AI agents use pylon_create_contact to create or update resources in Pylon — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pylon environment.
This tool creates a new contact record in the Pylon system, which is a write operation that modifies the customer database. While reversible (contacts can typically be deleted or updated), it adds new data to the system and could have moderate business impact if misused (e.g., creating duplicate or fraudulent contacts, polluting the database).
From the tool's definition Tool name 'pylon_create_contact' and description 'Create a new customer contact in Pylon' indicate data creation. The phrase 'Use carefully' suggests the action has reversible but notable consequences.
Attacks that exploit this kind of access
Create a new customer contact in Pylon. Use carefully. It is categorised as a Write tool in the Pylon MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pylon MCP server in PolicyLayer and add a rule for pylon_create_contact: 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_create_contact is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the pylon_create_contact 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_create_contact. 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_create_contact 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 →