AI agents use add_tag_to_contact to create or update resources in Systemeio — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Systemeio environment.
This tool creates or modifies a relationship (tag assignment) on an existing contact record. While it may indirectly trigger automations, the primary action is Write—assigning metadata to an entity. It is reversible (unlike Destructive) and does not execute arbitrary code (unlike Execute).
From the tool's definition Tool description states "Assign a tag to a contact" which is a modification operation. The note that it "can trigger automations" indicates side effects but the tool itself performs a reversible write (tags can be removed via delete_tag).
Attacks that exploit this kind of access
Assign a tag to a contact. This can trigger automations in Systeme.io (e.g., adding to a campaign, enrolling in a course). It is categorised as a Write tool in the Systemeio MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Systemeio MCP server in PolicyLayer and add a rule for add_tag_to_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 Systemeio. Nothing to install.
add_tag_to_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 add_tag_to_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 add_tag_to_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.
add_tag_to_contact is provided by the Systemeio MCP server (snzeeee/mcp-server-systemeio). 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 →