SiteCheck Web Intel

Vulnerability trend for a vendor from the NIST NVD: CVEs

security_cve_details_feed

Read-only

Vulnerability trend for a vendor (optionally one product) from the NIST NVD: CVEs published in the last N days (default 7, up to 120; a big vendor over a long window can take NVD 30+ seconds) naming the vendor (or mapped to its CPE with match=cpe), counts by severity, average and maximum CVSS score, CVEs per week, top CWE weaknesses and the highest-scored CVEs with score, severity, vector, date and description. Related tools on this server, for a different need: security_cve_nvd_lookup when you need one CVE record from the NIST National Vulnerability; security_openphish_feed when you need to check a URL or host against the OpenPhish public phishing. Price: $0.002 in USDC per successful call, paid with x402 (Base, Solana or Arc); failed calls are not charged.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "vendor": "<vendor>"
    },
    "name": "security_cve_details_feed"
  }
}

Input Schema

Name	Required	Description
`top`	No	How many top-scored CVEs to list, 1 to 50 (default 10)
`days`	No	Look-back window in days, 1 to 120 (default 7)
`match`	No	keyword (default: vendor/product words in the CVE text) or cpe (only CVEs NVD has mapped to the vendor CPE)
`vendor`	Yes	CPE vendor name, e.g. microsoft, apache, cisco, fortinet (required)
`product`	No	Optional CPE product name, e.g. windows_11_24h2, http_server, fortios

Output Schema

Name	Required	Description	Default
`to`	No
`days`	No
`from`	No
`match`	No
`source`	No
`vendor`	No
`perWeek`	No
`product`	No
`topCves`	No
`analysed`	No
`maxScore`	No
`checkedAt`	No
`totalCves`	No
`bySeverity`	No
`averageScore`	No
`topWeaknesses`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.4/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint/openWorldHint annotations, the description discloses latency risk ('a big vendor over a long window can take NVD 30+ seconds'), the default look-back window, and the payment model ($0.002 USDC per successful call via x402, failed calls not charged). These are operationally important facts an agent cannot infer from structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose and output list are front-loaded, and the related-tools and pricing sentences are separated by clear signposting. The first sentence is long and dense with parentheticals, but no sentence is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only, open-world feed with an output schema, the description covers scope, defaults, latency, cost, and alternatives. Nothing an agent needs to invoke it correctly or anticipate cost/delay is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents all five parameters including ranges and defaults. The description mostly restates those defaults ('default 7, up to 120') and adds only marginal meaning, such as the CPE-mapping behavior of match=cpe. Baseline 3 is appropriate when the schema carries the parameter burden.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ('Vulnerability trend for a vendor ... from the NIST NVD') and enumerates the exact outputs (severity counts, average/max CVSS, CVEs per week, top CWEs, highest-scored CVEs). It explicitly distinguishes itself from security_cve_nvd_lookup and security_openphish_feed, so an agent can route without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear routing guidance by naming two sibling tools and the conditions that select them ('when you need one CVE record', 'when you need to check a URL or host'). It stops short of stating when this tool itself is the wrong choice (e.g., for a single CVE lookup), but the alternative framing covers most of the decision.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All SiteCheck Web Intel tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?