contentrain_scan
Scans project source code to extract content strings, build dependency graphs, and summarize findings for content management.
Instructions
Scan project source code for content strings. Three modes: "graph" builds import/component graph for project intelligence, "candidates" extracts string literals with pre-filtering and pagination, "summary" provides quick overview stats. Read-only — no changes to disk or git. MCP finds strings deterministically; the agent decides what is content. Recommended workflow: start with "summary" or "graph" for orientation, then paginate through "candidates" to evaluate strings.
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": "contentrain_scan"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Scan mode. Default: candidates | |
| limit | No | Candidates mode: batch size. Default: 50 | |
| paths | No | Directories to scan (relative to project root). Default: auto-detect | |
| offset | No | Candidates mode: pagination offset. Default: 0 | |
| exclude | No | Additional directory names to exclude | |
| include | No | File extensions to include. Default: .tsx, .jsx, .vue, .ts, .js, .mjs, .astro, .svelte | |
| max_length | No | Candidates mode: maximum string length. Default: 500 | |
| min_length | No | Candidates mode: minimum string length. Default: 2 |