Search clinical guidelines using hybrid BM25 + semantic retrieval.
AI agents call search_guidelines to retrieve information from Fhir Synthetic without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves clinical guideline information using search and semantic methods. No data is created, modified, deleted, or committed. No code execution or financial operations occur. The blast radius of misuse is minimal—an agent could only retrieve guideline information, not alter records or trigger external actions. This fits the Read category: retrieves or queries data with no side effects.
From the tool's definition Tool name 'search_guidelines' and description 'Search clinical guidelines using hybrid BM25 + semantic retrieval' indicate a read-only query operation that retrieves information without modification or side effects.
Attacks that exploit this kind of access
Search clinical guidelines using hybrid BM25 + semantic retrieval. It is categorised as a Read tool in the Fhir Synthetic MCP Server, which means it retrieves data without modifying state.
Register the Fhir Synthetic MCP server in PolicyLayer and add a rule for search_guidelines: 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 Fhir Synthetic. Nothing to install.
search_guidelines 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_guidelines 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_guidelines. 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_guidelines is provided by the Fhir Synthetic MCP server (krishnakakani-github/fhir-synthetic-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 →