Can the UK Data: CVEs and package popularity MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the UK Data: CVEs and package popularity MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the UK Data: CVEs and package popularity MCP server have?

4 tools: 4 read. cve_lookup, npm_stats, pypi_stats and crate_stats.

Does the UK Data: CVEs and package popularity MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the UK Data: CVEs and package popularity MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the UK Data: CVEs and package popularity MCP server changed its tools?

Not since anlyon.dev started tracking it. Last scanned Nov 7, 2026.

UK Data: CVEs and package popularity MCP server

uk.co.reliness/dev-securityreliness.co.ukstreamable-httpv1.5.0Scanned 8 days ago

Software vulnerabilities (CVEs) from the US NVD and package downloads for npm, PyPI and crates

4 tools: 4 only read.

Reads private data · 0
Reads text others write · 4
Can send data out · 0
No findings

Tools listed without sign-in. Remote posture

With Anlyon

Decide which of this server's tools your agent can use.

Anlyon lists the tools and adopts none.
Each tool you adopt gets approvals and receipts.
Your agent never holds the key.

Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. anlyon.dev only lists and labels, and these labels are the same either way.

What the UK Data: CVEs and package popularity MCP server can do

The UK Data: CVEs and package popularity MCP server is published by reliness.co.uk, a domain the MCP Registry verified. It has 4 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.

4 tools bring in text other people can write (cve_lookup, npm_stats, pypi_stats and 1 more).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 7, 2026, version 1.5.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

4 tools

Only reads 4Looks things up and changes nothing.Show 4 read-only tools

crate_statsGet download statistics and metadata for a Rust crate from crates.io.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it
Get download statistics and metadata for a Rust crate from crates.io. Returns total and recent download counts along with the latest version number. (cost: 1 credit)
Annotations the server declares
- title: crate stats
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
cve_lookupDetails of one specific CVE by its ID (e.g., CVE-2021-44228).Reads text others writeNo findings
Why it is in this group
- The name "cve_lookup" says "lookup": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it
Details of one specific CVE by its ID (e.g., CVE-2021-44228). Returns the vulnerability description, CVSS score, severity, published/modified dates, weakness type (CWE), and reference links for fixes or advisories from the NIST National Vulnerability Database. (cost: 1 credit)
Annotations the server declares
- title: cve lookup
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
npm_statsGet download statistics for a JavaScript package on the npm registry.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it
Get download statistics for a JavaScript package on the npm registry. Returns the total download count for the last week to gauge popularity and usage trends. (cost: 1 credit)
Annotations the server declares
- title: npm stats
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
pypi_statsGet download statistics for a Python package from PyPI.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it
Get download statistics for a Python package from PyPI. Returns recent download counts for the last day, week, and month to measure library adoption. (cost: 1 credit)
Annotations the server declares
- title: pypi stats
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.

Reads private data0: Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4: Brings in text someone else can write: web pages, inbound email, messages, issues and comments.; crate_stats
cve_lookup
npm_stats
pypi_stats
Can send data out0: Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 14, 2026, 12:23 UTC, unchanged since Nov 7, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable: yes
HTTP status of an anonymous initialize: 200
tools/list served without credentials: yes
Tools that change things, listed without credentials: 0
Protocol version: 2025-06-18
WWW-Authenticate on 401: not observed
resource_metadata in WWW-Authenticate: not observed
RFC 9728 protected resource metadata: not observed
Authorization servers: not observed
Legacy HTTP+SSE transport: no
Dynamic client registration: not observed
Client ID metadata documents: not observed

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

All changes to this server

Install

Pinned to version 1.5.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http dev-security https://ukdata.reliness.co.uk/mcp/dev-security

claude mcp add --transport http dev-security https://ukdata.reliness.co.uk/mcp/dev-security

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json

{
  "permissions": {
    "allow": [
      "mcp__dev-security__cve_lookup",
      "mcp__dev-security__npm_stats",
      "mcp__dev-security__pypi_stats",
      "mcp__dev-security__crate_stats"
    ],
    "ask": [],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as dev-security. Review it before you use it.

Capability tags behind 4 rules

mcp__dev-security__cve_lookup untrusted-input
mcp__dev-security__npm_stats untrusted-input
mcp__dev-security__pypi_stats untrusted-input
mcp__dev-security__crate_stats untrusted-input

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://anlyon.dev/api/v1/servers/uk.co.reliness/dev-security/verify?hash=0e0099e2984b2ed7fd0dc979d791ce7098ac2a491412f81f68c97cc8104bf502" | jq -e '.changed == false'

Pinned hash 0e0099e2984b, from Nov 7, 2026, 00:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/uk.co.reliness/dev-security/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

[![anlyon.dev](https://anlyon.dev/badge/uk.co.reliness/dev-security.svg)](https://anlyon.dev/servers/uk.co.reliness/dev-security)

Source: MCP Registry. Synced Nov 7, 2026, 00:18 UTC.