MCP Toolbox for Databases is an open source MCP server that simplifies development of tools for database access. It handles complexities like connection pooling, authentication, and security, allowing you to integrate database tools with your AI agents more efficiently.
Choose one of the following installation methods:
# see releases page for other versions
export VERSION=0.5.0
curl -O https://storage.googleapis.com/genai-toolbox/v$VERSION/linux/amd64/toolbox
chmod +x toolbox
# see releases page for other versions
export VERSION=0.5.0
docker pull us-central1-docker.pkg.dev/database-toolbox/toolbox/toolbox:$VERSION
Configure a tools.yaml
file to define your tools, then start the server:
./toolbox --tools-file "tools.yaml"
Use toolbox help
to see all available options. To stop the server, press ctrl+c
.
Once your server is running, you can connect to it using one of the client SDKs:
Install the SDK:
pip install toolbox-core
Load your tools:
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")
Install the SDK:
pip install toolbox-langchain
Load your tools:
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()
Install the SDK:
pip install toolbox-llamaindex
Load your tools:
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 method is through the tools.yaml
file, which you can specify with the --tools-file tools.yaml
flag.
Define your data sources in the sources
section:
sources:
my-pg-source:
kind: postgres
host: 127.0.0.1
port: 5432
database: toolbox_db
user: toolbox_user
password: my-password
Define the actions your agent can take in the tools
section:
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 || '%';
Group tools together for easier loading with the toolsets
section:
toolsets:
my_first_toolset:
- my_first_tool
- my_second_tool
my_second_toolset:
- my_second_tool
- my_third_tool
You can then load specific toolsets in your application:
# 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")
For comprehensive documentation, visit the full documentation site.
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.