Get the workspace color palette used by annotate / annotate_batch semantic tokens.
AI agents call palette_get to retrieve information from Whiteboard without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns color palette data used by the annotation system. It retrieves existing configuration without modifying, deleting, or executing operations. The blast radius of misuse is minimal—an AI agent obtaining palette colors poses no security or operational risk. Classified as Read with low severity.
From the tool's definition Tool name 'palette_get' and description 'Get the workspace color palette' indicate a retrieval operation with no side effects. The verb 'Get' and use case (reading palette configuration for annotate operations) confirm read-only behavior.
Attacks that exploit this kind of access
Get the workspace color palette used by annotate / annotate_batch semantic tokens. It is categorised as a Read tool in the Whiteboard MCP Server, which means it retrieves data without modifying state.
Register the Whiteboard MCP server in PolicyLayer and add a rule for palette_get: 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 Whiteboard. Nothing to install.
palette_get is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the palette_get 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 palette_get. 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.
palette_get is provided by the Whiteboard MCP server (kamiazya/whiteboard). 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 →