A skill for connecting an AI agent to the user's logged-in Chrome browser through Better Browser MCP, while keeping each agent's tabs separate.

Attaching to the browser hub, opening and managing the agent's tabs, and working in tabs the agent owns or the user explicitly assigns.

It provides controlled browser access without mixing the agent's tabs with other agents' or the user's tabs.

bbmcp — Skill for Claude Code and Codex by nbiish: A skill for connecting an AI agent to the…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add skills/nbiish/betterbrowsermcp/bbmcp

Any agent

npx skills add nbiish/betterbrowsermcp --skill bbmcp

Clone the repo

git clone --depth 1 https://github.com/nbiish/betterbrowsermcp

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nbiish/betterbrowsermcp/bbmcp.svg)](https://agentmods.dev/skills/nbiish/betterbrowsermcp/bbmcp)

Your own site

<a href="https://agentmods.dev/skills/nbiish/betterbrowsermcp/bbmcp"><img src="https://agentmods.dev/badge/skills/nbiish/betterbrowsermcp/bbmcp.svg" alt="Measured on agentmods" height="20"></a>

Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,308 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00113	$0.02308
Opus 5	$0.00056	$0.01154
Sonnet 5	$0.00023	$0.00462
Haiku 4.5	$0.00011	$0.00231

Measured 4d ago against content hash fcf947b65326, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bbmcp scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Generic Streamable HTTP (curl smoke test):**

.agents/skills/bbmcp/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

bbmcp — drive the user's real browser as your own agent

One local hub process serves many agents. Each agent gets its own isolated context, its own tabs, and its own MCP endpoint. You never touch another agent's tabs, and the user never touches yours — unless they explicitly bind a tab to you in the extension popup (explicit consent).

Quickstart (zero config, zero user steps)

# 1. Attach — ALL arguments optional. Discovers/reuses the hub on ports
#    9223-9237 (or starts one on a free port), claims your agentId
#    (--agent, $BBMCP_AGENT_ID, or auto-generated), verifies your
#    endpoint, and prints ready-to-paste MCP config:
node <path-to-betterbrowsermcp>/scripts/bbmcp-connect.mjs --agent my-agent

# 2. NOTHING for the user to do. The extension auto-attaches to every
#    registered agent within ~30s. Only bind-their-tab remains a user
#    action — that consent gate is by design.

# 3. Wire your harness with the printed JSON (see "Harness wiring" below),
#    then call tools: browser_open_tab is your first tab.

1. The server

Hub (recommended, multi-agent): BROWSER_MCP_HUB=true BROWSER_MCP_PORT=9223 node <repo>/dist/index.js One process, any number of agents. WS at /ws/<agentId>, MCP at /mcp/<agentId>, health at GET /.
Single-agent (one process per agent, legacy): BROWSER_MCP_AGENT_ID=<id> BROWSER_MCP_PORT=9109 npx @nbiish/betterbrowsermcp@latest The extension auto-configures hermes and default endpoints on port 9109 on first install — use 9109 to match.
Build from source first if dist/ is missing: npm run build.
Port collisions hard-fail (never silently kills the other process). Never kill another agent's instance. The connect script avoids the problem entirely: it reuses an existing hub in 9223-9237 or starts on the first free port there — you never need to pick a port.
Loopback binds need no auth. Non-loopback (BROWSER_MCP_BIND=0.0.0.0) REQUIRES BROWSER_MCP_AUTH_TOKEN — both transports fail closed without it.

Read the full file on GitHub · 184 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

4d ago First seen · 184 lines · 113 tokens per session scan A fcf947b65326

Subscribe to this mod's changes

bbmcp is a skill published in the GitHub repository nbiish/betterbrowsermcp (0 stars, last pushed 5d ago), licensed Apache-2.0. It adds 113 tokens to every session and 2,308 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Browser automation

use-agent-browser-for-airi

Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…

moeru-ai/airi · 87 tokens

opencli-sitemap-author

Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.

jackwener/OpenCLI · 67 tokens

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

every-app/open-seo · 35 tokens

interactive-login

How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.

yc-software/qm · 46 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

google-safe-browsing

Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…

davidondrej/skills · 105 tokens

bbmcp