Reduce supplied context and check caller-declared, source-specific exact evidence retention.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Select passages from explicitly supplied sanitized documents under an estimated token budget, and check whether user-declared exact evidence excerpts remain in selected passages from their specified source. No web access, storage, payments, semantic correctness guarantee, or downstream prompt capture. Do not send credentials, government IDs, payment card data, protected health information, or confidential personal records.
Confirm these are authorized, sanitized or synthetic task-specific excerpts, not restricted data.
Caller-declared exact excerpts required for this task. An empty list means completeness was not tested.
Select passages from explicitly supplied sanitized documents under an estimated token budget, and check whether user-declared exact evidence excerpts remain in selected passages from their specified source. No web access, storage, payments, semantic correctness guarantee, or downstream prompt capture. Do not send credentials, government IDs, payment card data, protected health information, or confidential personal records.
| Argument | Type | Description |
|---|---|---|
| task* | string | |
| documents* | array | |
| sanitized* | boolean | Confirm these are authorized, sanitized or synthetic task-specific excerpts, not restricted data. |
| tokenBudget* | integer | |
| expectedEvidence | array | Caller-declared exact excerpts required for this task. An empty list means completeness was not tested. |
{
"type": "object",
"required": [
"task",
"tokenBudget",
"documents",
"sanitized"
],
"properties": {
"task": {
"type": "string",
"maxLength": 1200,
"minLength": 8
},
"documents": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"text"
],
"properties": {
"id": {
"type": "string",
"pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]{0,79}$"
},
"text": {
"type": "string",
"maxLength": 60000,
"minLength": 1
},
"title": {
"type": "string",
"maxLength": 160
}
},
"additionalProperties": false
},
"maxItems": 8,
"minItems": 1
},
"sanitized": {
"type": "boolean",
"const": true,
"description": "Confirm these are authorized, sanitized or synthetic task-specific excerpts, not restricted data."
},
"tokenBudget": {
"type": "integer",
"maximum": 16000,
"minimum": 64
},
"expectedEvidence": {
"type": "array",
"items": {
"type": "object",
"required": [
"sourceId",
"excerpt"
],
"properties": {
"excerpt": {
"type": "string",
"maxLength": 2000,
"minLength": 1
},
"sourceId": {
"type": "string",
"maxLength": 80
}
},
"additionalProperties": false
},
"maxItems": 32,
"description": "Caller-declared exact excerpts required for this task. An empty list means completeness was not tested."
}
},
"additionalProperties": false
}