Ruflo ships a full MCP 2025-11-25 compliant server that exposes 313 tools across five groups: coordination, memory, monitoring, GitHub, and system. It’s the primary integration point for Claude Code, Cursor, Windsurf, and any other MCP-compatible client. The server starts in under 400ms and supports stdio (default), HTTP, and WebSocket transports — pick the one that fits your editor.Documentation Index
Fetch the complete documentation index at: https://mintlify.com/ruvnet/ruflo/llms.txt
Use this file to discover all available pages before exploring further.
Starting the Server
Transports
| Transport | Use Case | Command |
|---|---|---|
stdio | Claude Code, Codex (default) | mcp start |
http | Windsurf, Cursor, REST clients | mcp start --transport http |
websocket | Real-time streaming apps | mcp start --transport websocket |
The
stdio transport is the canonical form for Claude Code. The server reads JSON-RPC messages from stdin and writes responses to stdout — no network port is opened. Use http or websocket for editors that connect over a network socket or for remote deployments.Registering with Editors
- Claude Code
- Cursor
- Windsurf
- OpenAI Codex CLI
Add Ruflo as a named MCP server with a single command:Verify the registration:Once added, all 313 Ruflo MCP tools are available directly in your Claude Code sessions —
swarm_init, agent_spawn, memory_search, hooks_route, and the rest.MCP Tool Groups
The 313 tools are organized into five groups. Load only what your workflow needs.| Group | Key Tools | Approx. Count |
|---|---|---|
coordination | swarm_init, agent_spawn, task_orchestrate | ~50 |
monitoring | swarm_status, agent_list, agent_metrics | ~40 |
memory | memory_store, memory_search, memory_usage, neural_train | ~60 |
github | github_swarm, repo_analyze, pr_enhance, code_review | ~80 |
system | benchmark and utility tools | ~83 |
claude-flow.config.json:
HTTP Transport Configuration
For Windsurf, Cursor (HTTP mode), REST clients, or any scenario where you need a network-accessible MCP endpoint, configure the server programmatically using@claude-flow/mcp:
CLAUDE_FLOW_AUTH_TOKEN in your environment to enable token authentication without modifying code:
Server Management Commands
Performance Targets
The@claude-flow/mcp package is built to these targets:
| Metric | Target |
|---|---|
| Server startup | <400ms |
| Tool registration | <10ms per tool |
| Tool execution overhead | <50ms |
| Connection acquire | <5ms |
Startup time: The full Ruflo CLI cold-start is ~35s on a fresh
npx pull due to the ML/embedding dependencies. For plugin scripts that invoke memory commands in hooks, set CLI_CORE=1 to use @claude-flow/cli-core instead — this drops cold-cache wall time from ~35s to ~1.5s (22.9× speedup). The full MCP server always uses the complete CLI regardless of CLI_CORE.After the first invocation, npx caches the package and subsequent starts take ~3s.MCP Methods Supported
Ruflo’s MCP server is fully MCP 2025-11-25 compliant and implements the complete protocol surface:| Method | Description |
|---|---|
initialize | Initialize connection and negotiate capabilities |
tools/list | List available tools (with optional pagination) |
tools/call | Execute a tool by name |
resources/list | List resources with cursor-based pagination |
resources/read | Read resource content |
resources/subscribe | Subscribe to resource updates |
prompts/list | List prompt templates |
prompts/get | Get a prompt with arguments |
tasks/status | Get async task status |
tasks/cancel | Cancel a running task |
logging/setLevel | Set server log level |
ping | Keep-alive |
Next Steps
Full MCP Tool Reference
Browse all 313 MCP tools organized by group, with parameter schemas and usage examples.
Environment Variables
Configure
CLAUDE_FLOW_TOOL_GROUPS, CLAUDE_FLOW_MCP_PORT, CLAUDE_FLOW_AUTH_TOKEN, and more.