agentmods.dev

claude-flow

claude-flow is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from ruvnet/RuView. Its token cost is not measured, scanned A, original, MIT.

An MCP server configuration for claude-flow, an AI-agent orchestration tool that coordinates specialized agents and provides shared tools and memory.

In plain words
What is it for?
Use it to run claude-flow as an MCP server with configured agent limits, hooks, coordination topology, and a hybrid memory backend.
Why use it?
It gives Claude Code a locally started service for coordinating agents, hooks, topology, and memory settings.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it. Also seen: listed in a Claude config.

not rated 99krepo +1.0k today A scan tokens not measured original MIT

Good fit Use it to run claude-flow as an MCP server with configured agent limits, hooks, coordination topology, and a hybrid memory backend.

Compare 6 mcp servers from other repositories ↓
Install with agentmods
npx agentmods add mcp/ruvnet/ruview/claude-flow
View source ↗ ruvnet/RuView cognitum.one
About the project

RuView is a WiFi sensing platform that uses disturbances in radio signals, captured by low-cost ESP32 sensors, to detect presence, movement, breathing, and heart rate without cameras or wearables. It is intended for spatial monitoring and smart-home integrations. The catalogue add-ons support workflows for operating and integrating RuView.

ruvnet/RuView · 98,659 stars · on GitHub · cognitum.one

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/ruvnet/RuView

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for claude-flow

README.md
[![agentmods](https://agentmods.dev/badge/mcp/ruvnet/ruview/claude-flow/github.svg)](https://agentmods.dev/mcp/ruvnet/ruview/claude-flow)
Your own site
<a href="https://agentmods.dev/mcp/ruvnet/ruview/claude-flow"><img src="https://agentmods.dev/badge/mcp/ruvnet/ruview/claude-flow/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for claude-flow

Your own site · 80×15
<a href="https://agentmods.dev/mcp/ruvnet/ruview/claude-flow"><img src="https://agentmods.dev/badge/mcp/ruvnet/ruview/claude-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

claude-flow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

8 near-identical copies found in the catalogue:

.mcp.json · 20 lines

What it actually says

{
  "claude-flow": {
    "command": "npx",
    "args": [
      "-y",
      "@claude-flow/cli@latest",
      "mcp",
      "start"
    ],
    "env": {
      "npm_config_update_notifier": "false",
      "CLAUDE_FLOW_MODE": "v3",
      "CLAUDE_FLOW_HOOKS_ENABLED": "true",
      "CLAUDE_FLOW_TOPOLOGY": "hierarchical-mesh",
      "CLAUDE_FLOW_MAX_AGENTS": "15",
      "CLAUDE_FLOW_MEMORY_BACKEND": "hybrid"
    },
    "autoStart": false
  }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 20 lines scan A 91357d6ea25c

Subscribe to this mod's changes

claude-flow is an MCP server published in the GitHub repository ruvnet/RuView (98,659 stars, last pushed today), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Building agentsdenseposeesp32monitoringrfwifiwifi-security
Related

Other mcp servers, from other repositories

guarftrain

Training Guardian — sidecar training monitor with crash recovery, agent decisions, MCP & web dashboard. Runs locally from the guarftrain Python package.

Washington5533/guarftrain · not measured

webhook-tester

Test webhook endpoints — send requests, measure latency, validate responses. x402 micropayment. Remote server at webhook-tester.api.klymax402.com.

Br0ski777/webhook-tester-x402 · not measured

mcp-certificate-monitor

A FastMCP server that lets an AI host monitor certificate expiry across a set of domains. Runs locally from the mcp-certificate-monitor Python package.

natesilva/mcp-certificate-monitor · not measured

eg4-mcp-server

Model Context Protocol server for EG4 solar inverter monitoring and control. Runs locally from the eg4-mcp-server Python package.

matt-dreyer/EG4_MCP_server · not measured

prometheus-mcp-server

Model Context Protocol server for Prometheus queries and metrics. Runs locally from the prometheus-mcp-server npm package.

yanmxa/prometheus-mcp-server · not measured

docs-langchain

MCP server "docs-langchain", hosted remotely at docs.langchain.com, as configured in langchain-ai/langchain.

langchain-ai/langchain · not measured