AI agents call labels_list to retrieve information from Osidb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries label data from OSIDB without side effects. As part of a read-only vulnerability management system, it falls squarely into the Read category. The blast radius is minimal—label listings cannot modify data, trigger external actions, or cause harm beyond information disclosure. Low severity reflects the non-sensitive nature of metadata queries in a security context.
From the tool's definition Tool is part of osidb-mcp server explicitly described as 'read-only querying' of vulnerability data. Tool name 'labels_list' matches the sibling tool 'flaw_labels_list' pattern, indicating it retrieves/lists label data without modification.
Attacks that exploit this kind of access
labels_list. It is categorised as a Read tool in the Osidb MCP Server, which means it retrieves data without modifying state.
Register the Osidb MCP server in PolicyLayer and add a rule for labels_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 Osidb. Nothing to install.
labels_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 labels_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 labels_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.
labels_list is provided by the Osidb MCP server (vdanen/osidb-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 →