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 barflotek/bellink-mcp --skill skillgit clone --depth 1 https://github.com/barflotek/bellink-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/barflotek/bellink-mcp/skill)<a href="https://agentmods.dev/skills/barflotek/bellink-mcp/skill"><img src="https://agentmods.dev/badge/skills/barflotek/bellink-mcp/skill/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/barflotek/bellink-mcp/skill"><img src="https://agentmods.dev/badge/skills/barflotek/bellink-mcp/skill.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 | $0.00044 | $0.00832 |
| Opus 5 | $0.00022 | $0.00416 |
| Sonnet 5 | $0.00009 | $0.00166 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
bellink 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 8d 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.
Bellink — AI Gateway to Business Tools
Connect your AI assistant to 30+ business tools through one MCP server.
Setup (30 seconds)
- Sign up at https://app.bellink.io (free Starter plan, no credit card)
- Connect your apps (Gmail, Mindbody, Meta, etc.)
- Copy your Bellink URL from the dashboard
- Tell your bot: "add MCP server bellink: [paste URL]"
That's it. Your AI now has access to all your connected apps.
Environment variable
The only credential needed is BELLINK_URL — the full MCP endpoint URL you copy from your Bellink dashboard. It contains your authentication key as a query parameter. No separate API key or Bearer token needed.
Example: BELLINK_URL=https://app.bellink.io/api/mcp/server?key=your_key_here
What you can do
Once connected, just ask:
- "What's on my schedule today?" → pulls from Calendar + Mindbody
- "Send a reply to that email from John" → reads and sends via Gmail
- "What's my revenue this month?" → pulls from Mindbody or Stripe
- "Book Sarah for tomorrow's 9am class" → books directly in Mindbody
- "Create a spreadsheet with this month's sales" → writes to Google Sheets
- "Show me my Meta ad performance" → pulls campaign insights
- "Create a Linear issue for this bug" → creates in your project
Supported apps
Gmail, Google Calendar, Google Sheets, Google Docs, Google Drive, Google Analytics, Google Forms, Mindbody, Meta (Facebook + Instagram + Ads), Linear, Airtable, Notion, Stripe, Slack, GitHub, Figma, Allegro, QuickBooks, Twilio, Webflow, WordPress, Typeform, Calendly, Beehiiv, Buttondown, n8n, Zoom, Shopify, WhatsApp, Outlook
MCP config (alternative setup)
If you prefer manual config, add to your mcporter.json:
{
"mcpServers": {
"bellink": {
"baseUrl": "BELLINK_URL",
"transport": "sse"
}
}
}
Replace BELLINK_URL with the URL from your Bellink dashboard (includes your key).
npm package
Also available as an npm package for Claude Desktop, Cursor, and other stdio MCP clients:
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.
- 8d ago First seen · 94 lines · 44 tokens per session scan A eb87ca69db21
bellink is a skill published in the GitHub repository barflotek/bellink-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 44 tokens to every session and 832 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 2026-08-31.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
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.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.