AI agents call query_affects 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 queries vulnerability affect records from OSIDB without modifying, deleting, or executing external operations. Blast radius is minimal—worst case, an AI agent retrieves sensitive vulnerability data, but cannot alter it. Classified as Read with high confidence based on server design and sibling tool patterns.
From the tool's definition Server is explicitly 'read-only' for 'querying' vulnerability data. Tool name 'query_affects' follows read pattern (query, get, list). Sibling tools are all read-only accessors (affect_get, affects_list, flaw_get, etc.).
Attacks that exploit this kind of access
query_affects. 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 query_affects: 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.
query_affects 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 query_affects 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 query_affects. 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.
query_affects 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 →