Query previously scraped disease information from local database.
AI agents call query_disease to retrieve information from Meducate MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing medical reference data from a local database. It performs a read-only query operation with no capability to modify, delete, or execute external actions. The scope is limited to fetching disease information for educational purposes.
From the tool's definition Tool name 'query_disease' and description 'Query previously scraped disease information from local database' indicate a retrieval operation with no data modification, deletion, or external side effects.
Attacks that exploit this kind of access
Query previously scraped disease information from local database. It is categorised as a Read tool in the Meducate MCP MCP Server, which means it retrieves data without modifying state.
Register the Meducate MCP server in PolicyLayer and add a rule for query_disease: 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 Meducate MCP. Nothing to install.
query_disease 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_disease 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_disease. 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_disease is provided by the Meducate MCP server (joshnuku/meducate-mcp-demo). 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 →