AI agents call tracker_get 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.
The tool retrieves tracker data from a vulnerability management system. It performs no modifications, deletions, or external operations. While the description is empty (lowering confidence slightly), the server's explicit read-only design and the consistent naming pattern with other GET operations on this server (affect_get, flaw_get) strongly indicate this is a read operation with minimal risk.
From the tool's definition Server is described as 'read-only querying' system. Tool name 'tracker_get' follows the GET pattern consistent with sibling read-only tools like 'affect_get' and 'flaw_get'.
Attacks that exploit this kind of access
tracker_get. 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 tracker_get: 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.
tracker_get 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 tracker_get 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 tracker_get. 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.
tracker_get 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 →