Search verified U.S. regulated-care providers (currently the GLP-1 / weight-management vertical is live) by vertical, city, state and business mode. Free tier (no key): identity fields per provider — entity_id, slug, vertical, name, city, state, business_mode, latitude, longitude, npi — plus a no...
AI agents call search_providers to retrieve information from Xcircl Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a data retrieval tool that searches and returns information about regulated care providers from a verified API. It has no side effects, does not modify data, execute code, or commit financial actions. The API key only unlocks additional read-only fields (compliance signals, pricing data).
From the tool's definition Tool description explicitly states it 'Search[es]' providers and 'Returns JSON' with provider fields. No create, modify, delete, or execute operations described.
Attacks that exploit this kind of access
Search verified U.S. regulated-care providers (currently the GLP-1 / weight-management vertical is live) by vertical, city, state and business mode. Free tier (no key): identity fields per provider — entity_id, slug, vertical, name, city, state, business_mode, latitude, longitude, npi — plus a notice describing paid fields. With XCIRCL_API_KEY: adds legitscript / license / fda compliance signals and cash price, each with source + verification timestamp. Returns JSON: { tier, publish_boundary, notice?, pagination: { total, limit, offset, returned }, filters, data: Provider[] }. Examples: -. It is categorised as a Read tool in the Xcircl Agent MCP Server, which means it retrieves data without modifying state.
Register the Xcircl Agent MCP server in PolicyLayer and add a rule for search_providers: 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 Xcircl Agent. Nothing to install.
search_providers 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_providers 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_providers. 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_providers is provided by the Xcircl Agent MCP server (25cy/xcircl-agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
search_providers is one line of Xcircl Agent'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 →