Health check — return the MISP server version and capability flags.
AI agents call misp_version to retrieve information from UltraProbe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that queries server information for diagnostic purposes. It has no side effects, does not modify data, and poses minimal risk to the system. The tool simply returns version and capability information, making it a benign Read operation.
From the tool's definition Tool performs a 'Health check — return the MISP server version and capability flags.' This retrieves metadata about the server without modifying, deleting, or executing operations on data.
Attacks that exploit this kind of access
Health check — return the MISP server version and capability flags. It is categorised as a Read tool in the UltraProbe MCP Server, which means it retrieves data without modifying state.
Register the UltraProbe MCP server in PolicyLayer and add a rule for misp_version: 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 UltraProbe. Nothing to install.
misp_version 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 misp_version 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 misp_version. 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.
misp_version is provided by the UltraProbe MCP server (ppcvote/misp-mcp-server). 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 →