Find the AI infrastructure or tool action for a task
unfragile_findFinds the product, and the specific tool action, that does a task, across AI infrastructure (search APIs, models, inference, browsers, harnesses, compute) and the MCP servers, APIs, CLIs, SDKs and models in our index. Each result carries the label from our checks (verified and signed · official · checked: not enough evidence yet · found in code, not yet checked · demo or tutorial · failed its last check) and a signed receipt. answer: true adds a written, cited answer; false returns the ranked list. A fact we hold (a price, a limit, a model id) arrives in structuredContent.blocks (type 'fact') and at the start of the answer, never in results.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"task": "<task>"
},
"name": "unfragile_find"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | With search: 'product' (which product does X), 'action' (the one operation to call) or 'model' (which AI model) | |
| lane | No | fast: ranked results only · standard: results and a written, cited answer (default) · best: a freshly written answer | |
| task | Yes | What you need done, in plain words | |
| limit | No | How many results (default 5) | |
| named | No | With search: products the task names, so they lead | |
| answer | No | Also return a written answer: the products that do it, each cited to its maker's own pages. Default here: true (this door has always answered); false lists the products without writing | |
| intent | No | Deprecated: the old name of `kind` (kept so 0.10 callers work) | |
| search | No | Optional: your own 3-10 word search phrase; skips our reading step | |
| max_age | No | Seconds: a remembered answer older than this is written afresh | |
| session_id | No | Your own id for this task (recorded on the receipt) | |
| client_model | No | The model that will read the answer (recorded on the receipt) |