Answers & Guidance

Frequently Asked Questions

Everything you need to know about importing specs, generating MCP servers, and connecting them to your AI clients.

What is MCP Studio?

MCP Studio turns an OpenAPI or Swagger specification into a runnable Model Context Protocol server. Upload a JSON spec and it parses every endpoint, validates schemas, and generates server code your AI agents can call as tools.

What is the Model Context Protocol?

MCP is an open protocol from Anthropic that standardizes how AI applications expose tools, data, and context to models. Generated servers implement protocol revision 2024-11-05 and work with any MCP-compatible client.

Which OpenAPI versions are supported?

OpenAPI 3.0, 3.1, and Swagger 2.0 in JSON format. Only .json files are accepted.

Which programming languages can I generate?

Servers can be generated in TypeScript, Python, Java, and PHP. Pick a runtime and target API base URL before generating.

Do I need to write any code?

No. Upload the spec, choose a language, and download the bundle. You only need the matching runtime installed to execute the generated server.

How do I connect a generated server to Claude Desktop or Cursor?

Each bundle includes a ready-to-paste config snippet. Add the server command to your Claude Desktop config or Cursor MCP settings, then restart the client so it discovers the new tools.

Are my credentials or secrets included in the output?

No. Base URLs and secrets are supplied through environment variables, so nothing sensitive is hard-coded into the generated server.

Where are my specifications stored?

Specifications are stored in your local database and addressed by UUID. You can revisit them any time from the API Specs library.

Can I re-download a server later?

Yes. The Generated Servers catalog tracks every build, so you can re-download or regenerate without uploading the spec again.

What are the requirements to run a generated server?

The runtime for your chosen language (Node.js, Python, a Java JDK, or PHP) plus network access to the target API base URL.

Why did my upload fail?

The most common causes are invalid JSON, a missing top-level paths object, or an unsupported file type. Correct the spec and upload it again.

Is there a file size limit?

Uploads are bounded by your server's PHP upload_max_filesize and post_max_size settings.

Still have questions?

Read the official Model Context Protocol documentation or start generating with your own specification.