AI agents call pylon_search_contacts to retrieve information from Pylon without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves contact data based on search criteria. It has no side effects, does not modify data, and does not execute arbitrary operations. It is a straightforward read operation that fits the Read category with low severity due to minimal blast radius if misused—worst case being retrieval of contact information already available in the system.
From the tool's definition Tool name contains 'search' and description states it 'Search[es] for customer contacts by name, email, company, or phone' — these are query operations with no modification, deletion, or execution of external code.
Attacks that exploit this kind of access
Search for customer contacts by name, email, company, or phone. It is categorised as a Read tool in the Pylon MCP Server, which means it retrieves data without modifying state.
Register the Pylon MCP server in PolicyLayer and add a rule for pylon_search_contacts: 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 Pylon. Nothing to install.
pylon_search_contacts 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 pylon_search_contacts 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 pylon_search_contacts. 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.
pylon_search_contacts is provided by the Pylon MCP server (@customer-support-success/pylon-mcp-server). 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 →