RP Engine
YAML-native agent workflow execution engine, written in Rust
What is RP Engine?
RP Engine is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to yaml-native agent workflow execution engine, written in rust
YAML-native agent workflow execution engine, written in Rust
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- YAML-native agent workflow execution engine, written in Rust
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx rp-engineConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use RP Engine
RP Engine (riceprompt-engine) is a YAML-native agent workflow execution engine written in Rust that lets you define multi-step AI pipelines declaratively. It supports multiple LLM providers — OpenAI, Anthropic, Gemini, DeepSeek, and any OpenAI-compatible endpoint — and offers built-in node types for generation, data transformation, multi-agent supervision, and native MCP tool integration. Developers use it to orchestrate complex agentic workflows without writing custom routing logic in application code.
Prerequisites
- Rust toolchain (rustc + cargo) installed, version 1.70 or higher
- An LLM provider API key, e.g. OPENAI_API_KEY for OpenAI or equivalent for other providers
- Node.js 18+ if using the npx launcher
- An MCP client such as Claude Desktop to connect to the MCP server endpoint
Add the crate to your Cargo project
If you are embedding RP Engine as a Rust library, add it to your Cargo.toml dependencies. This gives you direct access to the Engine builder and all node types.
[dependencies]
riceprompt-engine = "0.1"Set your LLM provider API key
RP Engine reads provider credentials from environment variables. Set OPENAI_API_KEY for OpenAI, or the relevant key for your chosen provider before running the engine.
export OPENAI_API_KEY=sk-...Define a workflow YAML
Create a YAML file that describes your agent graph. Each node has an id, a type (generate, transform, supervisor, mcp, etc.), and a config block specifying the provider, model, and template or script.
nodes:
- id: greet
type: generate
config:
provider: openai
model: gpt-4o-mini
template: tpl_greet
templates:
tpl_greet: "Hello, {{name}}! How can I help you today?"Run the workflow in Rust
Instantiate the Engine using its builder, then call run_yaml with your YAML string and a JSON input payload. The engine executes the graph and returns the final output.
use riceprompt_engine::Engine;
use serde_json::json;
#[tokio::main]
async fn main() -> anyhow::Result<()> {
let yaml = std::fs::read_to_string("workflow.yaml")?;
let engine = Engine::builder().build()?;
let result = engine.run_yaml(&yaml, json!({ "name": "Ada" })).await?;
println!("{result}");
Ok(())
}Configure the MCP server in Claude Desktop
Add RP Engine as an MCP server in your Claude Desktop config so Claude can invoke your YAML workflows as tools.
{
"mcpServers": {
"rp-engine": {
"command": "npx",
"args": ["rp-engine"],
"env": {
"OPENAI_API_KEY": "sk-..."
}
}
}
}RP Engine Examples
Client configuration
Minimal Claude Desktop configuration to launch RP Engine as an MCP server using npx.
{
"mcpServers": {
"rp-engine": {
"command": "npx",
"args": ["rp-engine"],
"env": {
"OPENAI_API_KEY": "sk-your-key-here"
}
}
}
}Prompts to try
Example prompts you can send to Claude once RP Engine is connected as an MCP server.
- "Run the summarization workflow on this text: [paste text]"
- "Execute the data-connector node to fetch records from my PostgreSQL database and summarize them"
- "Start the supervisor agent and route this customer query to the appropriate specialist"Troubleshooting RP Engine
Engine fails to start with 'OPENAI_API_KEY not set' error
Ensure the OPENAI_API_KEY environment variable is exported in the shell where npx rp-engine runs, or add it to the env block in your claude_desktop_config.json.
YAML workflow parse error on startup
Validate your workflow YAML with a linter (e.g. yamllint). Ensure all node ids are unique, all referenced template names exist, and the provider value matches one of: openai, anthropic, gemini, deepseek.
MCP tools from the mcp_tools node are not visible in Claude
Confirm your YAML workflow actually defines at least one mcp or mcp_tools node and that the server is fully initialized before Claude attempts to list tools. Restart Claude Desktop after any config change.
Frequently Asked Questions about RP Engine
What is RP Engine?
RP Engine is a Model Context Protocol (MCP) server that yaml-native agent workflow execution engine, written in rust It connects AI assistants to external tools and data sources through a standardized interface.
How do I install RP Engine?
Follow the installation instructions on the RP Engine GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with RP Engine?
RP Engine works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is RP Engine free to use?
Yes, RP Engine is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
RP Engine Alternatives — Similar Coding Agents Servers
Looking for alternatives to RP Engine? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up RP Engine in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use RP Engine?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.