AI agents call get_cve_summary 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 or queries CVE summary data without modifying, executing code, or deleting anything. It fits the Read category of data retrieval with no side effects. The server is explicitly documented as providing 'read-only querying' access to vulnerability data. Even with an empty description, the tool name and server context indicate safe data retrieval operations.
From the tool's definition Tool name 'get_cve_summary' indicates data retrieval. Server description states 'read-only querying' and all sibling tools (affect_get, affects_list, flaw_get, etc.) are Read operations.
Attacks that exploit this kind of access
get_cve_summary. 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 get_cve_summary: 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.
get_cve_summary 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_cve_summary 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_cve_summary. 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_cve_summary 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 →