Returns MyDisease.info build metadata: total disease document count, available annotation sources (MONDO, DOID, OMIM, DisGeNET, HPO, CTD), and their current release versions.
AI agents call metadata to retrieve information from Mcp Mydisease without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves static metadata about the MyDisease.info database, including document counts and version information. It has no side effects, makes no modifications, and poses minimal risk if misused.
From the tool's definition Returns MyDisease.info build metadata: total disease document count, available annotation sources... and their current release versions
Attacks that exploit this kind of access
Returns MyDisease.info build metadata: total disease document count, available annotation sources (MONDO, DOID, OMIM, DisGeNET, HPO, CTD), and their current release versions. It is categorised as a Read tool in the Mcp Mydisease MCP Server, which means it retrieves data without modifying state.
Register the Mcp Mydisease MCP server in PolicyLayer and add a rule for metadata: 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 Mcp Mydisease. Nothing to install.
metadata 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 metadata 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 metadata. 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.
metadata is provided by the Mcp Mydisease MCP server (https://gateway.pipeworx.io/mydisease/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 →