Cloudflare Workers AI MCP Server
Cloudflare Workers AI MCP Server
AI 에이전트가 Cloudflare Workers AI에 접근할 수 있게 해주는 Model Context Protocol (MCP) 서버 — 넉넉한 무료 티어를 제공하는 서버리스 LLM 추론, 임베딩, 이미지 생성 기능을 갖추고 있습니다.
도구
도구 | 설명 |
| 지원되는 채팅, 임베딩, 이미지 모델 나열 |
| LLM 채팅 완성 (Llama 3.3 70B, Llama 3.1 8B, Llama 4 Scout, Qwen Coder 32B, DeepSeek R1 Distill) |
| 텍스트 임베딩 (BGE small/base) |
| 이미지 생성 (Flux 1 Schnell) → base64 이미지 (PNG/JPEG) |
Related MCP server: Remote MCP Server Authless
설정
Workers AI 권한이 있는 Cloudflare API 토큰을 생성하세요: https://dash.cloudflare.com/profile/api-tokens
Account ID를 확인하세요 (Cloudflare 대시보드 오른쪽 사이드바 또는 대시보드 URL의
/accounts/{id}세그먼트)환경 변수를 내보내세요:
export CLOUDFLARE_ACCOUNT_ID="your-account-id"
export CLOUDFLARE_API_TOKEN="your-api-token"실행
npm install && npm run build
npm start # stdio MCP serverClaude Desktop
claude_desktop_config.json에 추가하세요:
{
"mcpServers": {
"cloudflare-workers-ai": {
"command": "node",
"args": ["/absolute/path/to/cloudflare-workers-ai-mcp/dist/index.js"],
"env": {
"CLOUDFLARE_ACCOUNT_ID": "your-account-id",
"CLOUDFLARE_API_TOKEN": "your-api-token"
}
}
}
}Cursor / VS Code / 기타 MCP 클라이언트
클라이언트를 동일한 명령어(node dist/index.js 및 두 개의 환경 변수)로 지정하세요.
OpenClaw
OpenClaw는 MCP 서버를 지원합니다 — 동일한 명령어를 MCP 구성에 추가하세요.
예시 프롬프트
"Cloudflare Workers AI에서 Llama 3.3 70B 모델을 사용하여 이 텍스트를 요약해 줘"
"눈보라 속 붉은 여우 이미지를 생성해 줘"
"유사도 검색을 위해 이 3개의 문장을 임베딩해 줘"
모델 (실시간 검증 완료)
채팅: POST /ai/v1/chat/completions (OpenAI 호환) · 임베딩 및 이미지: POST /ai/run/{model} (네이티브)
모델 — 채팅: @cf/meta/llama-3.3-70b-instruct-fp8-fast · @cf/meta/infire-llama-3.1-8b-instruct · @cf/meta/llama-4-scout-17b-16e-instruct · @cf/qwen/qwen2.5-coder-32b-instruct · @cf/deepseek-ai/deepseek-r1-distill-qwen-32b
임베딩: @cf/baai/bge-small-en-v1.5 · @cf/baai/bge-base-en-v1.5
이미지: @cf/black-forest-labs/flux-1-schnell
참고:
@cf/meta/llama-3.1-8b-instruct는 Cloudflare에 의해 폐기되었습니다 (2026-05-30) —@cf/meta/infire-llama-3.1-8b-instruct를 사용하세요.
테스트
npm test # unit tests (mocked fetch) + protocol test라이선스
MIT — puspoaditya가 제작했습니다.
Maintenance
Related MCP Servers
- AlicenseNot gradedqualityNot gradedmaintenanceEnables the creation and deployment of API-based MCP tools for Cursor Agent using Cloudflare Workers, streamlining development and integration of custom functionalities.4349
- FlicenseNot gradedqualityCmaintenanceA serverless MCP implementation on Cloudflare Workers that allows connecting AI models to custom tools without authentication requirements.
- FlicenseNot gradedqualityCmaintenanceA serverless MCP implementation on Cloudflare Workers that allows connecting AI models to custom tools without requiring authentication.
- FlicenseNot gradedqualityDmaintenanceEnables deployment of a remote MCP server on Cloudflare Workers without authentication. Supports custom tools and connections to Cloudflare AI Playground and Claude Desktop.
Related MCP Connectors
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Free public MCP for AI agents — 193 tools, 44 workflows. No API key.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/puspoaditya/cloudflare-workers-ai-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server