AI agents call list_connectors 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 name clearly indicates a read operation that retrieves or enumerates connector data. Given the context of a compliance auditing system, this would return information about available connectors (likely integrations with LMS or governance systems). No parameters or evidence suggests side effects, data modification, deletion, or external execution.
From the tool's definition Tool name 'list_connectors' indicates a listing/retrieval operation. No description provided, but the verb 'list' is a standard read operation that queries available connectors without modification.
Attacks that exploit this kind of access
list_connectors. 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 list_connectors: 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.
list_connectors 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 list_connectors 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 list_connectors. 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.
list_connectors 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 →