Install
$ agentstack add mcp-getcatalystiq-mcp-servers ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
MCP Servers
[](https://opensource.org/licenses/MIT) [](https://www.typescriptlang.org/) [](https://workers.cloudflare.com/) [](https://modelcontextprotocol.io)
A collection of Model Context Protocol (MCP) servers built on Cloudflare Workers. These servers enable Claude.ai and other MCP clients to interact with various APIs and services.
Available Servers
| Server | Description | Authentication | |--------|-------------|----------------| | [ElevenLabs](./elevenlabs) | Text-to-speech using ElevenLabs API | Password | | [Firecrawl](./firecrawl) | Web scraping and crawling | Password | | [Google Workspace](./google-workspace) | Gmail, Drive, Calendar, Docs, Sheets, Tasks | OAuth 2.0 | | [Kit](./kit) | ConvertKit email marketing platform | OAuth 2.0 | | [Nano Banana](./nano-banana) | Image generation using Gemini API | Password | | [Runware](./runware) | AI video generation | Password |
Architecture
All servers share a common architecture:
- Cloudflare Workers: Serverless deployment with global edge distribution
- Durable Objects: Session state persistence with SQLite storage
- KV Namespace: OAuth state management
- R2 Buckets: Media file storage (where applicable)
┌─────────────┐ ┌─────────────────────┐
│ Claude.ai │ ◄─── MCP ────► │ MCP Server │
│ (or other │ │ (CF Workers) │
│ MCP client)│ └──────────┬──────────┘
└─────────────┘ │
▼
┌─────────────────────┐
│ External API │
│ (ElevenLabs, │
│ Google, etc.) │
└─────────────────────┘
Getting Started
Each server has its own setup instructions. Generally:
- Navigate to the server directory
- Install dependencies:
npm install - Create KV namespace:
npm run create-kv - Update
wrangler.jsoncwith your KV namespace ID - Configure secrets (API keys, passwords)
- Deploy:
npm run deploy
See individual server READMEs for detailed instructions.
Local Development
Each server can be run locally for testing:
cd
npm run dev
Use MCP Inspector to test:
npx @modelcontextprotocol/inspector@latest
Security
- API keys are stored as Cloudflare secrets, never exposed to clients
- OAuth tokens stored securely in Durable Objects
- All communication over HTTPS
- Password-protected servers use encrypted cookies
Contributing
Contributions are welcome! Please ensure any new servers follow the existing patterns for authentication, error handling, and documentation.
License
MIT - see [LICENSE](./LICENSE) for details.
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: getcatalystiq
- Source: getcatalystiq/mcp-servers
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.