probe
Validate candidate parameters and obtain a zero-cost quote without executing the capability.
This record as markdown: /tools/qverisai-qveris-agent-toolkit/probe.md
What probe does on Qverisai
AI agents call probe to retrieve information from Qverisai without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why probe is rated Low
This tool validates parameters and returns quote/pricing information without side effects or execution. It is a read operation analogous to a dry-run or preview. While the server provides access to financial capabilities, this specific tool does not move money, modify data, or trigger external operations—it only queries and returns informational responses.
From the tool's definition Tool is described as 'Validate candidate parameters and obtain a zero-cost quote without executing the capability.' The use of 'zero-cost quote' and 'without executing' indicates this is a non-destructive read operation that retrieves information about a…
Attacks that exploit this kind of access
The rule that runs probe safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Qverisai, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For probe, this is the rule to start with:
probe is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Qverisai, apply this rule, and every probe call is checked against it from then on.
Questions about probe
Validate candidate parameters and obtain a zero-cost quote without executing the capability. It is categorised as a Read tool in the Qverisai MCP Server, which means it retrieves data without modifying state.
Register the Qverisai MCP server in PolicyLayer and add a rule for probe: 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 Qverisai. Nothing to install.
probe 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 probe 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 probe. 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.
probe is provided by the Qverisai MCP server (qverisai/qveris-agent-toolkit). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Qverisai, and thousands of servers like it.
This server
Across the catalogue