annotate_viz
AI agents use annotate_viz to create or update resources in HoloViz MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your HoloViz MCP Server environment.
Annotation is a reversible modification operation that adds or updates content (labels, notes, markers) on visualizations without destroying data. This fits the Write category. Severity is medium because misuse could deface visualizations or add misleading annotations, but the effect is limited in scope and reversible.
From the tool's definition Tool name 'annotate_viz' suggests modifying visualization objects by adding annotations. The empty description prevents direct confirmation, but annotation operations typically create or modify metadata/markup on existing visualizations.
Attacks that exploit this kind of access
annotate_viz. It is categorised as a Write tool in the HoloViz MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the HoloViz MCP Server MCP server in PolicyLayer and add a rule for annotate_viz: 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 HoloViz MCP Server. Nothing to install.
annotate_viz 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_viz 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_viz. 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_viz is provided by the HoloViz MCP Server MCP server (sumayabee/holoviz-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 →