AI agents call konsulto_get_finding to retrieve information from Konsulto without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool purely retrieves and queries data from the Konsulto audit platform without any side effects. The use of 'get' and explicit 'Read' language in the description clearly indicates a read-only data retrieval operation. Low severity due to minimal blast radius—an AI agent misusing this tool would only retrieve audit finding information that is already stored in the system.
From the tool's definition Tool name includes 'get' and description states 'Read a single finding by ID', with output being rendered markdown content. No modification, deletion, or execution of external operations occurs.
Attacks that exploit this kind of access
Read a single finding by ID, including its body rendered as markdown. It is categorised as a Read tool in the Konsulto MCP Server, which means it retrieves data without modifying state.
Register the Konsulto MCP server in PolicyLayer and add a rule for konsulto_get_finding: 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 Konsulto. Nothing to install.
konsulto_get_finding 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 konsulto_get_finding 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 konsulto_get_finding. 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.
konsulto_get_finding is provided by the Konsulto MCP server (konsulto/konsulto-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 →