# Flock > A desktop multi-agent harness built with Rust, Tauri, and React, powered by langgraph-rust. - **Type:** MCP server - **Install:** `agentstack add mcp-onelevenvy-flock` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [Onelevenvy](https://agentstack.voostack.com/s/onelevenvy) - **Installs:** 0 - **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml) - **Latest version:** 0.1.0 - **License:** Apache-2.0 - **Upstream author:** [Onelevenvy](https://github.com/Onelevenvy) - **Source:** https://github.com/Onelevenvy/flock ## Install ```sh agentstack add mcp-onelevenvy-flock ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # Flock A desktop multi-agent harness built with Rust, Tauri, and React, powered by langgraph-rust. **Visual Workflow | Multi-Agent Harness | Built-in Agent | Safe Sandbox & VNC | Cross-Platform | Any API Key** English | [简体中文](docs/README_zh.md) > **Note**: This project is built on top of [langgraph-rust](https://github.com/Onelevenvy/langgraph-rust), which is my personal Rust implementation of the LangGraph framework. > > **Refactoring History**: Flock has been completely rewritten from the ground up. The original version was a Python-based application using LangGraph, LangChain, and FastAPI as the backend. The current version is a native desktop application with a Rust backend, powered by Tauri for the desktop shell. This rewrite brings significant improvements in performance, reliability, and user experience. > > **Legacy Code**: The original Python codebase is preserved in the `legacy/python` branch for reference. --- ## 📋 Quick Navigation [Multi-Agent Harness & Workflow](#-multi-agent-harness--workflow) · [Core Features](#-core-features) · [Architecture](#-architecture) · [Quick Start](#-quick-start) --- ## 🤝 Multi-Agent Harness & Workflow — Visual Orchestration for AI Agents Flock is more than just a chat client. It's a comprehensive **multi-agent harness** combined with a powerful **Visual Workflow Editor**. It orchestrates and runs AI agents locally or inside sandbox containers to read/write files, execute bash commands, browse the web, and run complex pipelines. You see everything the agent does, and you're always in control. | Capability / Feature | Traditional Chat Clients | Flock (Multi-Agent Harness) | | :--- | :---: | :---: | | **Visual Workflow Builder** | No | **Yes** — ReactFlow editor with 10+ node types & streaming execution | | **AI Operating on Files** | Limited or No | **Yes** — Built-in agent with full filesystem, grep, and glob access | | **Multi-Step Autonomy** | No | **Yes** — Autonomous LangGraph-rust execution loop with approval prompts | | **Scheduled Task Automation** | No | **Yes** — Native Cron scheduler for 24/7 unattended workflows | | **Multi-Agent Collaboration** | No | **Yes** — Auto-detects & orchestrates multiple agents in team networks | | **Open Source & Extensible** | Rarely | **Yes** — Free, built with Rust & Tauri, fully extensible | --- ## 🌟 Core Features ### 🕸️ Visual Workflow Editor (ReactFlow Engine) * **Drag-and-Drop Canvas**: Design complex pipelines visually by connecting custom agent and logic nodes. * **10 Node Types Shipped**: * `start` & `answer`: Define workflow inputs and final delivery parameters. * `llm` & `agent`: Pure inference nodes and tool-enabled LangGraph agents. * `classifier` & `ifelse`: Semantic routing routers and conditional branch checkers. * `code`: Custom JS/Python code runners to execute arbitrary transformations. * `human`: Interactive interrupts asking for manual feedback or input. * `plugin` & `parameter_extractor`: Expose custom tools/plugins and extract structured data. * **Version Control & Execution History**: Easily manage multiple versions of your visual workflows, track historical execution paths, and debug states incrementally. ### 👥 Human-in-the-Loop (HITL) & Safe Interaction * **Interactive Tool Approvals**: Crucial actions (like writing files, running bash scripts, or modifying configurations) require explicit user approval before execution. You can inspect the plan, approve, or deny on the fly. * **VNC Screen Takeover**: Directly interact with sandboxed browser and OS interfaces. When the agent gets stuck on captchas, you can take over mouse/keyboard controls seamlessly. * **Workflow Breakpoints (`human` node)**: Place manual intervention checkpoints in the visual flow to request human decisions, form submissions, or variable modifications before proceeding. ### 🌐 Browser Automation & Computer Use * **Playwright Browser**: Scrape web data, click links, and bypass forms using an isolated browser execution engine. * **Computer Use**: Command virtual desktops using OS-level commands (`xdotool`). The agent monitors framebuffer screen feeds and handles mouse/keyboard events. ### 🤖 Built-in Agent — Zero Configuration * **Out of the box**: No external CLI tools to download or configure. Paste any API Key (OpenAI, Gemini, Anthropic Claude, AWS Bedrock, or Ollama/local) and start immediately. * **Skill Extensions**: Extensible via YAML-frontmatter prompts that support Hot-Reloading on file changes. ### 🔒 Safe Sandbox Environment * **Isolated Environment**: Executes risky shell scripts and code execution safely inside isolated environment containers. * **VNC Streaming**: Stream sandbox desktops directly into the UI via WebSockets for full visual inspection of the running environment. ### 🔌 MCP & Scheduled Tasks * **MCP (Model Context Protocol)**: Connect to third-party MCP servers once; all assistants and workflows automatically inherit the newly exposed schemas and tools. * **Scheduled Cron Tasks**: Set it once, the agent executes scheduled tasks on autopilot. Supports standard cron syntax for automated system maintenance, daily file aggregation, or report generation. --- ## 🏗️ Architecture ```mermaid graph TD UI[Tauri Desktop UI - React + Mantine] |IPC / Tauri Command| TauriHost[src-tauri Core] TauriHost |IPC Interface / JSON Protocol| AgentEngine[flock-agent - LangGraph Core] AgentEngine -->|Graph State Machine| StateGraph[langgraph-rust] AgentEngine |SQLite Checkpointer| DB[(SQLite Database)] AgentEngine |Discovery / Frontmatter| Skills[flock-skills] AgentEngine |Tool Execution| Registry[flock-tools - Tool Registry] Registry |Local Host| Builtin[Built-in Tools: Bash, Files, Grep] Registry |Model Context Protocol| MCP[MCP Server Registry] Registry |Isolated Container| Sandbox[Sandbox Client] Sandbox |X11 / VNC Server| VNC[x11vnc + websockify] |Websocket Stream| UI Sandbox |Playwright / xdotool| Browser[Browser & OS Controls] ``` ### Module Breakdown | Crate | Directory | Purpose | |-------|-----------|---------| | `flock-core` | `crates/flock-core` | Shared configuration schemas, SQLite DB models, encryption utilities, and IPC channels. | | `flock-agent` | `crates/flock-agent` | The core agent executor loop, LangGraph state engine, checkpointer, and memory system. | | `flock-workflow`| `crates/flock-workflow` | Workflow node logic and JSON-to-LangGraph AST compiler. | | `flock-tools` | `crates/flock-tools` | Built-in and sandboxed tools, VNC web socket proxies, and sandbox managers. | | `flock-skills` | `crates/flock-skills` | System prompts loader supporting variable injection and watcher-based hot-reload. | | `flock-ui` | `flock-ui` | React application featuring Zustand, i18next, and ReactFlow editor. | --- ## 🚀 Quick Start ### Prerequisites * **Rust**: `1.77.2` or later * **Node.js**: `18.x` or later ### Install & Run 1. **Clone the Repository** ```bash git clone https://github.com/Onelevenvy/flock.git cd flock ``` 2. **Install Frontend Dependencies** ```bash cd flock-ui npm install ``` 3. **Start Development App** ```bash npm run tauri dev ``` 4. **Run Backend Tests** ```bash cargo test --workspace ``` --- ## 📄 License Licensed under the Apache License, Version 2.0. See [LICENSE](LICENSE) for details. ## Source & license This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [Onelevenvy](https://github.com/Onelevenvy) - **Source:** [Onelevenvy/flock](https://github.com/Onelevenvy/flock) - **License:** Apache-2.0 Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** yes - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/mcp-onelevenvy-flock - Seller: https://agentstack.voostack.com/s/onelevenvy - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.