Allows LLMs to directly interact with a YugabyteDB database.
An MCP server implementation for YugabyteDB that allows LLMs to directly interact with your database.
Clone this repository and install dependencies:
git clone git@github.com:yugabyte/yugabytedb-mcp-server.git
cd yugabytedb-mcp-server
uv sync
The server is configured using the following environment variable:
YUGABYTEDB_URL
: The connection string for your YugabyteDB database (e.g., dbname=database_name host=hostname port=5433 user=username password=password
)Example .env
file:
YUGABYTEDB_URL=postgresql://user:password@localhost:5433/yugabyte
You can run the server with STDIO
transport using uv:
uv run src/server.py
or with Streamable-HTTP
transport:
uv run src/server.py --transport http
Build the Docker image:
docker build -t mcp/yugabytedb .
Run the container with STDIO
transport:
docker run -p 8080:8080 -e YUGABYTEDB_URL="your-db-url" mcp/yugabytedb
or with Streamable-HTTP
transport:
docker run -p 8080:8080 -e YUGABYTEDB_URL="your-db-url" mcp/yugabytedb --transport=http
To use this server with an MCP client (e.g., Claude Desktop, Cursor), add it to your MCP client configuration.
uv
Example configuration for Cursor:
{
"mcpServers": {
"yugabytedb-mcp": {
"command": "uv",
"args": [
"--directory",
"/path/to/cloned/yugabytedb-mcp-server/",
"run",
"src/server.py"
],
"env": {
"YUGABYTEDB_URL": "dbname=database_name host=hostname port=5433 user=username password=password load_balance=true topology_keys=cloud.region.zone1,cloud.region.zone2"
}
}
}
}
/path/to/cloned/yugabytedb-mcp-server/
with the path to your cloned repository.env
section.After building the docker container, add the following to claude_config.json
entry or equivalent json files for other editors:
{
"mcpServers": {
"yugabytedb-mcp-docker": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e",
"YUGABYTEDB_URL=dbname=yugabyte host=host.docker.internal port=5433 user=yugabyte password=yugabyte load_balance=false",
"mcp/yugabytedb"
]
}
}
}
mcpServers
.The logs for Claude Desktop can be found in the following locations:
The logs can be used to diagnose connection issues or other problems with your MCP server configuration. For more details, refer to the official documentation.
In the bottom panel of Cursor, click on "Output" and select "Cursor MCP" from the dropdown menu to view server logs. This can help diagnose connection issues or other problems with your MCP server configuration.
Start the server using Streamable-HTTP:
uv run src/server.py --transport http
Or with Docker:
docker run -p 8080:8080 -e YUGABYTEDB_URL="..." mcp/yugabytedb --transport=http
Launch the inspector:
npx @modelcontextprotocol/inspector
In the GUI, use the URL:
http://localhost:8080/invocations/mcp
Streamable-HTTP
Once connected via an MCP client, you can:
YUGABYTEDB_URL
: (required) The connection string for your YugabyteDB/PostgreSQL databaseYUGABYTEDB_URL
is set and correctuv
is installed and available in your PATH. Note: If claude is unable to access uv, giving the error: spawn uv ENOENT
, try symlinking the uv for global access:sudo ln -s "$(which uv)" /usr/local/bin/uv
pyproject.toml
src/server.py
Interact with Verodat AI Ready Data platform
MySQL database integration with configurable access controls and schema inspection
Immutable ledger database with live synchronization
An MCP server for the Chroma embedding database, providing persistent, searchable working memory for AI-assisted development with features like automated context recall and codebase indexing.
Securely access BigQuery datasets with intelligent caching, schema tracking, and query analytics via Supabase integration.
Search, Query and interact with data in your Milvus Vector Database.
Manage NocoDB server, support read and write databases
Connect to any relational database, and be able to get valid SQL, and ask questions like what does a certain column prefix mean.
Full Featured MCP Server for MongoDB Database.
Interact with Tinybird serverless ClickHouse platform