SkillTotal

Is Adeu MCP server safe?

No malicious indicators - review capabilities before installing
Notable — review in context (capabilities are not malware):
  • Node.js shell/command execution
  • Node.js filesystem write/delete
  • 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.

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

@adeu/mcp-server 3.0.7

npm_package · npm:@adeu/mcp-server
LOW
0
/ 100 risk score
Snapshot · scanned Oct 8, 2026 · @adeu/mcp-server@3.0.7 · engine 0.56.4 / ruleset 62

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

Capabilities — what this component can do (not a risk score):
filesystem writemcp tools detectedshell execution

Behavioral traits

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

Tool surface
Tool Usage
Execution authority
Tool Access Control / Direct Tool Access
Filesystem reach
Tool Execution Context

Findings (3)

HIGHNode.js shell/command executionST-SHELL-NODE

The component can run operating-system commands or spawn processes.

import { execSync } from "node:child_process";
gitSha = execSync("git rev-parse --short HEAD", { encoding: "utf-8" }).trim();

Why it matters: Powerful and often legitimate — confirm the commands aren't built from untrusted input.

Fix: Confirm the command and its arguments are fully controlled and not derived from untrusted input; prefer execFile with an argument array.

MEDIUMNode.js filesystem write/deleteST-FS-NODE-WRITE

The component writes or deletes files on disk.

fs.writeFileSync(outPath, outBuf);
fs.writeFileSync(outPath, outBuf);
fs.writeFileSync(outPath, result.outBuffer);
fs.writeFileSync(outPath, result.out_bytes);
fs.writeFileSync(e.unverified_path, e.unverified_bytes);
fs.writeFileSync(outPath, outBuf);
fs.writeFileSync(outPath, outBuf);
fs.writeFileSync(outPath, result.outBuffer);
fs.writeFileSync(outPath, result.out_bytes);
fs.writeFileSync(e.unverified_path, e.unverified_bytes);

Why it matters: Usually legitimate, but worth confirming the paths can't be controlled by untrusted input.

Fix: Confirm which files are written/deleted and that paths cannot be influenced by untrusted input.

LOWMCP tool surface detectedST-MCP-DETECTED

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

var server = new McpServer({
server.registerTool(
server.registerTool(
server.registerTool(
server.registerTool(
server.registerTool(
const transport = new StdioServerTransport();
{"version":3,"sources":["../src/index.ts","../src/response-builders.ts","../src/shared.ts","../src/ledger.ts","../src/doc-cache.ts","../src/protocol-adapter.ts"],"sourcesContent":["import { McpServer } from \"@modelcontextprotocol/sdk/serve …
{"version":3,"sources":["../src/index.ts","../src/response-builders.ts","../src/shared.ts","../src/ledger.ts","../src/doc-cache.ts","../src/protocol-adapter.ts"],"sourcesContent":["import { McpServer } from \"@modelcontextprotocol/sdk/serve …
{"version":3,"sources":["../src/index.ts","../src/response-builders.ts","../src/shared.ts","../src/ledger.ts","../src/doc-cache.ts","../src/protocol-adapter.ts"],"sourcesContent":["import { McpServer } from \"@modelcontextprotocol/sdk/serve …
{"version":3,"sources":["../src/index.ts","../src/response-builders.ts","../src/shared.ts","../src/ledger.ts","../src/doc-cache.ts","../src/protocol-adapter.ts"],"sourcesContent":["import { McpServer } from \"@modelcontextprotocol/sdk/serve …
{"version":3,"sources":["../src/index.ts","../src/response-builders.ts","../src/shared.ts","../src/ledger.ts","../src/doc-cache.ts","../src/protocol-adapter.ts"],"sourcesContent":["import { McpServer } from \"@modelcontextprotocol/sdk/serve …
{"version":3,"sources":["../src/index.ts","../src/response-builders.ts","../src/shared.ts","../src/ledger.ts","../src/doc-cache.ts","../src/protocol-adapter.ts"],"sourcesContent":["import { McpServer } from \"@modelcontextprotocol/sdk/serve …
{"version":3,"sources":["../src/index.ts","../src/response-builders.ts","../src/shared.ts","../src/ledger.ts","../src/doc-cache.ts","../src/protocol-adapter.ts"],"sourcesContent":["import { McpServer } from \"@modelcontextprotocol/sdk/serve …
const server = new McpServer({
server.registerTool(
server.registerTool(
server.registerTool(
server.registerTool(
server.registerTool(
const transport = new StdioServerTransport();

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 Adeu MCP server.

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 →