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.
npx skills add VibeTechnologies/vibe-mcp --skill setupgit clone --depth 1 https://github.com/VibeTechnologies/vibe-mcpWrote 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/vibetechnologies/vibe-mcp/setup)<a href="https://agentmods.dev/skills/vibetechnologies/vibe-mcp/setup"><img src="https://agentmods.dev/badge/skills/vibetechnologies/vibe-mcp/setup/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/vibetechnologies/vibe-mcp/setup"><img src="https://agentmods.dev/badge/skills/vibetechnologies/vibe-mcp/setup.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 | $0.00063 | $0.01014 |
| Opus 5.5 | $0.00025 | $0.00406 |
| Sonnet 5.5 | $0.00013 | $0.00203 |
| Haiku 4.5 | $0.00006 | $0.00101 |
Grade A, and why
setup 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up Vibe Browser
The vibe MCP server is only a relay. It has no browser of its own: it forwards
tool calls to the Vibe Chrome extension running in the user's real Chrome. Until
that extension is installed and connected, every browser tool will fail.
Work through the steps below in order. Stop as soon as Step 4 verifies.
Step 1 — Install the Vibe extension
Ask the user to install the extension in Chrome, Brave, or any Chromium browser:
Chrome Web Store (recommended) https://chromewebstore.google.com/detail/vibe-ai-browser-co-pilot/djodpgokbmobeclicaicnnidccoinado
Click Add to Chrome. The Vibe icon appears in the toolbar.
Developer version (if the store is blocked)
- Download https://github.com/VibeTechnologies/VibeWebAgent/releases/latest/download/vibe-ai-copilot-latest.zip
- Extract it to a permanent folder (deleting it later uninstalls the extension).
- Open
chrome://extensions, turn on Developer mode. - Click Load unpacked and select the extracted folder.
Step 2 — Turn on external control
The extension refuses external control until the user opts in:
- Click the Vibe icon in the Chrome toolbar.
- Open Settings.
- Enable MCP External Control.
- The status indicator should read Connected.
Chrome must stay open. Closing the browser drops the connection.
Step 3 — Choose local or remote
Local (default). Claude Code and Chrome are on the same machine. Nothing more to configure — the server auto-spawns a localhost relay daemon and the extension finds it.
Remote. Chrome runs on a different machine from Claude Code (for example Claude Code on a dev box, Chrome on the user's laptop). This needs no inbound port:
- In the extension Settings, switch to Remote mode.
- Copy the remote UUID it shows.
- Pass it to the server, either as an argument (
--remote <uuid>) or via theVIBE_REMOTE_URLenvironment variable.
The remote UUID is the only bearer credential for that browser. Treat it like a password. Never paste it into a file the user tracks in git, and never print it back in full. If it leaks, regenerate it in extension Settings.
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.
- 1mo ago First seen · 94 lines · 63 tokens per session scan A f065c8357518
setup is a skill published in the GitHub repository VibeTechnologies/vibe-mcp (3 stars, last pushed 24d ago), licensed Apache-2.0. It adds 63 tokens to every session and 1,014 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
x-use-inbox
Read X direct messages, triage inbox and request folders, send contextual reviewed messages, and inspect notifications with x-use. Use for unread chats, conversation search or replies, individual DMs, and All or Mentions notifications; use x-use-engage for public-post engagement and profile outreach research.
x-use
Install, register, and configure x-use, the browser-native MCP server for X (Twitter) automation that needs no X API key. Covers pip install, MCP client registration for Claude Desktop, Claude Code, Codex, Cursor and Windsurf, cookie-based account setup, keywords, and persona. Use when the user wants to set up x-use…
Agent Browser Automation
Fast Rust-based headless browser automation CLI with Node.js fallback for AI agents, featuring navigation, clicking, typing, snapshots, and structured commands optimized for agent workflows.
x-use-engage
Research X posts or profiles and prepare persona-voice public replies or individual profile outreach drafts with x-use. Use for public engagement, personalized outreach research, or local lead and campaign preparation; use x-use-inbox for incoming messages, conversation replies, and notifications.
x-use-review
Daily digest for an x-use account covering health, metrics, pending drafts, and queued work in one pass, then approve/reject/process per the user's direction. Use for "how is my account doing", daily check-ins, or before any batch of approvals.
x-use-threads
Read visible X post/reply threads and prepare or resume multi-post drafts with x-use. Use when the user asks to read, compose, review, or continue a public thread on X; use x-use-inbox for direct-message conversations.