cve_search_by_keyword
Free-text CVE search with optional date range. Matches keyword against CVE description text in the NVD.
This record as markdown: /tools/io-github-blackboxfoundry-livedatalink/cve-search-by-keyword.md
What cve_search_by_keyword does on Livedatalink
AI agents call cve_search_by_keyword to retrieve information from Livedatalink without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | number | — | Max results to return (1-2000, default 20). |
keyword | string | Yes | Free-text search phrase. |
pub_end_date | string | — | Optional YYYY-MM-DD upper bound. |
pub_start_date | string | — | Optional YYYY-MM-DD lower bound. |
Parameters from the server's own tool schema.
Why cve_search_by_keyword is rated Low
This is a search/query operation that retrieves existing vulnerability information from NVD. No side effects, no code execution, no data modification or deletion. While the data concerns security vulnerabilities, the tool itself is read-only and informational. Severity is low because misuse results only in unwanted information retrieval with no blast radius on systems or financial impact.
From the tool's definition Tool performs 'Free-text CVE search' and 'Matches keyword against CVE description text' - it retrieves data from the National Vulnerability Database without modifying, executing code, or triggering external actions.
Attacks that exploit this kind of access
The rule that runs cve_search_by_keyword safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Livedatalink, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For cve_search_by_keyword, this is the rule to start with:
cve_search_by_keyword is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Livedatalink, apply this rule, and every cve_search_by_keyword call is checked against it from then on.
Questions about cve_search_by_keyword
Free-text CVE search with optional date range. Matches keyword against CVE description text in the NVD. It is categorised as a Read tool in the Livedatalink MCP Server, which means it retrieves data without modifying state.
cve_search_by_keyword accepts 4 parameters: limit, keyword, pub_end_date, pub_start_date. Required: keyword. The full parameter table on this page comes from the server's own tool schema.
Register the Livedatalink MCP server in PolicyLayer and add a rule for cve_search_by_keyword: 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 Livedatalink. Nothing to install.
cve_search_by_keyword 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 cve_search_by_keyword 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 cve_search_by_keyword. 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.
cve_search_by_keyword is provided by the Livedatalink MCP server (https://livedatalink.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Livedatalink, and thousands of servers like it.
This server
Across the catalogue