Search for companies by name.
AI agents call crm_search_companies to retrieve information from Medicus CRM MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search operation to retrieve company records matching a name criterion. It is a read-only query with no side effects—it neither creates, modifies, deletes, nor executes external operations. The blast radius is minimal as misuse only exposes existing company data already stored in the system.
From the tool's definition Tool name 'crm_search_companies' and description 'Search for companies by name' indicate a query operation that retrieves data without modification or deletion.
Attacks that exploit this kind of access
Search for companies by name. It is categorised as a Read tool in the Medicus CRM MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Medicus CRM MCP Server MCP server in PolicyLayer and add a rule for crm_search_companies: 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 Medicus CRM MCP Server. Nothing to install.
crm_search_companies 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 crm_search_companies 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 crm_search_companies. 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.
crm_search_companies is provided by the Medicus CRM MCP Server MCP server (soundrolling/crmmcp). 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 →