AI agents use record_finding to create or update resources in SIFTGuard — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SIFTGuard environment.
This tool writes/creates a new forensic finding record to a case file. It creates data persistently but is reversible in principle (records can be deleted or amended). It does not execute code, delete data, or involve financial transactions. The severity is medium because misrecording findings could mislead an incident response investigation, but the blast radius is limited to the case file contents.
From the tool's definition Record a validated forensic finding to the case file
Attacks that exploit this kind of access
Record a validated forensic finding to the case file. Requires: title, severity, evidence list, mitre_technique, confidence. It is categorised as a Write tool in the SIFTGuard MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SIFTGuard MCP server in PolicyLayer and add a rule for record_finding: 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 SIFTGuard. Nothing to install.
record_finding is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the record_finding 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 record_finding. 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.
record_finding is provided by the SIFTGuard MCP server (sodiq-code/siftguard). 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 →