Cymbal Air Toolbox
Demo of a customer service agent (Cymbal Air) using LangGraph, Tools, and RAG to interact with Google Cloud Databases via MCP Toolbox.
What is Cymbal Air Toolbox?
Cymbal Air Toolbox is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to demo of a customer service agent (cymbal air) using langgraph, tools, and rag to interact with google cloud databases via mcp toolbox.
Demo of a customer service agent (Cymbal Air) using LangGraph, Tools, and RAG to interact with Google Cloud Databases via MCP Toolbox.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Demo of a customer service agent (Cymbal Air) using LangGrap
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx cymbal-air-toolbox-demoConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Cymbal Air Toolbox
Cymbal Air Toolbox Demo is an open-source reference implementation from Google Cloud Platform that shows how to build a customer service AI agent using LangGraph, MCP Toolbox, and Google Cloud databases. The agent answers questions about a fictional airline (Cymbal Air), handling queries about flight availability, airport amenities, and gate information by querying AlloyDB or BigQuery through the MCP Toolbox binary. It serves as a learning resource for developers who want to understand how to wire LangGraph agent loops to real cloud databases via the MCP protocol with retrieval-augmented generation.
Prerequisites
- Git to clone the repository
- Access to download the MCP Toolbox binary (v0.8.0+) from Google Cloud Storage
- A Google Cloud project with AlloyDB or BigQuery configured (see docs/database_setup.md in the repo)
- Python 3.10+ and pip for running the LangGraph agent
- Claude API key or Google Cloud AI credentials for the LLM backend
Clone the repository
Clone the demo repository from Google Cloud Platform's GitHub organization to get all configuration files and agent code.
git clone https://github.com/GoogleCloudPlatform/cymbal-air-toolbox-demo.git
cd cymbal-air-toolbox-demoDownload the MCP Toolbox binary
Download the Toolbox binary for your platform from Google Cloud Storage. This binary acts as the MCP server that bridges the LangGraph agent to your cloud databases.
export VERSION=0.8.0
curl -O https://storage.googleapis.com/genai-toolbox/v$VERSION/linux/amd64/toolbox
chmod +x toolboxSet up your Google Cloud database
Follow the database setup guide in the repository (docs/database_setup.md) to initialize an AlloyDB or BigQuery instance with the Cymbal Air flight and amenity data. This is a one-time step.
Configure tools.yaml
Edit the tools.yaml file in the repository root to point the Toolbox server at your database instance. This file defines the agent tools (find_flights, list_amenities, etc.) and their database queries.
Launch the MCP Toolbox server
Start the Toolbox server with your tools configuration. It will expose the defined tools over the MCP protocol for the LangGraph agent to consume.
./toolbox --tools-file "tools.yaml"Run the LangGraph agent
Start the Python agent application that connects to the running Toolbox server. Refer to the README for the exact run command, which varies by whether you use the local or Cloud Run deployment mode.
Cymbal Air Toolbox Examples
Client configuration
This demo does not use a standard MCP client config — the LangGraph agent connects directly to the Toolbox server at its local endpoint. The config below shows the conceptual structure.
{
"mcpServers": {
"cymbal-air-toolbox": {
"command": "./toolbox",
"args": ["--tools-file", "tools.yaml"],
"env": {
"GOOGLE_CLOUD_PROJECT": "your-gcp-project-id"
}
}
}
}Prompts to try
These prompts demonstrate the Cymbal Air customer service agent's capabilities via the find_flights and list_amenities tools.
- "Are there luxury shops in the terminal?"
- "Where can I get coffee near gate A6?"
- "What flights depart to NYC tomorrow?"
- "List all amenities available in Terminal B"
- "Is there a lounge near gate C12 where I can wait for my flight?"Troubleshooting Cymbal Air Toolbox
Toolbox binary fails to connect to the database
Verify that your Google Cloud credentials are active by running `gcloud auth application-default login`. Check that the database connection string in tools.yaml matches your AlloyDB or BigQuery instance details from the setup guide.
tools.yaml cannot be found or causes a parse error
Ensure you are running the ./toolbox binary from the repository root directory where tools.yaml is located. YAML indentation errors are common — validate the file with a YAML linter before launching.
The agent returns no results for flight queries
Confirm the database was initialized with flight data by following docs/database_setup.md completely. The demo data must be seeded before the find_flights tool can return results.
Frequently Asked Questions about Cymbal Air Toolbox
What is Cymbal Air Toolbox?
Cymbal Air Toolbox is a Model Context Protocol (MCP) server that demo of a customer service agent (cymbal air) using langgraph, tools, and rag to interact with google cloud databases via mcp toolbox. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Cymbal Air Toolbox?
Follow the installation instructions on the Cymbal Air Toolbox GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Cymbal Air Toolbox?
Cymbal Air Toolbox works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Cymbal Air Toolbox free to use?
Yes, Cymbal Air Toolbox is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Cymbal Air Toolbox Alternatives — Similar Cloud Services Servers
Looking for alternatives to Cymbal Air Toolbox? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Cymbal Air Toolbox in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Cymbal Air Toolbox?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.