AI agents call disease_links to retrieve information from Sniff Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to query or retrieve disease linkage information from the canine genomics atlas. It does not modify data (Write), execute arbitrary code (Execute), delete anything (Destructive), or involve financial transactions (Financial). The lack of description slightly reduces confidence, but the naming pattern and server context strongly indicate a lookup/retrieval function.
From the tool's definition Tool name 'disease_links' in a genomics/breed database context suggests retrieval of disease relationship data.
Attacks that exploit this kind of access
disease_links. It is categorised as a Read tool in the Sniff Mcp MCP Server, which means it retrieves data without modifying state.
Register the Sniff MCP server in PolicyLayer and add a rule for disease_links: 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 Sniff Mcp. Nothing to install.
disease_links 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 disease_links 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 disease_links. 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.
disease_links is provided by the Sniff MCP server (https://mcp.sniff.world/mcp/). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
disease_links is one line of Sniff's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →