Run all anomaly detectors across one service (or the whole fleet) and return anomalies sorted by severity.
AI agents call find_anomalies to retrieve information from LogSentry MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries log data to identify anomalies and returns findings. It has no side effects on the monitored services or data—it does not create, modify, delete, or execute external operations. While it may trigger internal anomaly detection algorithms, these are deterministic analysis functions on existing data, not arbitrary code execution.
From the tool's definition Tool performs anomaly detection analysis and returns results; described as 'Run all anomaly detectors' and 'return anomalies sorted by severity' — a read-only analytical operation that retrieves and analyzes existing log data without modifying, deleting, or…
Attacks that exploit this kind of access
Run all anomaly detectors across one service (or the whole fleet) and return anomalies sorted by severity. It is categorised as a Read tool in the LogSentry MCP MCP Server, which means it retrieves data without modifying state.
Register the LogSentry MCP server in PolicyLayer and add a rule for find_anomalies: 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 LogSentry MCP. Nothing to install.
find_anomalies 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 find_anomalies 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 find_anomalies. 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.
find_anomalies is provided by the LogSentry MCP server (mehtaniravm/logsentrymcpgooglehangout). 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 →