Cockroachdb MCP Server
@amineelkouhen
About Cockroachdb MCP Server
The CockroachDB MCP Server is a natural language interface designed for agentic applications to manage, monitor and query data in CockroachDB.
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"cockroach": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e",
"CRDB_HOST=<cockroachdb_host>",
"-e",
"CRDB_PORT=<cockroachdb_port>",
"-e",
"CRDB_DATABASE=<cockroachdb_database>",
"-e",
"CRDB_USERNAME=<cockroachdb_user>",
"mcp-cockroachdb"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Cockroachdb MCP Server?
Cockroachdb MCP Server is a natural language interface that enables LLMs and agentic applications to manage, monitor, and query data in CockroachDB. It integrates with MCP (Model Context Protocol) clients such as Claude Desktop and Cursor, allowing AI-driven workflows to interact directly with the database.
How to use Cockroachdb MCP Server?
Install and run the server using uvx with a CockroachDB connection URI or individual parameters. Alternatively, use a Docker image or clone the repository for development. Configure via command-line arguments or environment variables (e.g., CRDB_HOST, CRDB_PORT, CRDB_DATABASE). Connect any MCP client (like Claude Desktop) by editing its config file to point to the server.
Key features of Cockroachdb MCP Server
- Natural language queries and transaction creation
- Cluster health and node status monitoring
- Database operations: create, drop, list, switch
- Table management including indexes, views, and schemas
- SQL query execution with JSON, CSV, or table formatting
- Multi-statement transaction support and query plan analysis
Use cases of Cockroachdb MCP Server
- AI agents querying CockroachDB using natural language
- Monitoring cluster health and replication status
- Managing schemas, tables, and indexes programmatically
- Running and analyzing SQL queries through an LLM interface
FAQ from Cockroachdb MCP Server
What runtime dependencies does it require?
Python 3.13 or higher is required. The recommended way to run it is via uvx (from uv package manager) or using Docker.
How do I connect the server to my CockroachDB instance?
You can provide a connection URI (--url postgresql://user:pass@host:port/db) or specify individual parameters like --host, --port, --db, --user, and --password. SSL/TLS options are also available for secure connections.
What transport protocols does it support?
Currently only the stdio transport is supported. Support for streamable-http transport will be added in a future release.
Where does the data reside?
The server connects to your own CockroachDB instance; it does not store data itself. All data operations are executed directly against the database you specify.
Are there any known limitations or breaking changes?
The main branch is under active development and may contain breaking changes. It is recommended to use a tagged release (e.g., 0.1.0) for stable usage.
More Databases MCP servers
MongoDB MCP Server
mongodb-jsA Model Context Protocol server to connect to MongoDB databases and MongoDB Atlas Clusters.
Elasticsearch MCP Server
elastic
Snowflake MCP Server
isaacwasserman
Meilisearch MCP Server
meilisearchA Model Context Protocol (MCP) server for interacting with Meilisearch through LLM interfaces.
MCP Server for MySQL based on NodeJS
benborlaA Model Context Protocol server that provides read-only access to MySQL databases. This server enables LLMs to inspect database schemas and execute read-only queries.
Comments