slice_openapi
Index or extract matching operations and their schemas from large OpenAPI documents so agents can inspect only needed API details and save tokens.
Instructions
Read a large OpenAPI document cheaply: with no filters you get an index of operations; with filters you get only the matching operations and the schemas they use.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "slice_openapi"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | File to read, inside the server's root folder. Preferred way to pass input. | |
| tags | No | Only operations with one of these tags. | |
| text | No | The text itself. Only for small inputs: large text costs tokens to send. | |
| index | No | List operations only, no details. | |
| paths | No | Path patterns such as /repos/*/issues*. | |
| command | No | A command to run and trim (no shell). Only works if started with --allow-run. | |
| methods | No | Only these HTTP methods. | |
| operation_ids | No | Only these operation ids. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |