bb-browser

bb-browser is a CLI (and optional Chrome extension/daemon) plus an MCP server wrapper that lets AI agents control a real Chrome browser session using the user’s existing login state. It can run browser automation (click/fill/eval/fetch/network/screenshot) and provides “site adapters” (one JS file per command) to perform site-specific actions like search, feeds, transcripts, summaries, and more, returning results as JSON when requested.

Evaluated Mar 29, 2026 (0d ago)
Repo ↗ Automation devtools automation api mcp browser-automation ai-agents cli chrome-extension cdp
⚙ Agent Friendliness
56
/ 100
Can an agent use this?
🔒 Security
36
/ 100
Is it safe for agents?
⚡ Reliability
29
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
65
Documentation
70
Error Messages
0
Auth Simplicity
85
Rate Limits
20

🔒 Security

TLS Enforcement
60
Auth Strength
35
Scope Granularity
10
Dep. Hygiene
55
Secret Handling
25

Security is primarily tied to the user’s existing authenticated browser session; there is no explicit scope/permission model beyond what the browser session permits. The daemon can bind to public interfaces (0.0.0.0) which increases exposure risk if not protected. The README does not describe how session secrets/cookies are stored, redacted from logs, or encrypted, nor does it document threat model controls for eval/injection capabilities.

⚡ Reliability

Uptime/SLA
0
Version Stability
45
Breaking Changes
40
Error Recovery
30
AF Security Reliability

Best When

You have a user-owned Chrome login session and need an agent to interact with complex, auth-gated web UIs and extract results into structured JSON.

Avoid When

You cannot securely handle user credentials/session state, need fine-grained permissioning beyond what the user browser already has, or require clear published rate-limit/error-contracts for reliable automation.

Use Cases

  • Agentic web research across many sites using existing authenticated sessions
  • Building chat/agent workflows that need interactive browser actions (search, navigation, scraping-like data extraction) without APIs
  • Retrieving authenticated content such as social feeds, watchlists, and transcripts
  • Generating structured outputs for downstream processing via --json and --jq

Not For

  • Use as a general-purpose headless web-scraping tool for arbitrary unauthenticated targets
  • Operations requiring strict compliance boundaries around automated access or sensitive personal data handling
  • Workloads that need strong idempotency/transactional guarantees (browser actions are stateful)

Interface

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

Authentication

Methods: Uses existing browser login state (cookies/session) MCP integration via CLI invocation (no OAuth described)
OAuth: No Scopes: No

Authentication is effectively whatever permissions the user’s logged-in Chrome session already has; bb-browser itself does not appear to introduce a separate OAuth flow or scope model in the provided README.

Pricing

Free tier: No
Requires CC: No

No pricing information provided in the supplied content.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Statefulness: actions depend on the user’s current browser session and UI state
  • Network/content variability: adapters may break when a site changes
  • SSO/2FA prompts can block automation until user re-authenticates
  • Running with --host 0.0.0.0 exposes the daemon to the network; remote access should be tightly controlled

Alternatives

Full Evaluation Report

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

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

Scores are editorial opinions as of 2026-03-29.

5365
Packages Evaluated
21038
Need Evaluation
586
Need Re-evaluation
Community Powered