JSON Schema to MCP Schema
Convert a JSON Schema into an MCP tool definition.
About this tool
Paste a JSON Schema and get an MCP tool definition around it: a name, a description and the schema as inputSchema. Add a description in the second box, or the tool uses a default. The tool name is always tool, so rename it afterwards.
How to use
How it works
If your schema has a type, it is used unchanged as inputSchema. If it is just a map of properties without a type, it is wrapped as {"type":"object","properties":...,"additionalProperties":true}. The output is plain JSON you can drop into your server's tool list.
Worked example
A city lookup
- Input
- {"type":"object","properties":{"city":{"type":"string"}},"required":["city"]}
- Output
- { "name": "tool", "description": "Generated from JSON Schema", "inputSchema": { "type": "object", "properties": { "city": { "type": "string" } }, "required": [ "city" ] } }
- Walkthrough
- The schema is copied under inputSchema. Rename name from tool, and replace the default description with one that tells the model when to call it.
Limitations
- The name is always tool in the web tool.
- The schema is not validated or simplified, so unsupported keywords are passed through.
- A typed schema that is not an object is still used as is, which MCP will reject.
Questions
How do I convert a JSON Schema to an MCP tool?
Can I set the tool name?
What if my schema has no type?
Is anything sent to a server?
Features
- MCP-ready JSON
- Optional description
- Local only
Related resources
Guides and videos from around the web—opens on YouTube or the publisher’s site.
Machine Learning for Everybody
freeCodeCamp.org
Accessible ML survey for AI calculator and metric tools.
Watch on YouTubeTensorFlow 2.0 Complete Course
freeCodeCamp.org
Practical ML stack context next to AI utilities.
Watch on YouTube
- DeepLearning.AI
DeepLearning.AI
Courses and explainers for modern AI tooling.
- Data Index
Math is Fun
Stats primers when reading ML evaluation outputs.