Returns full detail for multiple ISM controls in one call. Accepts OSCAL ids and/or human labels (e.g. GOV-01).
AI agents call get_controls to retrieve information from ISM MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
get_controls retrieves and queries control information from the ISM database without creating, modifying, deleting, or executing any operations. It is a straightforward data retrieval function analogous to a search or get operation. No evidence of reversible writes, irreversible deletions, code execution, or financial transactions.
From the tool's definition Tool returns full detail for ISM controls; described as retrieval operation with no side effects or modification capabilities.
Attacks that exploit this kind of access
Returns full detail for multiple ISM controls in one call. Accepts OSCAL ids and/or human labels (e.g. GOV-01). It is categorised as a Read tool in the ISM MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ISM MCP Server MCP server in PolicyLayer and add a rule for get_controls: 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 MCP Server. Nothing to install.
get_controls 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 get_controls 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 get_controls. 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.
get_controls is provided by the ISM MCP Server MCP server (rusticeagle/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 →