Borrowing it
Nothing to install: this file belongs to nbiish/betterbrowsermcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nbiish/betterbrowsermcp/main/.agents/skills/bbmcp/SKILL.mdgit clone --depth 1 https://github.com/nbiish/betterbrowsermcpWrote 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.
[](https://agentmods.dev/skills/nbiish/betterbrowsermcp/bbmcp)<a href="https://agentmods.dev/skills/nbiish/betterbrowsermcp/bbmcp"><img src="https://agentmods.dev/badge/skills/nbiish/betterbrowsermcp/bbmcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nbiish/betterbrowsermcp/bbmcp"><img src="https://agentmods.dev/badge/skills/nbiish/betterbrowsermcp/bbmcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00113 | $0.02308 |
| Opus 5.5 | $0.00045 | $0.00923 |
| Sonnet 5.5 | $0.00023 | $0.00462 |
| Haiku 4.5 | $0.00011 | $0.00231 |
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 2mo 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):** 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.jsOne process, any number of agents. WS at/ws/<agentId>, MCP at/mcp/<agentId>, health atGET /. - Single-agent (one process per agent, legacy):
BROWSER_MCP_AGENT_ID=<id> BROWSER_MCP_PORT=9109 npx @nbiish/betterbrowsermcp@latestThe extension auto-configureshermesanddefaultendpoints 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) REQUIRESBROWSER_MCP_AUTH_TOKEN— both transports fail closed without it.
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.
- 2mo ago First seen · 184 lines · 113 tokens per session scan A fcf947b65326
bbmcp is a skill published in the GitHub repository nbiish/betterbrowsermcp (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 113 tokens to every session and 2,308 once invoked, about $0.0005 per session on Opus 5.5. 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.
bbmcp compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bbmcpnbiish/betterbrowsermcp | Skill | 1 | 2mo ago | Apache-2.0 | A | 113 | Claude Code, Codex |
| interactive-loginyc-software/qm | Skill | 16k | today | MIT | A | 46 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 13d ago | MIT | A | 52 | Claude Code, Codex |
| azure-messaging-webpubsub-javamicrosoft/skills | Skill | 3.2k | today | MIT | A | 43 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | today | MIT | A | 68 | Claude Code, Codex |
| open-design-browsercompozy/compozy | Skill | 2.9k | today | MIT | A | 56 | Claude Code, Codex |
| southwestborski/travel-hacking-toolkit | Skill | 926 | today | MIT | A | 40 | Claude Code |