Cloudflare Workers AI MCP Server
Cloudflare Workers AI MCP Server
Servidor del Model Context Protocol (MCP) que da a los agentes de IA acceso a Cloudflare Workers AI — inferencia de LLM serverless, embeddings y generación de imágenes con un generoso nivel gratuito.
Herramientas
Tool | Descripción |
| Lista los modelos de chat, embeddings e imágenes compatibles |
| Completado de chat LLM (Llama 3.3 70B, Llama 3.1 8B, Llama 4 Scout, Qwen Coder 32B, DeepSeek R1 Distill) |
| Embeddings de texto (BGE small/base) |
| Generación de imágenes (Flux 1 Schnell) → imagen base64 (PNG/JPEG) |
Related MCP server: Remote MCP Server Authless
Configuración
Crea un token de API de Cloudflare con el permiso Workers AI: https://dash.cloudflare.com/profile/api-tokens
Obtén tu ID de cuenta (barra lateral derecha del panel de Cloudflare, o el segmento
/accounts/{id}de cualquier URL del panel)Exporta las variables de entorno:
export CLOUDFLARE_ACCOUNT_ID="your-account-id"
export CLOUDFLARE_API_TOKEN="your-api-token"Ejecución
npm install && npm run build
npm start # stdio MCP serverClaude Desktop
Añádelo a claude_desktop_config.json:
{
"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 / otros clientes MCP
Apunta el cliente al mismo comando (node dist/index.js con las dos variables de entorno).
OpenClaw
OpenClaw es compatible con servidores MCP — añade el mismo comando a su configuración de MCP.
Ejemplos de prompts
«Resume este texto usando el modelo Llama 3.3 70B en Cloudflare Workers AI»
«Genera una imagen de un zorro rojo en una tormenta de nieve»
«Genera los embeddings de estas 3 frases para una búsqueda de similitud»
Modelos (verificados en vivo)
Chat: POST /ai/v1/chat/completions (compatible con OpenAI) · Embeddings e imágenes: POST /ai/run/{model} (nativo)
Modelos — chat: @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
Embeddings: @cf/baai/bge-small-en-v1.5 · @cf/baai/bge-base-en-v1.5
Imágenes: @cf/black-forest-labs/flux-1-schnell
Nota:
@cf/meta/llama-3.1-8b-instructfue deprecado por Cloudflare (2026-05-30) — usa@cf/meta/infire-llama-3.1-8b-instruct.
Pruebas
npm test # unit tests (mocked fetch) + protocol testLicencia
MIT — desarrollado por puspoaditya.
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