AI agents call affect_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.
This tool retrieves affect data from a vulnerability management system with no capability to modify, delete, or execute operations. The 'get' suffix indicates a simple retrieval operation consistent with read-only access. The blast radius is minimal—at worst, an agent could access sensitive vulnerability information, but cannot alter records or trigger external actions.
From the tool's definition Server is described as providing 'read-only querying' capabilities. Tool name 'affect_get' follows the pattern of other sibling tools like 'flaw_get', 'affects_list', 'affect_cvss_scores_list' which are all retrieval operations.
Attacks that exploit this kind of access
affect_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 affect_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.
affect_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 affect_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 affect_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.
affect_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 →