AI agents call search_flaws 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 is a query tool that retrieves flaw records from OSIDB. The server's read-only guarantee and pattern of sibling tools (all getters and listers) confirm this searches and returns vulnerability data without creating, modifying, or deleting anything. The blast radius of misuse is low—worst case exposes existing vulnerability information already in the system.
From the tool's definition Tool name is 'search_flaws' with empty description. Server is explicitly described as 'read-only querying' and the sibling tools (flaw_get, affects_list, affect_get, etc.) are all retrieval operations with no mutation capability.
Attacks that exploit this kind of access
search_flaws. 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 search_flaws: 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.
search_flaws 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 search_flaws 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 search_flaws. 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.
search_flaws 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 →