# Ruflo MCP server

> Lets an AI client orchestrate swarms of specialized agents, coordinate workflows, and retain self-learning memory across sessions.

- Repository: https://github.com/ruvnet/ruflo
- Page: https://hostedmcp.org/servers/ruvnet/ruflo
- Transport: stdio
- Stars: 81829
- License: MIT

## Install

### Claude Code

```sh
claude mcp add ruflo -- npx -y @claude-flow/cli-core
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "ruflo": {
      "command": "npx",
      "args": [
        "-y",
        "@claude-flow/cli-core"
      ]
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "ruflo": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@claude-flow/cli-core"
      ]
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"ruflo","type":"stdio","command":"npx","args":["-y","@claude-flow/cli-core"]}'
```

### Claude Desktop (`claude_desktop_config.json`)

```json
{
  "mcpServers": {
    "ruflo": {
      "command": "npx",
      "args": [
        "-y",
        "@claude-flow/cli-core"
      ]
    }
  }
}
```

### Codex

```sh
codex mcp add ruflo -- npx -y @claude-flow/cli-core
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.ruflo]
command = "npx"
args = ["-y", "@claude-flow/cli-core"]
```

### Gemini CLI

```sh
gemini mcp add -s user ruflo npx -- -y @claude-flow/cli-core
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "ruflo": {
      "command": "npx",
      "args": [
        "-y",
        "@claude-flow/cli-core"
      ]
    }
  }
}
```

## FAQ

### How do I get started with Ruflo?

Run npx ruflo@latest init in your project folder, then open Claude Code and give it a task. init adds Ruflo's agents, hooks, memory and MCP server to the project.

### How do I connect an MCP client like Codex to Ruflo?

Configure the command npx with the arguments ["-y", "ruflo@latest", "mcp", "start"]. Claude Code and other MCP clients pick it up that way, or via the init command.

### What does Ruflo add to Claude Code?

It adds over 100 specialized agents, coordinated swarms, self-learning memory, federation across machines and security guardrails. It acts as the execution layer around Claude Code and Codex.

### Does Ruflo require an LLM for memory and learning?

Local vector retrieval and contrastive updates can run without an LLM, but embeddings and configured learning modules are still required. Agent execution may still use an LLM.
