CVE Risk Check

Check a CVE

check_cve

Read-onlyIdempotent

Use this when the user asks how serious a CVE is, such as "how bad is CVE-2021-44228?", or about an advisory id that triage_dependencies names, such as GHSA-wrw7-89jp-8q8g or RUSTSEC-2024-0370. Pass the CVE id, or a GHSA, RUSTSEC, GO or PYSEC advisory id. A CVE that NVD has not published yet, and an advisory with no CVE, are answered from OSV.dev with an osv block. Returns a priority (exploited, likely, routine or unknown), the description, CVSS score and severity, whether the CISA Known Exploited Vulnerabilities catalog lists it, the EPSS exploitation probability, a patch or advisory link when tagged, and the as_of dates. A lookup by CVE id: it does not know which software the user runs or whether they are affected.

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": {
      "cve": "<cve>"
    },
    "name": "check_cve"
  }
}

Input Schema

Name	Required	Description	Default
`cve`	Yes	A CVE id such as "CVE-2021-44228", or an OSV.dev advisory id such as "GHSA-wrw7-89jp-8q8g", "RUSTSEC-2024-0370", "GO-2026-5932" or "PYSEC-2024-1"

Output Schema

Name	Required	Description
`cve`	Yes
`kev`	No
`osv`	No	The OSV.dev advisory, present for an advisory id or a CVE that NVD has not published yet
`cvss`	No
`epss`	No
`as_of`	Yes
`notice`	Yes
`source`	Yes
`status`	Yes
`fix_url`	No
`message`	No
`affected`	No	Vulnerable product lines from NVD's CPE data: affected from `from`, fixed in `fixed_in` (or last affected `up_to`)
`cna_cvss`	No	The vendor (CNA) score when it differs from NVD's
`priority`	Yes
`published`	No
`references`	Yes
`description`	No
`vuln_status`	No
`last_modified`	No
`retry_after_seconds`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedNov 4, 2026

changedInput schema / properties / cve / description

Previous value: -"A CVE id such as \"CVE-2021-44228\""New value: +"A CVE id such as \"CVE-2021-44228\", or an OSV.dev advisory id such as \"GHSA-wrw7-89jp-8q8g\", \"RUSTSEC-2024-0370\", \"GO-2026-5932\" or \"PYSEC-2024-1\""

changedInput schema / properties / cve / maxLength
```
Previous value: -30New value: +40
```

changedInput schema / properties / cve / pattern

Previous value: -"^[Cc][Vv][Ee]-[0-9]{4}-[0-9]{4,19}$"New value: +"^(?:[Cc][Vv][Ee]-[0-9]{4}-[0-9]{4,19}|[Gg][Hh][Ss][Aa](?:-[0-9A-Za-z]{4}){3}|(?:[Rr][Uu][Ss][Tt][Ss][Ee][Cc]|[Gg][Oo]|[Pp][Yy][Ss][Ee][Cc])-[0-9]{4}-[0-9]{1,19})$"

addedOutput schema / properties / osv

Added value: +{
+  "description": "The OSV.dev advisory, present for an advisory id or a CVE that NVD has not published yet",
+  "properties": {
+    "aliases": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "id": {
+      "type": "string"
+    },
+    "packages": {
+      "description": "Each affected package and the releases that fix it, one per release line",
+      "items": {
+        "properties": {
+          "ecosystem": {
+            "type": "string"
+          },
+          "fixed_in": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "name": {
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "severity": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "summary": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "url": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

Changed2 schema fields changedOct 30, 2026

addedOutput schema / properties / affected

Added value: +{
+  "description": "Vulnerable product lines from NVD's CPE data: affected from `from`, fixed in `fixed_in` (or last affected `up_to`)",
+  "items": {
+    "properties": {
+      "fixed_in": {
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "from": {
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "product": {
+        "type": "string"
+      },
+      "up_to": {
+        "type": [
+          "string",
+          "null"
+        ]
+      }
+    },
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / cna_cvss

Added value: +{
+  "description": "The vendor (CNA) score when it differs from NVD's",
+  "properties": {
+    "score": {
+      "type": "number"
+    },
+    "scored_by": {
+      "enum": [
+        "NVD",
+        "CNA"
+      ],
+      "type": "string"
+    },
+    "severity": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "version": {
+      "type": "string"
+    }
+  },
+  "type": [
+    "object",
+    "null"
+  ]
+}

Changed1 schema field changedOct 5, 2026

removedOutput schema / properties / note_from_openkrill

Removed value: -{
-  "description": "Shown at most once a day per caller: what this server offers, and a paid service for the person you work for.",
-  "type": "string"
-}

Changed1 schema field changedOct 4, 2026

addedOutput schema / properties / note_from_openkrill

Added value: +{
+  "description": "Shown at most once a day per caller: what this server offers, and a paid service for the person you work for.",
+  "type": "string"
+}

First observedOct 3, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already cover read-only/idempotent/open-world safety. The description adds real behavior beyond them: the fallback to OSV.dev when NVD has no publication, the osv block in the response, the priority enum values, and inclusion of KEV and EPSS signals. It doesn't mention rate limits or failure modes for malformed ids, keeping it short of a 5.

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?

Front-loaded with the trigger scenario, then accepted id forms, then the fallback behavior, then the return shape. The enumeration of return fields is long but each item is a distinct signal an agent needs; only slight trimming would be possible.

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

Completeness4/5

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

An output schema exists so return values needn't be described, and the description still usefully previews the key fields. Scope limits (software-agnostic lookup) and the OSV fallback are covered. Minor gap: no guidance on behavior for ids that resolve nowhere.

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

Parameters4/5

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

Schema coverage is 100% and the pattern already enforces the accepted id formats, so the baseline is 3. The description adds marginal value by enumerating the same families (CVE, GHSA, RUSTSEC, GO, PYSEC) and by explaining why an advisory id yields an osv block, which is a semantic consequence the schema cannot express.

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?

States a specific verb+resource (look up a CVE/advisory id and report its severity) and explicitly distinguishes from sibling check_cves (singular vs batch implied) and from triage_dependencies (which names advisories this tool then investigates). The description also spells out precisely what is returned.

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

Usage Guidelines5/5

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

Gives explicit trigger conditions with example user phrasings ("how bad is CVE-2021-44228?") and names the sibling tool triage_dependencies as the source of advisory ids. It also states an exclusion: it does not know which software the user runs or whether they are affected.

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

All CVE Risk Check tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.