AI agents use submit_intake to create or update resources in ComplyOS — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ComplyOS environment.
The tool likely creates or registers a new intake record in the compliance system—a reversible write operation. Without explicit description, confidence is moderate. The empty description reduces certainty but does not suggest destructive or execute-class behavior given the compliance auditing context of the server.
From the tool's definition Tool name is 'submit_intake' with empty description. In compliance/auditing systems, 'submit' typically creates new records or requests; 'intake' suggests initial data capture or onboarding.
Attacks that exploit this kind of access
submit_intake. It is categorised as a Write tool in the ComplyOS MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ComplyOS MCP server in PolicyLayer and add a rule for submit_intake: 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.
submit_intake 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 submit_intake 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 submit_intake. 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.
submit_intake 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 →