AI agents call trackers_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 tracker data from OSIDB vulnerability management system with no side effects. As a list operation on a read-only server, it poses minimal risk - worst case an agent could query sensitive vulnerability information, but cannot modify, delete, or execute operations. Low severity appropriate for information disclosure risk in controlled security context.
From the tool's definition Tool is part of osidb-mcp server which is explicitly 'read-only querying' system. Tool name 'trackers_list' follows the pattern of sibling tools (affect_get, affects_list, flaw_get, etc.) which are all read operations.
Attacks that exploit this kind of access
trackers_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 trackers_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.
trackers_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 trackers_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 trackers_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.
trackers_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 →