Skip to main content
SkillTotal

Is CodeScene MCP server safe?

What CodeScene MCP server does

The CodeScene MCP Server exposes CodeScene's Code Health analysis as local tools, so AI assistants can get code quality, maintainability and technical-debt insights on your codebase. It is published in the codescene-oss/codescene-mcp-server repository and on npm as @codescene/codehealth-mcp. It runs locally against your code and fetches hotspots and technical-debt goals from your CodeScene account over REST, using CS_ACCESS_TOKEN or a login; it also checks for new versions. Before installing, decide whether you need the account-connected feature set or the standalone option, and set CS_DISABLE_VERSION_CHECK if you do not want the version check.

Some risk - review before installing
Notable — review in context (a capability is not a malicious indicator):
  • Possible command injection (exec with dynamic command)
  • Sensitive path / secret-location reference
  • Node.js shell/command execution

What to do: Read the findings below before installing: each one opens the exact line of code it was found on.

CodeScene MCP server is an MCP server analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators, though 2 risky constructs are reported for review. Its Rust and Ruby code was not checked for shell, network or file access, so this result is partial. It can: filesystem read, mcp tools detected, network egress and shell execution — capabilities are what the code can do, not a verdict on intent. Risk score 40/100 (medium).

codescene-mcp-server

GitHub repository, read as an AI component · https://github.com/codescene-oss/codescene-mcp-server
MEDIUM
40
/ 100 risk score
Snapshot · scanned Nov 13, 2026 · codescene-mcp-server@6ceb808 · 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 CodeScene MCP server's authors. Report a false positive.

Capabilities — what this component can do (not a risk score):
filesystem readmcp tools detectednetwork egressshell 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
Network egress
Interaction & Communication / Direct Communication
Embedded credential access
Tool Execution Context / Agent Service Identity

Findings (6)

HIGHPossible command injection (exec with dynamic command)ST-CMDI-NODE

The code builds an OS command out of values that can change at runtime, then runs it through a shell.

execSync(`node scripts/download-binary.js ${binaryTarget}`, {
execSync(`npx @vscode/vsce package --target ${vsTarget}`, {

Why it matters: If any of those values come from untrusted input, an attacker can run their own commands on the machine.

Fix: Use execFile/spawn with an argument array instead of exec; never build a shell command string from external input.

CapabilityMCP server launches a host commandnot scored · severity highST-MCP-SERVER-EXEC

An MCP server entry launches a command on your host.

"command": "${__dirname}/bin/darwin/cs-mcp",

Why it matters: Trusting the manifest means running that binary — verify what it is and where it comes from.

Fix: Verify the launched command and its source before trusting this MCP server configuration.

HIGHSensitive path / secret-location referenceST-SENS-PATH

The component references credential locations like ~/.ssh or .aws/credentials.

let config = ssh_home_dir()?.join(".ssh/config");

Why it matters: Touching secret locations is a common first step before stealing them — confirm why it's needed.

Fix: Verify why the component references credential locations; reading these is a common precursor to secret exfiltration.

CapabilityNode.js shell/command executionnot scored · severity highST-SHELL-NODE

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

import { execFileSync } from "node:child_process";
import { spawn } from "node:child_process";
const child = spawn(binaryPath, args, {
import { execFileSync } from 'node:child_process';
import { execSync } from 'node:child_process';
execSync(`node scripts/download-binary.js ${binaryTarget}`, {
execSync(`npx @vscode/vsce package --target ${vsTarget}`, {
import { execFile } from 'child_process';

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.

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

The component makes outbound network requests.

import https from "node:https";
import http from "node:http";
import https from 'node:https';
import http from 'node:http';

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.

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 CodeScene 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.

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 →