get_labels
AI agents call get_labels to retrieve information from Mcp Atlassian without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves labels, which are read-only queries with no side effects. No data is modified, deleted, or financial operations involved. Despite the empty description reducing precision slightly, the naming convention and server context strongly indicate a simple data retrieval operation. Severity is low as label retrieval poses minimal risk even if misused by an agent.
From the tool's definition Tool name 'get_labels' indicates retrieval of label data. Server context shows this is part of Atlassian Confluence/Jira integration where labels are metadata tags on issues and pages.
Attacks that exploit this kind of access
get_labels. It is categorised as a Read tool in the Mcp Atlassian MCP Server, which means it retrieves data without modifying state.
Register the Mcp Atlassian MCP server in PolicyLayer and add a rule for get_labels: 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 Mcp Atlassian. Nothing to install.
get_labels 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_labels 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_labels. 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_labels is provided by the Mcp Atlassian MCP server (voarsh2/mcp-atlassian). 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 →