{"type":"mcp_client","name":"flock","description":"Flock is a flexible low-code platform for orchestrating collaborative agents, offering features like MCP tools support, parameter extraction, subgraph nodes, human-in-the-loop interactions, and multimodal chat capabilities. Flock is a flexible","category":"Productivity","language":"TypeScript","stars":1083,"forks":76,"owner":"Onelevenvy","github_url":"https://github.com/Onelevenvy/flock","homepage":"Email:qingxin1114@163.com","setup":"## Setup\n\n#### 1. Deploy with Docker Compose\n\n##### 1.1 Method 1: Pull Frontend and Backend Images from Docker Hub\n\n```bash\n# Clone the repository\ngit clone https://github.com/Onelevenvy/flock.git\n\n# Navigate to the docker directory\ncd flock/docker\n\n# Copy the environment configuration file\ncp ../.env.example .env\n\n# Start the docker compose\ndocker compose  up -d\n\n```\n\n#### 1.2 Method 2: Locally Build Frontend and Backend Images\n\n```bash\n# Clone the repository\ngit clone https://github.com/Onelevenvy/flock.git\n\n# Navigate to the docker directory\ncd flock/docker\n\n# Copy the environment configuration file\ncp ../.env.example .env\n\n# First, build the frontend and backend images\ndocker compose -f docker-compose.localbuild.yml build\n\n# Then, start Docker Compose\ndocker compose -f docker-compose.localbuild.yml up -d\n\n```\n\n#### 2. Start with Local Source Code\n\n#### 2.1 Preparation\n\n##### 2.1.1 Clone the Code\n\ngit clone https://github.com/Onelevenvy/flock.git\n\n##### 2.1.2 Copy Environment Configuration File\n\n```bash\ncp .env.example .env\n```\n\n##### 2.1.3 Generate Secret Keys\n\nSome environment variables in the .env file have a default value of changethis.\nYou have to change them with a secret key, to generate secret keys you can run the following command:\n\n```bash\npython -c \"import secrets; print(secrets.token_urlsafe(32))\"\n```\n\nCopy the content and use that as password / secret key. And run that again to generate another secure key.\n\n##### 2.1.4 Install postgres,qdrant,redis\n\n```bash\ncd docker\ndocker compose -f docker-compose.middleware.yml up -d\n```\n\n#### 2.2 Run Backend\n\n##### 2.2.1 Installation of the basic environment\n\nServer startup requires Python 3.12.x. It is recommended to use pyenv for quick installation of the Python environment.\n\nTo install additional Python versions, use pyenv install.\n\n```bash\npyenv install 3.12\n```\n\nTo switch to the \"3.12\" Python environment, use the following command:\n\n```bash\npyenv global 3.12\n```\n\nFollow these steps :\nNavigate to the \"backen\" directory:\n\n```bash\ncd backend\n```\n\nactivate the environment.\n\n```bash\npoetry env use 3.12\npoetry install\n```\n\n##### 2.2.2 initiral data\n\n```bash\n\n# Run migrations\nalembic upgrade head\n\n```\n\n##### 2.2.3 run unicorn\n\n```bash\n uvicorn app.main:app --reload --log-level debug\n```\n\n##### 2.2.4 run celery (Not necessary, unless you want to use the rag function)\n\n```bash\npoetry run celery -A app.core.celery_app.celery_app worker --loglevel=debug\n```\n\n#### 2.3 Run Frontend\n\n##### 2.3.1 Enter the web directory and install the dependencies\n\n```bash\ncd web\npnpm install\n```\n\n##### 2.3.2 Start the web service\n\n```bash\ncd web\npnpm dev\n\n# or pnpm build then pnpm start\n```","tools":"## Available Tools\n\n1.  ChatBot (Build chatbots)\n2.  SimpleRAG (Build RAG applications)\n3.  Hierarchical Agent (Coordinate hierarchical agent teams)\n4.  Sequential Agent (Coordinate sequential agent teams)\n5.  Work-Flow (Orchestrate workflows)\n6.  Intent Recognition Node (Automatically identify user input intent and route to different processing flows)\n7.  CrewAI Integration (Leverage CrewAI's multi-agent capabilities)\n8.  MCP Tools Support (Integrate with Model Context Protocol (MCP) servers)\n9.  Parameter Extractor Node (Automatically extract structured information from text and output in JSON format)\n10. Subgraph Node Support (Encapsulate and reuse complete sub-workflows)\n11. Human Node (Human-in-the-loop node supporting tool call review, LLM output validation, and context provision)\n12. Multimodal Chat Support (Support for multimodal chat, currently only supports image modality)\n13. If-Else Node (Support conditional logic in workflows)\n14. Code Execution Node (Write and execute Python scripts directly within your workflow)\n15. Tool Calling (Enable agents to utilize external tools and APIs)\n16. Retrieval Augmented Generation (Enable agents to reason with internal knowledge base)\n17. Human-In-The-Loop (Enable human approval before tool calling)\n18. Open Source Models (Use open-source LLM models such as llama, Qwen and Glm)\n19. Multi-Tenancy (Manage and support multiple users and teams)\n20. Persistent conversations (Save and maintain chat histories, allowing you to continue conversations)\n21. Observability (Monitor and track your agents' performance and outputs in real-time using LangSmith)\n","faq":null,"created_at":"2024-09-04T01:21:01+00:00","updated_at":"2025-03-28T16:52:43+00:00","source_url":"https://model-context-protocol.com/clients/low-code-workflow-chatbot-rag-agent","related_articles":[]}