WhoDB
A lightweight database workspace with an MCP server: the agent reads the schema, runs queries and explores data in PostgreSQL, MySQL and more
High risk
We rate an entry high when the tool writes to external systems, handles money, production databases or secrets, or runs arbitrary commands. The CLI installs it only with your consent.
Why this level
- Connects to databases and can modify data
- Runs queries with the connected database user's permissions
- AI features send content to the chosen provider
Install
In your terminal, with SkillFoxx CLI
npx skillfoxx add mcp/whodbDetects the agents on your machine, checks the risk and pins the version.
Other ways to install
This entry is high risk, so there is no one-click install. Review the code and add the config by hand.
Run in a terminal
claude mcp add --transport stdio whodb -- npx -y whodb mcp serveOr add to the file .mcp.json, in the project
{
"mcpServers": {
"whodb": {
"command": "npx",
"args": [
"-y",
"whodb",
"mcp",
"serve"
]
}
}
}If the file already exists, add the server inside the mcpServers key.
Add to the file ~/.cursor/mcp.json, for all projects
{
"mcpServers": {
"whodb": {
"command": "npx",
"args": [
"-y",
"whodb",
"mcp",
"serve"
]
}
}
}If the file already exists, add the server inside the mcpServers key. For a single project, put the same block into .cursor/mcp.json.
Run in a terminal
code --add-mcp '{"name":"whodb","type":"stdio","command":"npx","args":["-y","whodb","mcp","serve"]}'Or add to the file .vscode/mcp.json, in the project
{
"servers": {
"whodb": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"whodb",
"mcp",
"serve"
]
}
}
}If the file already exists, add the server inside the servers key.
Run in a terminal
codex mcp add whodb -- npx -y whodb mcp serveOr add to the file ~/.codex/config.toml, for all projects
[mcp_servers.whodb]
command = "npx"
args = ["-y", "whodb", "mcp", "serve"]If the file already exists, append the block to the end.
Add to the file ~/.gemini/settings.json, for all projects
{
"mcpServers": {
"whodb": {
"command": "npx",
"args": [
"-y",
"whodb",
"mcp",
"serve"
]
}
}
}If the file already exists, add the server inside the mcpServers key.
Add to the file ~/.config/devin/mcp_config.json, for all projects
{
"mcpServers": {
"whodb": {
"command": "npx",
"args": [
"-y",
"whodb",
"mcp",
"serve"
]
}
}
}If the file already exists, add the server inside the mcpServers key. Legacy Cascade keeps the MCP config in ~/.codeium/windsurf/mcp_config.json.
Formerly Windsurf.
Add to the file cline_mcp_settings.json, for all projects
{
"mcpServers": {
"whodb": {
"command": "npx",
"args": [
"-y",
"whodb",
"mcp",
"serve"
]
}
}
}If the file already exists, add the server inside the mcpServers key. Open the settings file in Cline: MCP Servers tab, Configure MCP Servers.
Add to the file .roo/mcp.json, in the project
{
"mcpServers": {
"whodb": {
"command": "npx",
"args": [
"-y",
"whodb",
"mcp",
"serve"
]
}
}
}If the file already exists, add the server inside the mcpServers key.
A fork of Roo Code, same .roo folders.
Add to the file opencode.json, in the project
{
"mcp": {
"whodb": {
"type": "local",
"command": [
"npx",
"-y",
"whodb",
"mcp",
"serve"
]
}
}
}If the file already exists, add the server inside the mcp key.
Add to the file ~/.config/zed/settings.json, for all projects
{
"context_servers": {
"whodb": {
"command": "npx",
"args": [
"-y",
"whodb",
"mcp",
"serve"
]
}
}
}If the file already exists, add the server inside the context_servers key.
Add to the file .codeassistant/mcp.json, in the project
{
"mcpServers": {
"whodb": {
"command": "npx",
"args": [
"-y",
"whodb",
"mcp",
"serve"
]
}
}
}If the file already exists, add the server inside the mcpServers key.
Run WhoDB with docker run --rm -it -p 8080:8080 clidey/whodb and open http://localhost:8080; for the agent, add the MCP server as npx -y whodb mcp serve in the client config.
Other ways from the author
docker run --rm -it -p 8080:8080 clidey/whodbStarts the WhoDB workspace at http://localhost:8080. Native installers and a CLI are also available.
This is third-party code. Review the repository files before installing.
What it does
WhoDB is a self-hosted database workspace: browse and edit data in a table grid, see a visual graph of tables and relationships, work in a query scratchpad with history and autocomplete, and import or export. It runs in the browser, as a desktop app and as a CLI, and supports PostgreSQL, MySQL, SQL Server, Oracle and other sources. For agents there is an MCP server started with npx whodb mcp serve that lets Claude, Cursor and other clients read the schema and run queries. The CLI includes agents for data analysis, query optimization and reports, and an installer can write skills, MCP config and rules into assistant directories. AI features are optional and run through a provider you choose.
Who it is for. For developers, analysts and data engineers who want database access and queries through an agent without a heavy client.
Good fit when
- You want the agent to explore the schema and run queries
- You want quick data browsing and editing without a heavy client
- You want text-to-SQL and data analysis through a chosen provider
Not a fit when
- You cannot give the agent access to a production database with write rights
- You only need the web interface without an agent connection
Example request
Show the table relationships in this database and build a query for last month's ordersLimitations
The MCP server needs database connection details, and the database user's permissions bound what it can do. AI features are optional and need your own provider, local or hosted. Change queries affect real data, so grant agent access deliberately and prefer a replica or test database.
How to disable. Remove the whodb entry from the MCP client config and stop the WhoDB container or app.
MCP
- Transport
- stdio
- Authentication
- not required
Security check
- Connects to databases and can modify data
- Runs queries with the connected database user's permissions
- AI features send content to the chosen provider
README in short
The README presents WhoDB as a lightweight self-hosted database workspace: a table grid, a visual schema graph, a query scratchpad, import and export and mock-data generation. It runs in the browser, as a desktop app, a snap and a CLI, installed via Docker or a native installer. AI features are optional and connect to Ollama, OpenAI, Anthropic, LM Studio or another compatible provider. It also ships an MCP server for assistants and a CLI with data analysis, query optimization and report agents, plus an installer for skills and config into assistant directories. Apache-2.0 licensed.
FAQ
How do I limit the agent?
Through the database user's permissions: give a read-only connection or a test database, and that bounds what the MCP server can do.
Is an AI provider required?
No. Browsing, editing and queries work without one; natural-language questions need a provider you choose.
Related
166 skills for scientific work: bioinformatics, cheminformatics, clinical data, geospatial analysis and 100+ databases
Google's open-source MCP server for databases: ready tools for Postgres, MySQL, BigQuery, Spanner and more, plus custom tools in tools.yaml
Official Hugging Face skills: Hub operations via the hf CLI, datasets, model training, Spaces, evals and deployment
A visualization language for agents and an MCP server: neat charts from a simple semantic spec