get_tags
AI agents call get_tags to retrieve information from Civitai MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves tag information from the Civitai API with no side effects. It follows the Read category pattern of the server: querying and filtering data without modification, creation, or deletion. Low severity due to no destructive capability; low blast radius if an AI agent calls it with unexpected arguments.
From the tool's definition Tool name 'get_tags' combined with server description indicating it 'provides tools for filtering models' and context of sibling Read-only tools (get_creators, get_images, get_latest_models, get_model, etc.) indicates this retrieves tag metadata.
Attacks that exploit this kind of access
get_tags. It is categorised as a Read tool in the Civitai MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Civitai MCP Server MCP server in PolicyLayer and add a rule for get_tags: 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 Civitai MCP Server. Nothing to install.
get_tags 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 get_tags 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 get_tags. 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.
get_tags is provided by the Civitai MCP Server MCP server (waura/civitai-mcp-server). 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 →