Attach an annotation to a graph node.
AI agents use annotate_node to create or update resources in Trailmark MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Trailmark MCP Server environment.
This tool creates or modifies metadata (annotations) associated with code repository nodes. It is reversible (annotations can be cleared, as evidenced by the sibling tool 'clear_annotations'), making it Write rather than Destructive.
From the tool's definition Tool description states 'Attach an annotation to a graph node,' which is a reversible modification operation. The verb 'attach' indicates data creation/modification without permanent deletion. Annotations can typically be removed or updated.
Attacks that exploit this kind of access
Attach an annotation to a graph node. It is categorised as a Write tool in the Trailmark MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Trailmark MCP Server MCP server in PolicyLayer and add a rule for annotate_node: 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 Trailmark MCP Server. Nothing to install.
annotate_node 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 annotate_node 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 annotate_node. 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.
annotate_node is provided by the Trailmark MCP Server MCP server (parsiya/trailmark-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 →