AI agents call flaws_count 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 performs a read-only query operation that retrieves count statistics. It has no side effects, does not execute arbitrary code, does not modify data, and does not involve financial transactions. The blast radius of misuse is minimal—an agent could only perform excessive queries, which is a DoS concern but not inherent to the tool's capability. This is a straightforward Read operation.
From the tool's definition Tool is described as 'Count flaws matching the same filters as flaws_list (no result bodies)' and is part of a read-only OSIDB querying server. The operation retrieves aggregate counts without returning detailed data or modifying state.
Attacks that exploit this kind of access
Count flaws matching the same filters as flaws_list (no result bodies). 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_count: 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_count 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_count 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_count. 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_count 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 →