Search for Docker images in Docker Hub
AI agents call search_docker_image to retrieve information from Pacman without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only search operation against Docker Hub. It retrieves and displays information about available Docker images but does not create, modify, execute, or delete any resources. The blast radius of misuse is minimal—an agent might return irrelevant or excessive search results, but no data would be compromised or systems affected.
From the tool's definition Tool name 'search_docker_image' and description 'Search for Docker images in Docker Hub' indicate a query operation that retrieves information without modifying, executing, or deleting anything.
Documented attack patterns abuse exactly the kind of access search_docker_image gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pacman, and nothing reaches the server without passing your rules. This is the rule we recommend for search_docker_image:
{
"version": "1",
"default": "deny",
"tools": {
"search_docker_image": {}
}
}search_docker_image is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search for Docker images in Docker Hub. It is categorised as a Read tool in the Pacman MCP Server, which means it retrieves data without modifying state.
Register the Pacman MCP server in PolicyLayer and add a rule for search_docker_image: 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 Pacman. Nothing to install.
search_docker_image 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_docker_image 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_docker_image. 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_docker_image is provided by the Pacman MCP server (oborchers/mcp-server-pacman). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Pacman, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 Pacman tools catalogued and risk-classified — across an index of 43,000+ MCP servers.