intercom_create_contact
AI agents use intercom_create_contact to create or update resources in Integrations MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Integrations MCP environment.
Creating a contact in Intercom adds new data to a customer database reversibly. This is a Write category action because it modifies state but is not destructive (can be updated or deleted later). Severity is medium because contact creation could enable unwanted outreach or database pollution if misused by an agent, but the blast radius is contained to Intercom and doesn't involve deletion or financial impact.
From the tool's definition Tool name is 'intercom_create_contact' which explicitly performs a create operation. The description is empty, but the name clearly indicates data creation/modification action in Intercom (a customer communication platform).
Attacks that exploit this kind of access
intercom_create_contact. It is categorised as a Write tool in the Integrations MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Integrations MCP server in PolicyLayer and add a rule for intercom_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 Integrations MCP. Nothing to install.
intercom_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 intercom_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 intercom_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.
intercom_create_contact is provided by the Integrations MCP server (shriram-vasudevan/integrations-mcp). 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 →