Search Google Images via SERP API. Returns image results with URLs, thumbnails, dimensions, and sources ready for import to WordPress media library. Requires SERP API key configured in ML Media Hub settings.
AI agents call mlmh_search_images to retrieve information from FluentCommunity Manager without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries an external API (Google Images via SERP) and retrieves metadata (URLs, thumbnails, dimensions, sources). While it does not modify data, the medium severity reflects the risk that an AI agent could scrape and surface potentially copyrighted, inappropriate, or malicious images for import into WordPress, creating downstream content moderation and legal liability issues.
From the tool's definition Tool description explicitly states it 'Search[es]' Google Images and 'Returns image results' — retrieval operations with no data modification. No delete, create, update, or execute capabilities mentioned.
Attacks that exploit this kind of access
Search Google Images via SERP API. Returns image results with URLs, thumbnails, dimensions, and sources ready for import to WordPress media library. Requires SERP API key configured in ML Media Hub settings. It is categorised as a Read tool in the FluentCommunity Manager MCP Server, which means it retrieves data without modifying state.
Register the FluentCommunity Manager MCP server in PolicyLayer and add a rule for mlmh_search_images: 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 FluentCommunity Manager. Nothing to install.
mlmh_search_images 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 mlmh_search_images 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 mlmh_search_images. 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.
mlmh_search_images is provided by the FluentCommunity Manager MCP server (wplaunchify/fluent-community-mcp). 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 →