Is Ref Tools MCP server safe?

ref-tools-mcp is an AI npm_package analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators, though 2 risky constructs are reported for review. It can: mcp tools detected and network egress — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).

ref-tools-mcp 3.0.3

npm_package · https://github.com/ref-tools/ref-tools-mcp

LOW

/ 100 malicious-risk

Snapshot · scanned Jun 20, 2026 · ref-tools-mcp@3.0.3 · engine 0.18.0 / ruleset 19

No malicious indicators - review capabilities before installing

Notable — review in context (capabilities are not malware):

Node.js network egress
MCP tool surface detected

No malicious indicators found by static analysis.

Capabilities — what this component can do (not a risk score):

mcp tools detectednetwork egress

Findings (2)

MEDIUMNode.js network egressST-NET-NODE

The component makes outbound network requests.

index.ts:19-19

import axios from 'axios'

index.ts:279-279

const response = await axios.get(url, {

index.ts:312-312

if (axios.isAxiosError(error) && error.response?.status === 401) {

index.ts:328-328

text: `Error during documentation search: ${axios.isAxiosError(error) ? error.message : (error as Error).message}`,

index.ts:351-351

const response = await axios.get(readUrl, {

index.ts:380-380

if (axios.isAxiosError(error) && error.response?.status === 401) {

index.ts:396-396

text: `Error reading URL: ${axios.isAxiosError(error) ? error.message : (error as Error).message}`,

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.

manifest.json:1-1

server.json:1-1

index.ts:101-101

const server = new Server(

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

Or get notified if this component's risk changes:

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