AI agents call collect_security_evidence to retrieve information from ComplyOS without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool collects (reads/gathers) existing security and SOC2 evidence for auditor review. 'Readiness-only' implies no modifications are made — it is purely a data retrieval and packaging operation. Severity is medium because the collected evidence packet may contain sensitive security configuration details, audit trails, and compliance data that could be valuable to an adversary if exposed.
From the tool's definition Collect a readiness-only security/SOC2 evidence packet for auditor review
Attacks that exploit this kind of access
Collect a readiness-only security/SOC2 evidence packet for auditor review. It is categorised as a Read tool in the ComplyOS MCP Server, which means it retrieves data without modifying state.
Register the ComplyOS MCP server in PolicyLayer and add a rule for collect_security_evidence: 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 ComplyOS. Nothing to install.
collect_security_evidence is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the collect_security_evidence 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 collect_security_evidence. 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.
collect_security_evidence is provided by the ComplyOS MCP server (simongonzalezdc/complyos). 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 →