP servers for Claude, Cursor, Windsurf and more.
Smithery is the registry and hosted runtime for Model Context Protocol servers — discover, install and run MCP servers for Claude, Cursor, Windsurf and more.
Smithery is the npm-style registry for Model Context Protocol servers. With thousands of MCP servers now published — for GitHub, Postgres, Stripe, Slack, Brave Search, filesystem access, browser automation and every conceivable SaaS — the bottleneck moved from 'are there MCP servers?' to 'how do I find, configure and host them?'. Smithery solves that.
The web catalog lets you search by capability, see install counts and reviews, and copy a one-line install command tailored to Claude Desktop, Cursor, Windsurf, Cline, OpenClaw, VS Code or any other MCP client. Configuration forms are generated from each server's JSON schema, so the catalog page asks you for exactly the right credentials and options — no more reading READMEs to figure out which env vars you need.
The hosted runtime spins up streamable HTTP MCP servers for you so you do not have to manage local processes. This matters for three reasons: cloud agents can reach MCP without anyone installing anything, remote teammates share the same configured server, and Claude.ai (browser, not desktop) can connect to tools. The runtime handles auth, sandboxing and basic observability so you can see which tool calls are made.
For server authors, Smithery is the distribution channel. Publish your TypeScript or Python MCP server, get install analytics, accept payments through the marketplace, and reach every MCP client without separate integrations. That is real distribution leverage — there is no comparable surface for shipping agent tools right now.
Pricing: Free covers browsing, installing servers and basic hosted runtime usage. Pro/Team is usage-based with higher hosted limits, private servers, team management and analytics. Server authors monetise through the marketplace and can charge per call, per seat, or subscription.
Real pros: install commands genuinely work first-try, the schema-driven configuration UI prevents the most common MCP setup errors, and the hosted runtime removes a real ops burden. Real cons: hosted runtime cold starts on niche servers, some servers in the long tail are unmaintained, and the monetization story for free open-source authors is still evolving.
If you are working with MCP, also look at the official Anthropic MCP docs and registry, the Anthropic Console workbench for testing, and the clients that consume MCP: Claude, Cursor Agent and Windsurf. My recommendation: every team building with MCP should at least browse Smithery for known servers before writing one from scratch; hosted runtime is worth it the day you have more than two MCP servers in production.
Was this helpful?
Smithery has effectively become the discovery and distribution layer of the MCP ecosystem — if you build with MCP, you almost certainly route through it.
Searchable catalog of MCP servers with install counts, reviews and per-client install commands.
Streamable HTTP MCP servers run for you — no local processes, supports cloud agents and Claude.ai.
Configuration forms generated from each server's JSON schema so credentials and options are explicit.
Publish a server once and reach every MCP client; analytics show real install and call volume.
Per-call, per-seat or subscription pricing for paid MCP servers.
$0
Usage-based
Revenue share
Ready to get started with Smithery?
View Pricing Options →We believe in transparent reviews. Here's what Smithery doesn't handle well:
Weekly insights on the latest AI tools, features, and trends delivered to your inbox.
Integrations
Open protocol that automates AI model connections to external data sources, tools, and services through a standardized interface.
Coding Agents
Anthropic Console is the official developer platform for managing Claude AI API access, monitoring usage, generating API keys, and building AI-powered applications with comprehensive project management and team collaboration tools.
AI Chatbots and Assistants
Claude is Anthropic’s general AI assistant, but its best fit is more specific: careful work with language, code, and long context. Many teams choose Claude when they need a model that can read a large document, preserve nuance, write in a r
Coding Agents
AI-first code editor with autonomous coding capabilities. Understands your codebase and writes code collaboratively with you.
AI Coding
Agentic AI IDE — originally from Codeium, now owned by Cognition and rebranding to Devin Desktop. The Cascade agent does deep-context, multi-file edits with inline diffs.
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 →MCP went from interesting spec to production infrastructure in early 2026. With 10,000+ servers, enterprise vendors going GA, and a roadmap focused on discovery and multi-agent workflows, here's the practical builder's guide to what changed and what to do about it.
AI agents without memory restart from zero every conversation, wasting time and money. Here's how the three types of agent memory work, why they matter for your business, and which tools actually deliver results in 2026.
Deploy AI agents to production with confidence. Covers containerization, cloud deployment on AWS/Azure/GCP, Kubernetes orchestration, observability, cost control, and security best practices.
Running an online store means juggling product listings, customer questions, inventory, pricing, and marketing — all at once. AI agents can now handle most of it for you. Here's exactly how to automate your e-commerce business without hiring a team.