AI agents call get_palette to retrieve information from Musea without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that analyzes a Vue component to extract and return its properties palette (control types, defaults, ranges, options). It retrieves existing component information for inspection purposes. No side effects, code execution, data modification, or destructive operations are involved. Confidence is high because the function is clearly passive analysis/introspection.
From the tool's definition Tool 'get_palette' derives and retrieves an interactive props palette for a component—it reads/queries component metadata and configuration without modifying or executing anything.
Attacks that exploit this kind of access
Derive an interactive props palette (control types, defaults, ranges, options) for a component described by an Art file. Falls back to SFC analysis when native palette inference is sparse. It is categorised as a Read tool in the Musea MCP Server, which means it retrieves data without modifying state.
Register the Musea MCP server in PolicyLayer and add a rule for get_palette: 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 Musea. Nothing to install.
get_palette 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 get_palette 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 get_palette. 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.
get_palette is provided by the Musea MCP server (@vizejs/musea-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 →