mcp-pool
A curated collection of Model Context Protocol (MCP) servers for popular SaaS platforms — Stripe, Sentry, Notion, Linear, Datadog, Vercel, PagerDuty, HubSpot, Intercom, Shopify, Google Workspace
Documentation
MCP Pool
Documentation | npm | GitHub
A curated collection of Model Context Protocol (MCP) servers that give AI assistants direct access to popular SaaS APIs — no dashboard switching required.
MCP Pool bridges the gap between AI chat interfaces and the business tools teams rely on daily. Ask questions in natural language, get real answers backed by live data.
Packages
| Package | Description | Version |
|---|---|---|
| **@vineethnkrishnan/stripe-mcp** | Stripe — payments, customers, subscriptions, invoices |  |
| **@vineethnkrishnan/sentry-mcp** | Sentry — issues, events, stack traces. Self-hosted support. |  |
| **@vineethnkrishnan/notion-mcp** | Notion — pages, databases, search, content |  |
| **@vineethnkrishnan/linear-mcp** | Linear — issues, projects, teams (GraphQL) |  |
| **@vineethnkrishnan/datadog-mcp** | Datadog — monitors, metrics, events. Multi-site support. |  |
| **@vineethnkrishnan/vercel-mcp** | Vercel — deployments, projects, build logs |  |
| **@vineethnkrishnan/pagerduty-mcp** | PagerDuty — incidents, on-call, services. EU support. |  |
| **@vineethnkrishnan/hubspot-mcp** | HubSpot — contacts, deals, companies |  |
| **@vineethnkrishnan/intercom-mcp** | Intercom — conversations, contacts, support |  |
| **@vineethnkrishnan/shopify-mcp** | Shopify — orders, products, customers |  |
| **@vineethnkrishnan/google-workspace-mcp** | Google Workspace — Gmail, Calendar, Drive, Sheets |  |
Quick Start
Prerequisites
- Node.js >= 20 (see `.nvmrc`)
Use with Claude Desktop
Add to your `claude_desktop_config.json`:
{
"mcpServers": {
"stripe": {
"command": "npx",
"args": ["-y", "@vineethnkrishnan/stripe-mcp"],
"env": {
"STRIPE_SECRET_KEY": "sk_test_..."
}
}
}
}Then ask Claude things like:
- *"How many active subscriptions do we have?"*
- *"Why did the last payment for cus_123 fail?"*
- *"Show me our current Stripe balance."*
Development
# Clone and install
git clone https://github.com/vineethkrishnan/mcp-pool.git
cd mcp-pool
npm install| Command | Description |
|---|---|
| `npm run build` | Build all packages |
| `npm test` | Run tests across all packages |
| `npm run lint:check` | Lint with ESLint |
| `npm run format:check` | Check formatting with Prettier |
| `npm run docs:start` | Start docs dev server |
Project Structure
mcp-pool/
├── packages/
│ ├── oauth-core/ # Shared OAuth 2.0 infrastructure
│ │ └── src/
│ │ ├── strategies/ # OAuth & static token strategies
│ │ └── cli/ # Auth login/logout CLI helpers
│ └── / # MCP server (×11)
│ └── src/
│ ├── index.ts # MCP server entry point
│ ├── services/ # API SDK wrapper
│ ├── tools/ # MCP tool definitions
│ └── common/ # Shared types & utilities
├── docs/ # Docusaurus documentation site
├── .github/workflows/ # CI, quality, security, release
└── package.json # Monorepo root (npm workspaces)CI/CD
| Workflow | Trigger | What it does |
|---|---|---|
| CI | Push / PR to `main` | Lint, test (Node 20 + 22), build |
| Quality | Push / PR to `main` | Dead code detection (knip), code duplication (jscpd) |
| Security | Push / PR / weekly | CodeQL analysis, dependency review, Trivy scan |
| Commit Lint | PR | Validates PR title follows Conventional Commits |
| Release | Push to `main` | release-please versioning, npm publish, docs deploy |
Adding a New MCP Server
1. Create `packages//` following the structure in `packages/stripe/`
2. Implement a service layer (API wrapper) and tool layer (MCP interface)
3. Add tests — aim for full coverage
4. Add the package entry to `release-please-config.json` and `.release-please-manifest.json`
5. Add documentation pages in `docs/`
See CONTRIBUTING.md for full guidelines.
Commit Convention
All commits follow Conventional Commits:
feat(stripe): add refund support
fix(stripe): handle null customer email
docs: update installation guideEnforced via commitlint + husky pre-commit hooks.
Documentation
Visit the documentation site for detailed guides on each MCP server.
Roadmap
See the roadmap for planned features and upcoming milestones:
- **v0.2.0** — Write operations, SSE transport, streaming responses
- **v0.3.0** — Webhooks, multi-account, expanded API coverage, new servers
License
MIT — Vineeth Krishnan
Frequently asked questions
What is mcp-pool?
mcp-pool is A curated collection of Model Context Protocol (MCP) servers for popular SaaS platforms — Stripe, Sentry, Notion, Linear, Datadog, Vercel, PagerDuty, HubSpot, Intercom, Shopify, Google Workspace
How do I install mcp-pool?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is mcp-pool open source?
Yes — it is hosted on GitHub at https://github.com/vineethkrishnan/mcp-pool and has 1 stars.
Related MCP tools
The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.
MCP server that enables AI assistants to interact with Google Gemini CLI, leveraging Gemini's massive token window for large file analysis and codebase understanding
Universal AI context generator. Saves thousands of tokens per conversation in Claude Code, Cursor, Copilot, Codex, and more.
A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.
Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI
Unity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP