Flock

v1.0.0Coding Agentsstable

A multi agent desktop application built with Rust and Tauri.

agentaichatbotdeekseekharness
Share:
1,072
Stars
0
Downloads
0
Weekly
0/5

What is Flock?

Flock is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to multi agent desktop application built with rust and tauri.

A multi agent desktop application built with Rust and Tauri.

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A multi agent desktop application built with Rust and Tauri.

Use Cases

Multi-agent desktop application for Rust
LangGraph-powered agent coordination
Onelevenvy

Maintainer

LicenseApache-2.0
Languagerust
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx flock

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Flock

Flock is an open-source, multi-agent desktop application built with Rust and Tauri that lets you compose LangGraph-powered agent workflows through a visual interface. It supports multiple LLM backends including OpenAI, Anthropic Claude, Google Gemini, AWS Bedrock, and local Ollama models, and provides built-in tools for bash execution, file system operations, grep search, Playwright browser automation, and VNC desktop streaming. Developers building local multi-agent automation systems use Flock to coordinate agents across tasks without deploying cloud infrastructure, with MCP servers extending the tool ecosystem available to all agents.

Prerequisites

  • Rust 1.77.2 or later with cargo
  • Node.js 18.x or later with npm
  • An API key for at least one LLM provider (OpenAI, Anthropic, Google Gemini, or AWS Bedrock credentials), or a running Ollama instance
  • Git to clone the repository
  • An MCP-compatible client if using Flock's MCP interface
1

Clone the repository

Clone the Flock repository from GitHub to your local machine.

git clone https://github.com/Onelevenvy/flock.git
cd flock
2

Install frontend dependencies

Navigate to the flock-ui directory and install Node.js dependencies required for the Tauri frontend.

cd flock-ui
npm install
3

Launch the development build

Start the Tauri development environment, which compiles the Rust backend and launches the desktop application.

npm run tauri dev
4

Configure your LLM provider

Inside the Flock UI, navigate to Settings and enter your API key for your preferred LLM provider. Flock supports OpenAI, Anthropic Claude, Google Gemini, AWS Bedrock, and local Ollama models—no environment variables needed, all configured through the UI.

5

Connect an MCP server

To extend agent tool capabilities, connect an MCP server through Flock's MCP integration. Once connected, all agents and workflows automatically inherit the new tool schemas from the MCP server.

{
  "mcpServers": {
    "flock": {
      "command": "npx",
      "args": ["flock"]
    }
  }
}
6

Run backend tests

Verify your Rust workspace is set up correctly by running the full test suite.

cargo test --workspace

Flock Examples

Client configuration

Configuration for adding Flock as an MCP server in your Claude Desktop setup.

{
  "mcpServers": {
    "flock": {
      "command": "npx",
      "args": ["flock"]
    }
  }
}

Prompts to try

Use these prompts inside the Flock desktop UI to explore multi-agent workflows.

- "Create a two-agent pipeline where Agent A researches a topic and Agent B writes a summary"
- "Run a bash script to check disk usage and report files larger than 100MB"
- "Open a browser with Playwright and take a screenshot of example.com"
- "Search all Python files in ~/projects for any TODO comments"
- "Coordinate agents to clone a repo, run tests, and report the results"

Troubleshooting Flock

Tauri build fails with Rust compilation errors

Update your Rust toolchain with `rustup update stable` and ensure you are on Rust 1.77.2 or later. On macOS, also install Xcode command line tools with `xcode-select --install`. Clear the Cargo cache with `cargo clean` before rebuilding.

LLM provider is not responding in the desktop UI

Confirm your API key is correctly entered in Settings. For Ollama local models, verify Ollama is running with `ollama serve` and that your chosen model is pulled (`ollama pull llama3`). AWS Bedrock requires valid AWS credentials with Bedrock model access enabled in your region.

MCP tools are not available to agents after connecting a server

After connecting an MCP server, restart the Flock agent runtime from the UI. All assistants and workflows inherit new tool schemas on initialization, so a restart is required for new MCP tools to become available.

Frequently Asked Questions about Flock

What is Flock?

Flock is a Model Context Protocol (MCP) server that multi agent desktop application built with rust and tauri. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Flock?

Follow the installation instructions on the Flock GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Flock?

Flock works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Flock free to use?

Yes, Flock is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Browse More Coding Agents MCP Servers

Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "flock": { "command": "npx", "args": ["-y", "flock"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Flock?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides