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
Knowledge graph-based persistent memory system
Logs statistical variations and unusual events in conversation structures to a SQLite database.
Enables persistent knowledge storage for Claude using a knowledge graph with multiple database backends like PostgreSQL and SQLite.
Access the OSV (Open Source Vulnerabilities) database for vulnerability information. Query vulnerabilities by package version or commit, batch query multiple packages, and get detailed vulnerability information by ID.
An MCP server for Quickbase, enabling seamless integration with AI assistants like Claude Desktop.
Provides read-only access to Apache Iceberg tables via Apache Impala, allowing LLMs to inspect schemas and execute queries.
Securely access BigQuery datasets with intelligent caching, schema tracking, and query analytics via Supabase integration.
An MCP server that provides tools to interact with Powerdrill datasets, enabling smart AI data analysis and insights.
MCP server for SQLite files. Supports Datasette-compatible metadata!
Interact with Snowflake databases to query and manage data.