security_exposure

SERVERLivedatalink SOURCEhttps://livedatalink.ai/mcp

Low RISK CLASS

Category Read

Parameters 41 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-blackboxfoundry-livedatalink/security-exposure.md

WHAT IT DOES

What security_exposure does on Livedatalink

AI agents call security_exposure 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
`vendor`	string	—	Optional vendor to narrow the NVD CPE match (e.g. 'apache', 'openbsd').
`product`	string	Yes	Product or package name to assess (e.g. 'log4j', 'openssl', 'struts').
`version`	string	—	Optional version string (informational; shown in the report).
`max_cves`	number	—	Max CVEs to pull from NVD for analysis (default 40).

Parameters from the server's own tool schema.

RISK

Why security_exposure is rated Low

Even though security_exposure only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs security_exposure 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 security_exposure, this is the rule to start with:

security_exposure Allowed

security_exposure is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "security_exposure": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Livedatalink, apply this rule, and every security_exposure call is checked against it from then on.

FAQ

Questions about security_exposure

What does the security_exposure tool do? +

One-call known-vulnerability exposure for a vendor/product/package, built on the LiveDataLink cyber domain. Fans out to NVD (CVE search by vendor+product or keyword), the CISA KEV catalog (actively-exploited flag - the highest signal), FIRST EPSS (exploit-probability scores for the most-severe CVEs), and aggregates MITRE CWE weakness types from the matched CVEs. Returns total CVEs, counts by CVSS severity band, KEV membership with the actively-exploited CVEs listed, the highest EPSS score, the critical CVEs, top CWE weakness types, an overall exposure rollup (KEV present -> high), and an evidence list. No matches returns a friendly 0-exposure result; if the cyber source is unavailable that is noted per-source. Exactly one NVD call per invocation. INFORMATIONAL security research, not advice. Package-registry maintenance/staleness signals are out of scope for this tool. It is categorised as a Read tool in the Livedatalink MCP Server, which means it retrieves data without modifying state.

What parameters does security_exposure accept? +

security_exposure accepts 4 parameters: vendor, product, version, max_cves. Required: product. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on security_exposure? +

Register the Livedatalink MCP server in PolicyLayer and add a rule for security_exposure: 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.

What risk level is security_exposure? +

security_exposure is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit security_exposure? +

Yes. Add a rate_limit block to the security_exposure 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.

How do I block security_exposure completely? +

Set action: deny in the PolicyLayer policy for security_exposure. 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.

What MCP server provides security_exposure? +

security_exposure 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.

KEEP EXPLORING

More on Livedatalink, and thousands of servers like it.

This server

All 280 Livedatalink tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →