MCP Toolbox for Databases is an open source server that enables you to develop database tools for AI agents more easily and securely. It handles complex tasks such as connection pooling and authentication while providing a central location for your tools to be shared between applications.
Choose one of the following installation methods:
Binary Installation
# See releases page for other versions
export VERSION=0.4.0
curl -O https://storage.googleapis.com/genai-toolbox/v$VERSION/linux/amd64/toolbox
chmod +x toolbox
Container Image
# See releases page for other versions
export VERSION=0.4.0
docker pull us-central1-docker.pkg.dev/database-toolbox/toolbox/toolbox:$VERSION
First, configure a tools.yaml
file to define your tools, then start the server:
./toolbox --tools_file "tools.yaml"
You can use toolbox help
to see all available command-line options. To stop the server, press ctrl+c
.
After your server is running, you can load the tools into your application using one of the client SDKs:
Core SDK
pip install toolbox-core
from toolbox_core import ToolboxClient
# Update the URL to point to your server
client = ToolboxClient("http://127.0.0.1:5000")
# These tools can be passed to your application!
tools = await client.load_toolset("toolset_name")
LangChain / LangGraph SDK
pip install toolbox-langchain
from toolbox_langchain import ToolboxClient
# Update the URL to point to your server
client = ToolboxClient("http://127.0.0.1:5000")
# These tools can be passed to your application!
tools = client.load_toolset()
LlamaIndex SDK
pip install toolbox-llamaindex
from toolbox_llamaindex import ToolboxClient
# Update the URL to point to your server
client = ToolboxClient("http://127.0.0.1:5000")
# These tools can be passed to your application!
tools = client.load_toolset()
The primary configuration file is tools.yaml
, which defines your data sources, tools, and toolsets.
The sources
section defines the data sources your tools will access:
sources:
my-pg-source:
kind: postgres
host: 127.0.0.1
port: 5432
database: toolbox_db
user: toolbox_user
password: my-password
The tools
section defines the actions an agent can perform:
tools:
search-hotels-by-name:
kind: postgres-sql
source: my-pg-source
description: Search for hotels based on name.
parameters:
- name: name
type: string
description: The name of the hotel.
statement: SELECT * FROM hotels WHERE name ILIKE '%' || $1 || '%';
The toolsets
section allows you to create groups of tools that can be loaded together:
toolsets:
my_first_toolset:
- my_first_tool
- my_second_tool
my_second_toolset:
- my_second_tool
- my_third_tool
Load specific toolsets in your code:
# This will load all tools
all_tools = client.load_toolset()
# This will only load the tools listed in 'my_second_toolset'
my_second_toolset = client.load_toolset("my_second_toolset")
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.