AI agents use note_add to create or update resources in Tpm — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tpm environment.
This tool creates new note/comment records reversibly. While it modifies the task state by appending information, it does not destructively overwrite, delete, or execute external operations. The action is confined to adding metadata (notes/comments) to project management records in a local SQLite database, which is a standard write operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool description states 'Add a note/comment to a ticket or task' — this is a create operation that adds new data to an existing task/ticket without deleting or modifying existing data.
Attacks that exploit this kind of access
PROJECT MANAGEMENT (TPM): Add a note/comment to a ticket or task for context or decisions. It is categorised as a Write tool in the Tpm MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tpm MCP server in PolicyLayer and add a rule for note_add: 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 Tpm. Nothing to install.
note_add 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 note_add 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 note_add. 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.
note_add is provided by the Tpm MCP server (urjitbhatia/tpm-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 →