czechmed_referral_assist
AI agents call czechmed_referral_assist to retrieve information from CzechMedMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The suffix 'assist' and 'referral' context indicate a read operation that retrieves or provides guidance on referral information without side effects. No evidence suggests modification, deletion, or execution of external operations. Confidence is moderate (0.6) due to empty description; if it performs write operations or executes external referral systems, classification should be re-evaluated.
From the tool's definition Tool name 'czechmed_referral_assist' suggests querying or assisting with referral information from Czech healthcare databases. The tool description is empty, limiting direct evidence.
Attacks that exploit this kind of access
czechmed_referral_assist. It is categorised as a Read tool in the CzechMedMCP MCP Server, which means it retrieves data without modifying state.
Register the CzechMed MCP server in PolicyLayer and add a rule for czechmed_referral_assist: 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 CzechMedMCP. Nothing to install.
czechmed_referral_assist 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 czechmed_referral_assist 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 czechmed_referral_assist. 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.
czechmed_referral_assist is provided by the CzechMed MCP server (petrsovadina/czechmedmcp). 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 →