mcp-server-puppeteer

A thin wrapper/extension intended to expose an existing MCP server implementation for Puppeteer (browser automation) within a Zed editor context, delegating to the upstream @modelcontextprotocol/server-puppeteer MCP server.

Evaluated Mar 30, 2026 (22d ago)
Repo ↗ Automation mcp puppeteer browser-automation zed-extension tooling agents
⚙ Agent Friendliness
29
/ 100
Can an agent use this?
🔒 Security
30
/ 100
Is it safe for agents?
⚡ Reliability
30
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
40
Documentation
15
Error Messages
0
Auth Simplicity
90
Rate Limits
0

🔒 Security

TLS Enforcement
60
Auth Strength
20
Scope Granularity
10
Dep. Hygiene
30
Secret Handling
30

Only minimal information is available. Browser automation capabilities can be risky (data exposure, malicious page execution). No explicit auth/scopes, rate limiting, or secret-handling guidance is provided in the supplied content.

⚡ Reliability

Uptime/SLA
0
Version Stability
50
Breaking Changes
50
Error Recovery
20
AF Security Reliability

Use Cases

  • • Run Puppeteer-controlled browser automation via an MCP-capable agent workflow
  • • Automate web page interactions (navigation, clicks, scraping-like extraction) through agent tool calls
  • • Integrate Puppeteer MCP capabilities into the Zed editor environment

Not For

  • • Security-sensitive browsing or handling of highly confidential data without additional safeguards
  • • Running untrusted automation flows without isolation/sandboxing
  • • Production deployments where the wrapper’s configuration and behavior are not fully documented

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

OAuth: No Scopes: No

No authentication details were provided in the supplied README/repo metadata; behavior likely depends on the upstream MCP server implementation.

Pricing

Free tier: No
Requires CC: No

No pricing information provided.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • ⚠ Browser automation actions are inherently stateful (page/session/DOM), so retries can produce different outcomes if the page state changes
  • ⚠ Tool timeouts/hanging navigation can cause agent stalls if not handled
  • ⚠ Running arbitrary pages may involve additional security/sandboxing requirements not described here

Alternatives

Use @modelcontextprotocol/server-puppeteer directly (Node.js MCP server) Use Puppeteer directly from your own service (without MCP) If available for your stack, use other MCP-to-browser/automation providers

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for mcp-server-puppeteer.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo
API endpoint ↗ Agent guide ↗ Report inaccuracy

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
♥
Community Powered