Scan text
scan_textScans inline content such as SKILL.md, MCP tool descriptions, or web-fetched configs for security risks without writing to disk; set kind to apply the relevant rules.
Instructions
Scans content passed inline, such as a SKILL.md, an MCP tool description or an MCP config fetched from the web, without writing it to disk. Set kind to say what the content is. Read-only and offline.
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": {
"content": "<content>"
},
"name": "scan_text"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | What the content is; selects the rules that apply. | skill |
| content | Yes | The text to scan. | |
| filename | No | Name shown in findings. Only its base name is used. | |
| max_findings | No | Largest number of findings to return, most severe first. | |
| min_severity | No | Leave out findings below this severity. | low |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| tool | Yes | ||
| counts | Yes | ||
| skipped | Yes | ||
| targets | Yes | ||
| version | Yes | ||
| complete | Yes | False when some files or folders were not scanned; a scan that is not complete is not a clean result. | |
| findings | Yes | ||
| filesScanned | Yes | ||
| skippedFiles | Yes | ||
| highestSeverity | Yes | ||
| omittedFindings | Yes |