AI agents call sampleLLM as a supporting operation in My workflows.
With no description available, the tool's behavior cannot be determined from the provided information. The name 'sampleLLM' suggests it may interact with a language model (possibly sampling/querying it), which would be a Read-like operation, but this is speculative. Given the uncertainty, confidence is very low and category defaults to Other.
From the tool's definition Tool name is 'sampleLLM' and description is empty or uninformative.
Attacks that exploit this kind of access
sampleLLM. It is categorised as a Other tool in the My MCP Server, which means it performs auxiliary operations.
Register the My MCP server in PolicyLayer and add a rule for sampleLLM: 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 My. Nothing to install.
sampleLLM is a Other tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the sampleLLM 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 sampleLLM. 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.
sampleLLM is provided by the My MCP server (kcbabo/everything-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 →