Learn MCP

Build an MCP server in minutes.

You don't need to learn the protocol to ship one. If you have an OpenAPI spec or a GraphQL endpoint, you have 90% of an MCP server — here's the practical path for the last 10%.

01
Import

Paste an OpenAPI spec or GraphQL endpoint

02
Curate

Pick the tools AI should see, tune descriptions

03
Secure

Choose auth: OAuth, API keys, or signed JWTs

04
Publish

Live on our gateway or your own domain

Step 1 — Import what you already have

Paste an OpenAPI spec, point at a GraphQL endpoint, or pick a managed connector. CMD+K parses it and drafts one tool per operation — names, typed inputs, descriptions — in about a minute. This is the moment most teams expect to take a sprint.

new-mcp-server
$ cmdk mcp create --spec openapi.yaml
Parsing spec… 27 endpoints found. Generating tools:
orders.search
orders.refund
customers.lookup
invoices.create
Live at mcp.yourdomain.com OAuth 2.1 · per-user identity

Step 2 — Curate ruthlessly

Don’t expose all 27 endpoints. Models pick tools by reading descriptions, and a focused set of 10–15 well-described tools outperforms a full API dump every time. Rewrite descriptions in plain language (“Search a customer’s orders by email or order id”), mark risky operations, and leave destructive endpoints out until you have confirm-flows in place.

Step 3 — Decide who calls are made as

This is the step that separates production from prototype. Options, in increasing strictness: a shared API key (fine for internal read-only data), per-user API keys, or full OAuth where each end user connects their own account and every tool call runs with that identity — attributed, rate-limited, revocable. CMD+K hosts the OAuth 2.1 gateway and consent screens, so “strict” stops meaning “slow.”

Step 4 — Publish, connect, watch the logs

Publishing gives you a live MCP endpoint on our gateway or your own domain, plus a hosted connect page your customers use from Claude and any MCP-speaking client. From day one you get per-tool analytics and per-user logs — which tools get used, by whom, and what failed. That feedback loop is where good MCP servers get great.

Prefer to hand-roll it?

Fair. The official MCP SDKs are solid, and for a weekend project they’re all you need. What you’re signing up to operate is everything around the protocol: token storage, per-user OAuth flows, rate limits, retries, logs, uptime. That’s the layer teams like Mapgrid (illustrative scenario) chose not to own — and why the wizard exists. Try it on the free trial; your spec will tell you in ten minutes whether this is your path.

Ship the layer between
your product and AI.

Every workspace starts with a 14-day free trial — widget, knowledge base and MCP included. No credit card. Upgrade only when you need scale.

No credit card · 14-day free trial · Questions? Book 1:1 with the founder