Skip to content
CVE Security logo

CVE Security MCP server

Which servers in the official MCP registry are CVE Security's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-20

← Back to CVE Security

Whose server it is
  • Registry namecom.cve-security/cve-intelligenceverified in the MCP registry

The registry name sits under cve-security.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-20
  • Stateanswerschecked 2026-10-20
  • Tools9
  • Server calls itselfcve-security
  • Server version1.9.0
  • Protocol version2025-06-18

On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 316 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 2 of the 7 days it takes to judge reliability.

Once connected

  • For "track whether a vulnerability is being exploited in the wild", the likely first call is get_sightings.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 2, the first on 2026-10-20
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer252 ms
  • Space in an agent's context≈ 3,366 tokensthe definitions of all its tools (9), which an agent carries on every turn
  • Tool definitionsA · 96 of 100
  • Typed results0 of 9 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 2 of 9

What an agent can do with it

  • not sure · check whether a CVE is detectable with nuclei or Snort
  • not sure · find CVEs affecting your vendors and products
  • can do · track whether a vulnerability is being exploited in the wild

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers9 tools · read 2026-10-20
  • get_cve

    Full intelligence record for one CVE: per-scorer CVSS, EPSS, CISA KEV/ransomware/SSVC, four remote-detection modalities (the checks that work over the network) plus a host-check tier (self-contained Nuclei templates and Metasploit local…

  • search_cves

    Search the catalog. Free text (q) and/or structured filters: vendor (slug), cwe (CWE-nnn), technique (ATT&CK id, such as T1190), year ("2024,2025"), sev ("critical,high"), kev (0|1), kev_from / kev_to (ISO days, half-open CISA listing…

  • query_package

    CVEs affecting one open-source package, by purl (pkg:npm/lodash) or ecosystem + name (Maven names are group:artifact). Returns the CVE list KEV-first with each OSV version range VERBATIM: `events` plus one render-safe projection: `fixed`…

  • get_updates

    The publication change stream: what this site published, stamped with OUR publish time (first_published, kev_added, detection_added, remediation_added, first_sighted, chain_added, and the BOD 26-04 Table 1 input changes ssvc_changed…

  • get_scoreboard

    The Defender Scoreboard report (CC BY 4.0): exploited vs detectable vs patchable, every figure with its method, caveat and denominator, plus the corpus block and any method-change notes. Cite as "CVE Security Defender Scoreboard…

  • get_sightings

    Field sightings: CVEs a named sensor network recorded in the last 7 or 30 days, most sighting days first. A field sighting is a day on which Shadowserver honeypots (cited by VulnCheck KEV and published as daily lists by CIRCL…

  • get_chains

    Known Chained Vulnerabilities™: pairs of CVEs that a cited source reports were used together in one exploit chain (VulnCheck KEV entry text, Metasploit modules, SigmaHQ rules, press, research or academic sentences, community text judged…

  • get_epss_movers

    CVEs whose EPSS exploitation probability rose the most recently. window is "7d" (default) or "30d". Each rise is measured between same-EPSS-model-version scores, so a model release (which shifts the whole distribution) never appears as a…

  • table1_read

    BOD 26-04 Table 1 read for up to 50 CVEs at a stated asset exposure. Per CVE this dataset supplies CISA KEV status and due date, CISA's SSVC Automatable and Technical impact (Vulnrichment) and CISA's forensic triage flag on the KEV entry…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "cve-intelligence": {
      "type": "http",
      "url": "https://cve-security.com/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http cve-security https://cve-security.com/api/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://cve-security.com/api/mcp as a custom connector in the settings.

OpenAPI spec

16 paths, read 2026-10-20. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.