Skip to main content
SkillTotal

Is Everything reference MCP server safe?

What Everything reference MCP server does

Everything is a test server for people building MCP clients. Its README says it exercises all features of the MCP protocol, including prompts, tools, resources and sampling, and is not intended to be a useful server. The npm author field names Model Context Protocol a Series of LF Projects, LLC. Our scan of the package found outbound network code alongside the MCP tool definitions and an npm prepare script. Before installing, confirm you actually need a protocol test fixture; it is meant for client development and testing, not for day-to-day agent work.

No malicious indicators - review capabilities before installing
Notable — review in context (a capability is not a malicious indicator):
  • Node.js network egress
  • npm prepare hook
  • MCP tool surface detected

What to do: Nothing here argues against installing it. Grant the capabilities it lists only if you expect the tool to need them.

Everything reference MCP server is an MCP server analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators. It can: install time execution, mcp tools detected and network egress — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).

@modelcontextprotocol/server-everything 2.3.0

npm package · npm:@modelcontextprotocol/server-everything
LOW
0
/ 100 risk score
Snapshot · scanned Nov 13, 2026 · @modelcontextprotocol/server-everything@2.3.0 · engine 1.1.0 / ruleset 100

Get notified when this component changes

Change alerts aren't live yet. Leave your email and we'll let you know when they launch. We use it only for this and delete it on request.

Automated static-analysis result. It can contain false positives and false negatives, and is not a claim about the intent of Everything reference MCP server's authors. Report a false positive.

Capabilities — what this component can do (not a risk score):
install time executionmcp tools detectednetwork egress

Behavioral traits

How this component maps to the CSA agentic threat model. Descriptive — it never affects the risk score.

Tool surface
Tool Usage
Network egress
Interaction & Communication / Direct Communication
Supply-chain provenance risk
General Protections / Supply Chain

Findings (3)

Capabilitynpm prepare hooknot scored · severity mediumST-INSTALL-NPM-PREPARE

package.json has a 'prepare' script (runs on git/local installs and before publishing).

package.json:26 
"prepare": "npm run build",

Why it matters: Usually a build step, but confirm it doesn't fetch or run remote code.

Fix: Usually a legitimate build step; confirm it only builds and does not fetch or execute remote code.

CapabilityNode.js network egressnot scored · severity mediumST-NET-NODE

The component makes outbound network requests.

dist/tools/gzip-file-as-resource.js:22 
import { lookup } from "node:dns/promises";
dist/tools/gzip-file-as-resource.js:269 
const response = await fetch(target, { signal, redirect: "manual" });

Why it matters: Usually legitimate, but confirm the destinations are expected and no sensitive data leaves.

Fix: Confirm the destination hosts are expected and that no sensitive data is sent off-host.

CapabilityMCP tool surface detectednot scored · severity lowST-MCP-DETECTED

An MCP tool surface (manifest or tool definitions) was found.

dist/server/index.js:74 
const server = new McpServer({
dist/tools/echo.js:31 
server.registerTool(name, config, async (args) => {
dist/tools/get-annotated-message.js:41 
server.registerTool(name, config, async (args) => {
dist/tools/get-env.js:80 
server.registerTool(name, config, async () => {
dist/tools/get-header-params.js:85 
server.registerTool(name, config, async ({ region, repeat }, ctx) => {
dist/tools/get-resource-links.js:39 
server.registerTool(name, config, async (args) => {
dist/tools/get-resource-reference.js:46 
server.registerTool(name, config, async (args) => {
dist/tools/get-roots-list.js:37 
server.registerTool(name, config, async (_args, ctx) => {
dist/tools/get-structured-content.js:45 
server.registerTool(name, config, async (args) => {
dist/tools/get-sum.js:36 
server.registerTool(name, config, async (args) => {
dist/tools/get-tiny-image.js:30 
server.registerTool(name, config, async () => {
dist/tools/gzip-file-as-resource.js:172 
server.registerTool(name, config, async (args) => {
dist/tools/simulate-research-query.js:156 
server.registerTool(name, config, async (args, ctx) => {
dist/tools/toggle-simulated-logging.js:46 
server.registerTool(name, config, async () => {
dist/tools/toggle-subscriber-updates.js:46 
server.registerTool(name, config, async () => {
dist/tools/trigger-elicitation-request-async.js:77 
server.registerTool(name, config, async () => {
dist/tools/trigger-elicitation-request.js:189 
server.registerTool(name, config, async (_args, ctx) => {
dist/tools/trigger-list-changed.js:42 
server.registerTool(name, config, async (args) => {
dist/tools/trigger-log-messages.js:48 
server.registerTool(name, config, async (_args, ctx) => {
dist/tools/trigger-long-running-operation.js:46 
server.registerTool(name, config, async (args, ctx) => {
dist/tools/trigger-multi-step-elicitation.js:89 
server.registerTool(name, config, async (_args, ctx) => {
dist/tools/trigger-resource-update.js:42 
server.registerTool(name, config, async (args) => {
dist/tools/trigger-sampling-request-async.js:54 
server.registerTool(name, config, async (args) => {
dist/tools/trigger-sampling-request.js:51 
server.registerTool(name, config, async (args, ctx) => {
dist/tools/trigger-url-elicitation.js:83 
server.registerTool(name, config, async (args, ctx) => {

Why it matters: Just context — review which tools it offers and their permissions.

Fix: Review the declared MCP tools and their permissions.

How attackers abuse these capabilities

Interactive labs on the attack class behind the rules above. They show the technique, not anything found in Everything reference MCP server.

Maintain Everything reference MCP server?

Check the next package before your agent installs it

The free Claude Code plugin scans each npm, PyPI or MCP package with this report's open-source engine before the install command runs. It runs on your machine and needs no account.

Set up the pluginOr scan pull requests in CI with the GitHub Action

Check your own component

Run the same evidence-backed scan on any MCP server, agent skill, or package.

Scan your own component

How we determine this: deterministic static analysis (regex + AST), evidence-anchored, no code execution. Methodology →