scan_script
Analyze the active script: extracts character/environment/object assets and splits narration into voice blocks. DESTRUCTIVE on re-run (assets are recreated, not merged — curated descriptions, reference images, and voices are lost; prefer rescan_voice_blocks after script edits). Async — returns {j...
This record as markdown: /tools/com-framesail-framesail/scan-script.md
What scan_script does on Framesail
AI agents call scan_script to permanently remove resources in Framesail, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | — | Model ID to scan with; empty uses the default (see list_models("script_scan")) |
project_id | string | Yes | Project ID, as returned by create_project or list_projects |
editable_sections | object | — | Per-call prompt section overrides, keyed by section name; see get_section_template("script_scan") |
Parameters from the server's own tool schema.
Why scan_script is rated Critical
The tool explicitly warns it is DESTRUCTIVE when re-run, causing irreversible loss of curated descriptions, reference images, and voice configurations. Data is overwritten rather than merged, making the action non-reversible for previously curated assets.
From the tool's definition DESTRUCTIVE on re-run (assets are recreated, not merged — curated descriptions, reference images, and voices are lost)
Attacks that exploit this kind of access
The rule that runs scan_script safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Framesail, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For scan_script, this is the rule to start with:
scan_script is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Framesail, apply this rule, and every scan_script call is checked against it from then on.
Questions about scan_script
Analyze the active script: extracts character/environment/object assets and splits narration into voice blocks. DESTRUCTIVE on re-run (assets are recreated, not merged — curated descriptions, reference images, and voices are lost; prefer rescan_voice_blocks after script edits). Async — returns {job_id}. It is categorised as a Destructive tool in the Framesail MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
scan_script accepts 3 parameters: model, project_id, editable_sections. Required: project_id. The full parameter table on this page comes from the server's own tool schema.
Register the Framesail MCP server in PolicyLayer and add a rule for scan_script: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Framesail. Nothing to install.
scan_script is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the scan_script rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for scan_script. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
scan_script is provided by the Framesail MCP server (https://api.framesail.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Framesail, and thousands of servers like it.
Across the catalogue