AI agents use pylon_add_tags 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.
Adding tags is a metadata modification operation that creates associations without destructive side effects. While it alters issue state, the change is reversible through the removal or update operations, making it Write rather than Destructive.
From the tool's definition Tool description states it 'Add tags to a Pylon issue' which modifies issue metadata. The operation is explicitly reversible ('without removing existing tags') and complementary tools exist for removal ('pylon_remove_tags') and replacement…
Attacks that exploit this kind of access
Add tags to a Pylon issue without removing existing tags. To replace all tags, use pylon_update_issue; to remove tags, use pylon_remove_tags. 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_add_tags: 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_add_tags 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_add_tags 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_add_tags. 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_add_tags 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 →