AI agents call flaws_search 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 searches/queries flaw data from OSIDB without modification or side effects. The server is explicitly read-only, and all sibling tools are retrieval operations. Search is a classic Read category operation. Low severity because it only exposes vulnerability metadata without execution, financial, or destructive capabilities.
From the tool's definition Tool name 'flaws_search' combined with server description stating 'read-only querying of flaws' and sibling tools all following read-only patterns (affect_get, flaw_get, *_list operations). Tool description is empty but naming and context are clear.
Attacks that exploit this kind of access
flaws_search. 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 flaws_search: 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.
flaws_search 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 flaws_search 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 flaws_search. 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.
flaws_search 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 →