AI agents use ploomes_contacts_create to create or update resources in Ploomes — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ploomes environment.
The tool creates new records in a business-critical CRM system (Ploomes). While reversible (contacts can be deleted via ploomes_contacts_delete), creating unauthorized contacts could pollute customer databases, enable spam campaigns, or create fraudulent records. The operation modifies the system state irreversibly in terms of audit trails and business logic.
From the tool's definition Tool name and description explicitly state 'Create a new contact' — this is a write operation that adds new data to the CRM system.
Attacks that exploit this kind of access
Create a new contact in Ploomes CRM. Name is required. Use OtherProperties to set custom fields.\n\n. It is categorised as a Write tool in the Ploomes MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ploomes MCP server in PolicyLayer and add a rule for ploomes_contacts_create: 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 Ploomes. Nothing to install.
ploomes_contacts_create 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 ploomes_contacts_create 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 ploomes_contacts_create. 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.
ploomes_contacts_create is provided by the Ploomes MCP server (ploomes-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 →