AI agents call flaw_cvss_scores_list 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 CVSS security scores for a given vulnerability flaw identifier. It performs a simple paginated query with no side effects, state changes, or external operations. The read-only nature of the OSIDB server and the passive data retrieval pattern confirm Read category classification.
From the tool's definition Tool name 'flaw_cvss_scores_list' and description 'Paginated CVSS score rows for a flaw id' indicate data retrieval only. Server description explicitly states 'read-only querying'. No modification, deletion, execution, or financial operations are possible.
Attacks that exploit this kind of access
Paginated CVSS score rows for a flaw id. 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 flaw_cvss_scores_list: 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.
flaw_cvss_scores_list 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 flaw_cvss_scores_list 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 flaw_cvss_scores_list. 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.
flaw_cvss_scores_list 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 →