AI agents call sentrul_trace_lookup to retrieve information from Sentrul without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing trace data by identifier with no side effects. It is a read-only query operation. The emphasis on 'public' and the specific retrieval mechanism (by ID) further indicate this is a data retrieval function with no ability to modify, delete, or execute operations. Severity is low as the blast radius of misuse is limited to unauthorized information disclosure of already-public trace data.
From the tool's definition Tool name contains 'lookup' and description states 'Retrieve a public Langfuse trace by ID' — purely a retrieval operation with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Retrieve a public Langfuse trace by ID. It is categorised as a Read tool in the Sentrul MCP Server, which means it retrieves data without modifying state.
Register the Sentrul MCP server in PolicyLayer and add a rule for sentrul_trace_lookup: 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 Sentrul. Nothing to install.
sentrul_trace_lookup 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 sentrul_trace_lookup 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 sentrul_trace_lookup. 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.
sentrul_trace_lookup is provided by the Sentrul MCP server (sentrul/sentrul-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 →