browserbase-mcp

browserbase-mcp is a skill for Claude Code, Codex from Friz-zy/ai-capability-registry. It costs 33 tokens per session (473 once invoked), scanned A, original, MIT.

A connection that lets an agent control a web browser, collect information from websites, and capture screenshots through Browserbase and Stagehand.

In plain words
What is it for?
Use it for browser automation, website data extraction, and screenshot capture.
Why use it?
It removes the need to handle browser interactions and web-page data collection manually.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for browser automation, website data extraction, and screenshot capture.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/friz-zy/ai-capability-registry/browserbase
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.

Any agent
npx skills add Friz-zy/ai-capability-registry --skill browserbase
Clone the repo
git clone --depth 1 https://github.com/Friz-zy/ai-capability-registry

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.

agentmods badge for browserbase-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/friz-zy/ai-capability-registry/browserbase.svg)](https://agentmods.dev/skills/friz-zy/ai-capability-registry/browserbase)
Your own site
<a href="https://agentmods.dev/skills/friz-zy/ai-capability-registry/browserbase"><img src="https://agentmods.dev/badge/skills/friz-zy/ai-capability-registry/browserbase.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 473 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 52
    Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.
    Fix: Pin the image: image:tag or image@sha256:abc123
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.00473
Opus 5 $0.00016 $0.00236
Sonnet 5 $0.00007 $0.00095
Haiku 4.5 $0.00003 $0.00047

Measured 4d ago against content hash ecf9ce2eecbd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

browserbase-mcp scanned grade A with 0 findings 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

mcp/servers/browserbase/SKILL.md · 69 lines

What it actually says

Browserbase

Allow LLMs to control a browser with Browserbase and Stagehand for AI-powered web automation, intelligent data extraction, and screenshot capture.

When to use

  • Use Browserbase only when the task directly involves the relevant service, SaaS product, platform, or technology.

Connection

Docker stdio

{
  "command": "docker",
  "args": [
    "run",
    "--rm",
    "-i",
    "-e",
    "BROWSERBASE_API_KEY",
    "-e",
    "BROWSERBASE_PROJECT_ID",
    "-e",
    "GEMINI_API_KEY",
    "mcp/browserbase"
  ]
}

MCP instructions

  • Use the MCP tools only for the user-requested service workflow and prefer read-only operations by default.
  • Confirm the target account, workspace, project, repository, or dataset before actions that can read private data or mutate remote state.
  • This server requires authorization or environment-provided credentials; ask the user before connecting or requesting access.

Docker launch notes

  • Launch through Docker stdio with docker run --rm -i -e BROWSERBASE_API_KEY -e BROWSERBASE_PROJECT_ID -e GEMINI_API_KEY mcp/browserbase.
  • Confirm required environment variables before launch: BROWSERBASE_API_KEY, BROWSERBASE_PROJECT_ID, GEMINI_API_KEY.

References

Security policy

  • Trust: reviewed
  • Default mode: manual_review
  • Permission default: manual_review
  • Authentication: Unspecified in source metadata
  • Warning: Default mode is manual_review.
  • Warning: Permission default is manual_review.
  • Required posture: Complete manual review before connecting or invoking tools; this generated record does not grant approval.
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 4d ago First seen · 69 lines · 33 tokens per session scan A ecf9ce2eecbd

Subscribe to this mod's changes

browserbase-mcp is a skill published in the GitHub repository Friz-zy/ai-capability-registry (9 stars, last pushed 8d ago), licensed MIT. It adds 33 tokens to every session and 473 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.