AI agents call ddg_image_search to retrieve information from Basic MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Image search is a read-only operation that queries an external search engine and returns results without modifying, executing code, deleting data, or creating financial obligations. The blast radius of misuse is minimal — an agent could perform unwanted searches or make excessive requests, but cannot damage systems or data through this tool alone.
From the tool's definition Tool description states 'Search DuckDuckGo for images' — a search operation that retrieves data with no side effects. Consistent with sibling tools (ddg_news_search, ddg_text_search, ddg_video_search) which are all query/search operations.
Attacks that exploit this kind of access
Search DuckDuckGo for images. It is categorised as a Read tool in the Basic MCP MCP Server, which means it retrieves data without modifying state.
Register the Basic MCP server in PolicyLayer and add a rule for ddg_image_search: 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 Basic MCP. Nothing to install.
ddg_image_search 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 ddg_image_search 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 ddg_image_search. 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.
ddg_image_search is provided by the Basic MCP server (nimishgautam/basic-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 →