sendgrid_add_contact
AI agents use sendgrid_add_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.
SendGrid is a marketing platform where contacts are email subscribers/recipients. Adding a contact creates a new database record, which is reversible (contacts can be deleted or updated later). This is a Write operation rather than Read (does not just retrieve data) or Destructive (does not delete).
From the tool's definition Tool name 'sendgrid_add_contact' indicates creation of a new contact record in SendGrid, a bulk email and marketing automation platform. The 'add' verb combined with 'contact' strongly suggests a write operation that creates or modifies data.
Attacks that exploit this kind of access
sendgrid_add_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 sendgrid_add_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.
sendgrid_add_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 sendgrid_add_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 sendgrid_add_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.
sendgrid_add_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 →