Free-text search across all annotations (domain, variable, description).
AI agents call search_annotations to retrieve information from CRF Annotation MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though search_annotations only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Free-text search across all annotations (domain, variable, description). It is categorised as a Read tool in the CRF Annotation MCP Server MCP Server, which means it retrieves data without modifying state.
Register the CRF Annotation MCP Server MCP server in PolicyLayer and add a rule for search_annotations: 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 CRF Annotation MCP Server. Nothing to install.
search_annotations 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 search_annotations 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 search_annotations. 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.
search_annotations is provided by the CRF Annotation MCP Server MCP server (vikasgaddu1/crf-annotation-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.