Is Puppeteer MCP server safe?

What Puppeteer MCP server does

This server provides browser automation through Puppeteer: an MCP client can navigate to any URL, take screenshots, click, hover, fill forms, select options and execute JavaScript in the page. The npm author field lists Anthropic, PBC, and npm marks the package as no longer supported. It launches and controls a local browser; launch options come from PUPPETEER_LAUNCH_OPTIONS or from the navigate tool's arguments. Before installing, keep allowDangerous / ALLOW_DANGEROUS at its default of false, which rejects launch flags such as --no-sandbox and --disable-web-security.

No malicious indicators - review capabilities before installing

Notable — review in context (a capability is not a malicious indicator):

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.

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

@modelcontextprotocol/server-puppeteer 2025.5.12

npm package · npm:@modelcontextprotocol/server-puppeteer

LOW

/ 100 risk score

Snapshot · scanned Nov 13, 2026 · @modelcontextprotocol/server-puppeteer@2025.5.12 · 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 Puppeteer MCP server's authors. Report a false positive.

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

install time executionmcp tools detected

Behavioral traits

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

Tool surface

Tool Usage

Supply-chain provenance risk

General Protections / Supply Chain

Findings (2)

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:18

"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.

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

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

dist/index.js:367

const server = new Server({

dist/index.js:417

server.setRequestHandler(ListToolsRequestSchema, async () => ({

dist/index.js:420

server.setRequestHandler(CallToolRequestSchema, async (request) => handleToolCall(request.params.name, request.params.arguments ?? {}));

dist/index.js:422

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 Puppeteer MCP server.

Install Script lab

Maintain Puppeteer 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 plugin Or 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 →