Clear extracted reactions for a document and parse it again.
AI agents call reparse_document to permanently remove resources in Scifinder Route — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool irreversibly clears (deletes) all extracted reactions associated with a document before re-parsing. The 'clear' operation destroys existing extracted data, which may not be recoverable depending on system design. This destructive deletion of reaction data, even if followed by re-parsing, constitutes an irreversible action on potentially significant scientific data.
From the tool's definition Clear extracted reactions for a document and parse it again
Attacks that exploit this kind of access
Clear extracted reactions for a document and parse it again. It is categorised as a Destructive tool in the Scifinder Route MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Scifinder Route MCP server in PolicyLayer and add a rule for reparse_document: 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 Scifinder Route. Nothing to install.
reparse_document 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 reparse_document 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 reparse_document. 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.
reparse_document is provided by the Scifinder Route MCP server (kettly1260/scifinder-route-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →