AI agents call ism_coverage_gaps 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 name and surrounding context (IRAP review, coverage tracking, query layer) strongly suggest this queries or retrieves coverage gap information rather than modifying or executing operations. Sibling tools 'ism_coverage_read' and 'ism_coverage_upsert' show a pattern where read operations are separated from write operations; this tool's name suggests retrieval.
From the tool's definition Tool name 'ism_coverage_gaps' combined with server context showing 'coverage tracking for IRAP review' and sibling tools like 'ism_coverage_read' and 'ism_list_*' indicate this retrieves or queries gap data.
Attacks that exploit this kind of access
ism_coverage_gaps. 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_coverage_gaps: 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_coverage_gaps 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_coverage_gaps 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_coverage_gaps. 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_coverage_gaps 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 →