What databases does Whodb support?
Community Edition supports PostgreSQL, MySQL, SQLite3, MongoDB, Redis, MariaDB, and ElasticSearch. Enterprise Edition adds Oracle, SQL Server, DynamoDB, Athena, Snowflake, Cassandra, and more.
@clidey
Basic information
WhoDB CLI - a powerful database management tool with interactive TUI, programmatic commands, and MCP server for AI assistants.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"whodb": {
"command": "npx",
"args": [
"-y",
"@clidey/whodb-cli",
"mcp",
"serve"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
Whodb is a lightweight (<50MB) database management tool that supports PostgreSQL, MySQL, SQLite3, MongoDB, Redis, MariaDB, ElasticSearch (Community Edition) and additional databases in the Enterprise Edition. It includes a CLI with an MCP (Model Context Protocol) server for AI assistants like Claude and Cursor.
Install the CLI via curl -fsSL https://raw.githubusercontent.com/clidey/whodb/main/cli/install/install.sh | bash, npm install -g @clidey/whodb-cli, or upcoming Homebrew. Launch the interactive TUI with whodb-cli or run the MCP server with whodb-cli mcp serve. The server listens on port 8080 by default.
Community Edition supports PostgreSQL, MySQL, SQLite3, MongoDB, Redis, MariaDB, and ElasticSearch. Enterprise Edition adds Oracle, SQL Server, DynamoDB, Athena, Snowflake, Cassandra, and more.
Set environment variables for your AI provider: `WHODB_OLLAMA_HOST` for Ollama, `WHODB_OPENAI_API_KEY` for OpenAI, `WHODB_ANTHROPIC_API_KEY` for Anthropic, or `WHODB_AI_GENERIC_<ID>_*` for any OpenAI-compatible endpoint.
No. Docker is a recommended quick start (run `docker run -it -p 8080:8080 clidey/whodb`), but you can also install the CLI directly or build from source with Go and Node.js.
The MCP server allows AI assistants like Claude and Cursor to interact with databases through the Model Context Protocol. Run `whodb-cli mcp serve` to start it.
Data is stored in the connected databases (not in Whodb itself). For SQLite, you can mount a volume to persist the file. Whodb is stateless and does not store your data.

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
🚀 The fast, Pythonic way to build MCP servers and clients.
Comments