SkillTotal

Is Everything reference MCP server safe?

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

@modelcontextprotocol/server-everything is an AI npm_package analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators, though 3 risky constructs are reported for review. 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 2026.8.31

npm_package · npm:@modelcontextprotocol/server-everything
LOW
0
/ 100 risk score
Snapshot · scanned Sep 24, 2026 · @modelcontextprotocol/server-everything@2026.8.31 · engine 0.53.0 / ruleset 60

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)

MEDIUMnpm prepare hookST-INSTALL-NPM-PREPARE

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

package.json:23-23 
"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.

MEDIUMNode.js network egressST-NET-NODE

The component makes outbound network requests.

dist/tools/gzip-file-as-resource.js:141-141 
const response = await fetch(url, { signal: controller.signal });

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.

LOWMCP tool surface detectedST-MCP-DETECTED

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

dist/server/index.js:30-30 
const server = new McpServer({
dist/tools/echo.js:29-29 
server.registerTool(name, config, async (args) => {
dist/tools/get-annotated-message.js:39-39 
server.registerTool(name, config, async (args) => {
dist/tools/get-env.js:24-24 
server.registerTool(name, config, async (args) => {
dist/tools/get-resource-links.js:37-37 
server.registerTool(name, config, async (args) => {
dist/tools/get-resource-reference.js:43-43 
server.registerTool(name, config, async (args) => {
dist/tools/get-roots-list.js:38-38 
server.registerTool(name, config, async (args, extra) => {
dist/tools/get-structured-content.js:43-43 
server.registerTool(name, config, async (args) => {
dist/tools/get-sum.js:34-34 
server.registerTool(name, config, async (args) => {
dist/tools/get-tiny-image.js:28-28 
server.registerTool(name, config, async (args) => {
dist/tools/gzip-file-as-resource.js:54-54 
server.registerTool(name, config, async (args) => {
dist/tools/toggle-simulated-logging.js:30-30 
server.registerTool(name, config, async (_args, extra) => {
dist/tools/toggle-subscriber-updates.js:33-33 
server.registerTool(name, config, async (_args, extra) => {
dist/tools/trigger-elicitation-request-async.js:41-41 
server.registerTool(name, config, async (args, extra) => {
dist/tools/trigger-elicitation-request.js:39-39 
server.registerTool(name, config, async (args, extra) => {
dist/tools/trigger-long-running-operation.js:38-38 
server.registerTool(name, config, async (args, extra) => {
dist/tools/trigger-sampling-request-async.js:48-48 
server.registerTool(name, config, async (args, extra) => {
dist/tools/trigger-sampling-request.js:43-43 
server.registerTool(name, config, async (args, extra) => {
dist/tools/trigger-url-elicitation.js:85-85 
server.registerTool(name, config, async (args, extra) => {

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

Fix: Review the declared MCP tools and their permissions.

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 →