AI agents call ism_list_by_classification 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.
The tool retrieves/queries ISM control data indexed by classification. No side effects, modification, execution, or deletion are implied. The 'list' prefix and context of an information security manual query service indicate a retrieval operation. Empty description lowers confidence slightly but the naming pattern and server architecture strongly suggest read-only behavior.
From the tool's definition Tool name 'ism_list_by_classification' follows a read-only pattern ('list_*') consistent with sibling tools like 'ism_list_by_topic'. The server is described as a 'query layer' with no mention of modification capabilities for this tool.
Attacks that exploit this kind of access
ism_list_by_classification. 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_classification: 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_classification 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_classification 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_classification. 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_classification 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 →