search_images
AI agents call search_images to retrieve information from Docker Explorer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to search or query Docker images (likely by name, tag, or other metadata) without modifying, deleting, or executing anything. This is a retrieval operation with no side effects. While the tool description is empty, the name and server context strongly suggest it is a search/list function.
From the tool's definition Tool name is 'search_images' and the server description indicates it 'provides tools for interacting with Docker images, containers, and registries, enabling AI assistants to search, analyze, and manage Docker resources.' The 'search' function combined with…
Attacks that exploit this kind of access
search_images. It is categorised as a Read tool in the Docker Explorer MCP Server, which means it retrieves data without modifying state.
Register the Docker Explorer MCP server in PolicyLayer and add a rule for 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 Docker Explorer. Nothing to install.
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 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 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.
search_images is provided by the Docker Explorer MCP server (jar285/mcp-docker). 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 →