AI agents call tags_list to retrieve information from Voog without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries tag data without side effects. It performs a simple listing operation typical of Read category tools. The GET request method confirms no data is being created, modified, or deleted. Low severity because listing public tag metadata poses minimal risk even if accessed by an unauthorized agent.
From the tool's definition Tool name 'tags_list' and description 'List all tags on the site (`GET /tags`)' indicate a read-only operation using HTTP GET method. No modification, deletion, or execution capability is mentioned.
Attacks that exploit this kind of access
List all tags on the site (GET /tags). Returns the full. It is categorised as a Read tool in the Voog MCP Server, which means it retrieves data without modifying state.
Register the Voog MCP server in PolicyLayer and add a rule for tags_list: 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 Voog. Nothing to install.
tags_list 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 tags_list 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 tags_list. 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.
tags_list is provided by the Voog MCP server (runnel/voog-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 →