AI agents call ism_list_by_topic to retrieve information from Ism without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries ISM control data filtered by topic, with no side effects. It is a straightforward read operation that matches the Read category (search, list, get, fetch). The severity is low because querying security control metadata poses minimal risk even if invoked by an untrusted agent—the data returned is informational only and does not alter system state or permissions.
From the tool's definition Tool name contains 'list', description states 'List controls' with no modification or deletion capabilities. Returns enumerated controls under a topic.
Attacks that exploit this kind of access
List controls under a specific topic (exact match, use ism_list_topics to enumerate). It is categorised as a Read tool in the Ism MCP Server, which means it retrieves data without modifying state.
Register the Ism MCP server in PolicyLayer and add a rule for ism_list_by_topic: 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 Ism. Nothing to install.
ism_list_by_topic 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 ism_list_by_topic 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 ism_list_by_topic. 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.
ism_list_by_topic is provided by the Ism MCP server (samueldudley/ism-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 →