listCollectionsLABSCO SUMMARY
Schema inspection matters more in MongoDB than anywhere else, because there is no schema to read.
In a relational database the model can be handed a table definition. In MongoDB the shape lives in the documents, varies between them, and drifts over time — so a query written from an assumption fails silently by matching nothing. Being able to sample the actual structure first is what makes generated queries land. As always with database access, the write half deserves a separate decision from the read half.
What it is
A server that connects a model to a MongoDB database, covering the read path and the write path.
What you get
- Querying collections
- Schema inspection, so the shape of the data is discoverable rather than assumed
- Managing the data itself
Requirements
Node.js 18 or higher, and a connection to the database. MIT licensed.
Setup effort
Add the configuration to your client
USE CASES
01
Asking a question of the data
Query the collection directly.
02
Finding out what the documents look like
Inspect the real shape before writing a query.
8 tools
Listed in project docs. Your client may show a different list.
findinsertOneupdateOnedeleteOnecreateIndexdropIndexindexesBEFORE YOU INSTALL
What to know first
Tools you get
8 tools named in the project's documentation.
Requires
- Node.js 18 or higher
- A MongoDB instance (local or remote) and its connection string
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
MCP Clients
Claude Desktop — npx
CLAUDE DESKTOP — NPX · JSON
{
"mcpServers": {
"mongodb": {
"command": "npx",
"args": [
"mongo-mcp",
"mongodb://<YOUR_USERNAME>:<YOUR_PASSWORD>@<YOUR_HOST>:<YOUR_PORT>/<YOUR_DATABASE>?authSource=admin"
]
}
}
}
