List metadata about the OpenCRAVAT annotators that will be run.
AI agents call list_annotators to retrieve information from OpenCRAVAT without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists metadata about annotators—a read-only query operation with no side effects. It does not execute annotations, modify data, or trigger external operations. The blast radius if misused is minimal; an attacker could only enumerate available annotators, not alter them or access sensitive variant data.
From the tool's definition Tool name 'list_annotators' and description 'List metadata about the OpenCRAVAT annotators' indicates retrieval of information about available annotators with no modification, creation, execution, or deletion of data.
Documented attack patterns abuse exactly the kind of access list_annotators gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OpenCRAVAT, and nothing reaches the server without passing your rules. This is the rule we recommend for list_annotators:
{
"version": "1",
"default": "deny",
"tools": {
"list_annotators": {}
}
}list_annotators is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List metadata about the OpenCRAVAT annotators that will be run. It is categorised as a Read tool in the OpenCRAVAT MCP Server, which means it retrieves data without modifying state.
Register the OpenCRAVAT MCP server in PolicyLayer and add a rule for list_annotators: 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 OpenCRAVAT. Nothing to install.
list_annotators 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 list_annotators 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 list_annotators. 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.
list_annotators is provided by the OpenCRAVAT MCP server (karchinlab/oc-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OpenCRAVAT, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 OpenCRAVAT tools catalogued and risk-classified — across an index of 43,000+ MCP servers.