CFFBRW — AI Workflow Compiler for Cloudflare Edge
@shizlie
About CFFBRW — AI Workflow Compiler for Cloudflare Edge
AI-powered workflow compiler for Cloudflare edge. Compile automation from prose via MCP, run forever without AI tokens. 14 tools, 4 resources.
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"cffbrw": {
"type": "url",
"url": "https://api.cffbrw.com/mcp",
"headers": {
"Authorization": "Bearer <YOUR_API_KEY>",
"Accept": "application/json, text/event-stream"
}
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is CFFBRW — AI Workflow Compiler for Cloudflare Edge?
CFFBRW compiles automation written in plain English markdown into a deterministic execution plan and runs it on Cloudflare’s edge. It requires no AI tokens at runtime and is self-healing. It is aimed at developers who want long-running, reliable workflows without ongoing AI costs.
How to use CFFBRW — AI Workflow Compiler for Cloudflare Edge?
Obtain an API key at cffbrw.com/api-keys, add the server configuration to your .mcp.json file, then run the “introduce” prompt to learn the tools. From there you can compile, validate, deploy, and schedule workflows entirely through MCP.
Key features of CFFBRW — AI Workflow Compiler for Cloudflare Edge
- Compiles plain English markdown into execution plans
- Runs on Cloudflare’s edge with self-healing capability
- No AI tokens consumed at runtime
- 14 tools, 4 resources, 2 prompts included
- 11 step types: http_request, ai_call, transform, loop, etc.
- Connector catalog for 10+ services (Google, Slack, Notion, etc.)
Use cases of CFFBRW — AI Workflow Compiler for Cloudflare Edge
- Schedule recurring data transformations or API calls
- Orchestrate multi-step approval flows with human_approval steps
- Connect Google Drive, Slack, and Notion into one automation
- Deploy and monitor workflows directly from an MCP client
FAQ from CFFBRW — AI Workflow Compiler for Cloudflare Edge
How do I get an API key?
Visit cffbrw.com/api-keys to obtain a free API key for the server.
Does CFFBRW consume AI tokens at runtime?
No. AI tokens are only used during the compilation step; running workflows costs nothing in AI tokens.
What step types does CFFBRW support?
It supports 11 step types: http_request, ai_call, transform, conditional, loop, wait, human_approval, code, mcp_call, connector, and sub_workflow.
What connectors are available?
The connector catalog includes Google Drive, Sheets, Calendar, Gmail, Slack, Discord, Notion, SendGrid, Resend, and Webhook.
How do I start using the server?
Add the server config to your .mcp.json, get an API key, and run the “introduce” prompt to learn the tools. Then compile, validate, deploy, and schedule workflows via MCP.
More Reasoning MCP servers
End-to-End Agentic AI Automation Lab
MDalamin5This repository contains hands-on projects, code examples, and deployment workflows. Explore multi-agent systems, LangChain, LangGraph, AutoGen, CrewAI, RAG, MCP, automation with n8n, and scalable agent deployment using Docker, AWS, and BentoML.
Part 1. Real-Time LangGraph Agent with MCP Tool Execution
junfanz1This project demonstrates a decoupled real-time agent architecture that connects LangGraph agents to remote tools served by custom MCP (Modular Command Protocol) servers. The architecture enables a flexible and scalable multi-agent system where each tool can be hosted independent
IntelliNode Medical Use Cases
BarqawizMulti-Agent AI Orchestration Workshop
Task Planner MCP Server
CaptainCrouton89An MCP (Model Context Protocol) server that helps AI assistants (like Claude) break down complex tasks into manageable steps, track progress, and manage a hierarchical task list.
MCP Servers
junfanz1This project demonstrates a decoupled real-time agent architecture that connects LangGraph agents to remote tools served by custom MCP (Modular Command Protocol) servers. The architecture enables a flexible and scalable multi-agent system where each tool can be hosted independent
Comments