query_production
AI agents call query_production to retrieve information from Petropt/petro without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name and server context strongly suggest data retrieval without modification. However, production data in petroleum engineering can be sensitive or commercially valuable, warranting medium severity if exposed to unauthorized agents. Confidence is 0.75 because the description is empty, preventing full verification of potential side effects.
From the tool's definition Tool named 'query_production' with prefix 'query' typically retrieves data. Server description indicates 'query production data' as a capability.
Attacks that exploit this kind of access
query_production. It is categorised as a Read tool in the Petropt/petro MCP Server, which means it retrieves data without modifying state.
Register the Petropt/petro MCP server in PolicyLayer and add a rule for query_production: 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 Petropt/petro. Nothing to install.
query_production 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 query_production 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 query_production. 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.
query_production is provided by the Petropt/petro MCP server (petropt/petro-mcp). 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 →