# claude-flow

Connect Claude Code to claude-flow tools for agent coordination and shared task context. The MCP setup uses ANTHROPIC_API_KEY.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed · ★ 79357
- Author: ruvnet
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/ruvnet/ruflo
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/claude-flow

## What it does

claude-flow adds an agent-management layer around Claude Code and Codex. Its MCP server exposes tools for coordinating agents and working with memory across sessions. You can connect it locally with `npx`.

The Claude Code setup command takes `ANTHROPIC_API_KEY`, `GITHUB_TOKEN`, and `FLOW_NEXUS_API_KEY`. Without the required key values, that configured command cannot start the server as intended. The project also describes agent swarms and communication across machines; those capabilities depend on the chosen mode and configuration.

## Requirements
- Needs: Node.js (commands run via npx)
- Environment variables: `ANTHROPIC_API_KEY`, `CLAUDE_FLOW_MODE`, `CLAUDE_FLOW_MEMORY_PATH`, `CLAUDE_FLOW_MAX_AGENTS`, `CLAUDE_FLOW_PORT`, `GITHUB_TOKEN`, `FLOW_NEXUS_API_KEY` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add --env ANTHROPIC_API_KEY=<ANTHROPIC_API_KEY> --env CLAUDE_FLOW_MODE=<CLAUDE_FLOW_MODE> --env CLAUDE_FLOW_MEMORY_PATH=<CLAUDE_FLOW_MEMORY_PATH> --env CLAUDE_FLOW_MAX_AGENTS=<CLAUDE_FLOW_MAX_AGENTS> --env CLAUDE_FLOW_PORT=<CLAUDE_FLOW_PORT> --transport stdio claude-flow -- npx -y claude-flow
```
Replace <…> with your own values. 2 more environment variables are in the server README

### Codex

**Platform CLI**
```bash
codex mcp add claude-flow --env ANTHROPIC_API_KEY=<ANTHROPIC_API_KEY> --env CLAUDE_FLOW_MODE=<CLAUDE_FLOW_MODE> --env CLAUDE_FLOW_MEMORY_PATH=<CLAUDE_FLOW_MEMORY_PATH> --env CLAUDE_FLOW_MAX_AGENTS=<CLAUDE_FLOW_MAX_AGENTS> --env CLAUDE_FLOW_PORT=<CLAUDE_FLOW_PORT> -- npx -y claude-flow
```
Replace <…> with your own values. 2 more environment variables are in the server README

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "claude-flow": {
            "command": "npx",
            "args": [
                "-y",
                "claude-flow"
            ],
            "env": {
                "ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>",
                "CLAUDE_FLOW_MODE": "<CLAUDE_FLOW_MODE>",
                "CLAUDE_FLOW_MEMORY_PATH": "<CLAUDE_FLOW_MEMORY_PATH>",
                "CLAUDE_FLOW_MAX_AGENTS": "<CLAUDE_FLOW_MAX_AGENTS>",
                "CLAUDE_FLOW_PORT": "<CLAUDE_FLOW_PORT>"
            }
        }
    }
}
```
Replace <…> with your own values. 2 more environment variables are in the server README

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "claude-flow": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "claude-flow"
            ],
            "env": {
                "ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>",
                "CLAUDE_FLOW_MODE": "<CLAUDE_FLOW_MODE>",
                "CLAUDE_FLOW_MEMORY_PATH": "<CLAUDE_FLOW_MEMORY_PATH>",
                "CLAUDE_FLOW_MAX_AGENTS": "<CLAUDE_FLOW_MAX_AGENTS>",
                "CLAUDE_FLOW_PORT": "<CLAUDE_FLOW_PORT>"
            }
        }
    }
}
```
Replace <…> with your own values. 2 more environment variables are in the server README

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add -e ANTHROPIC_API_KEY=<ANTHROPIC_API_KEY> -e CLAUDE_FLOW_MODE=<CLAUDE_FLOW_MODE> -e CLAUDE_FLOW_MEMORY_PATH=<CLAUDE_FLOW_MEMORY_PATH> -e CLAUDE_FLOW_MAX_AGENTS=<CLAUDE_FLOW_MAX_AGENTS> -e CLAUDE_FLOW_PORT=<CLAUDE_FLOW_PORT> claude-flow npx -y claude-flow
```
Replace <…> with your own values. 2 more environment variables are in the server README

## When to use it
- connect claude-flow tools to Claude Code over MCP
- coordinate several agents on a task
- carry context between sessions
- enable agents on separate machines to communicate

## Example prompts
- Coordinate several agents to complete this task.
- Use claude-flow memory to continue with context from the previous session.
- Set up communication between agents on separate machines.

## Similar
- [hindsight-docs](https://affpapa.org/en/nevibecode/skills/hindsight-docs.md) — skill · 9200 installs
- [knowledge-agent](https://affpapa.org/en/nevibecode/skills/knowledge-agent.md) — skill · 5700 installs
- [context-engineering-collection](https://affpapa.org/en/nevibecode/skills/context-engineering-collection.md) — skill · 4200 installs
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 386989
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33918
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81115
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47392

From the same set: [ruvnet/ruflo](https://affpapa.org/en/nevibecode/by/ruvnet/ruflo.md) — 146 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md