Extract brand assets from any domain. Returns logo URL, favicon, theme colors, OG image, and site name. Free preview: GET https://brand-assets.apimesh.xyz/preview?domain=... returns Google favicon URL for free
AI agents call brand_assets to retrieve information from APIMesh MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs data retrieval only—fetching publicly available branding metadata from domains. There are no side effects, no code execution, no data modification, and no destructive operations. It is a classic Read category tool with minimal security risk (low severity) since the information returned is typically public-facing branding data.
From the tool's definition Tool description explicitly states it 'Extract[s] brand assets from any domain' and 'Returns logo URL, favicon, theme colors, OG image, and site name.' These are all read-only retrieval operations with no modification or deletion of data.
Attacks that exploit this kind of access
Extract brand assets from any domain. Returns logo URL, favicon, theme colors, OG image, and site name. Free preview: GET https://brand-assets.apimesh.xyz/preview?domain=... returns Google favicon URL for free. It is categorised as a Read tool in the APIMesh MCP Server MCP Server, which means it retrieves data without modifying state.
Register the APIMesh MCP Server MCP server in PolicyLayer and add a rule for brand_assets: 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 APIMesh MCP Server. Nothing to install.
brand_assets 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 brand_assets 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 brand_assets. 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.
brand_assets is provided by the APIMesh MCP Server MCP server (mbeato/apimesh). 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 →