aggregate
Run an aggregation pipeline on a MongoDB collection
LABSCO SUMMARY
getSchema is the reason to pick this over a bare Mongo connection.
An agent guessing at field names in a schemaless collection burns several queries getting empty results back. getSchema returns the field names and their types up front, so find and aggregate get written against what the documents actually contain. Writes are single-document only — insertOne, updateOne, deleteOne — so a filter that matches more than you expected still touches one record.
What it is
A MongoDB server over one connection string: the usual reads — find, findOne, aggregate, count, distinct — single-document writes, a collection listing, and a getSchema call that reports the field names and types a collection actually holds.
What you get
- Documents matching a filter, with sort and limit for paging through them
- A single document by filter, when one is all you want
- Aggregation pipelines run as written — $match, $group and the rest
- A count of the documents matching a filter
- The distinct values a field takes across a collection
- The collections in the database, with an optional filter
- Field names and types for a collection, analysed from the documents in it
- Single-document insert, update and delete
Requirements
MONGODB_URI, a full connection string — MongoDB Atlas and authenticated deployments both work. MONGODB_DATABASE names the default database and is optional. Installs from npm as @sourabhshegane/mongodb-mcp-that-works.
Setup effort
One command — npx -y @sourabhshegane/mongodb-mcp-that-works@latest
USE CASES
01
Working out what is in a collection nobody documented
List the collections, then read back the field names and types instead of paging through sample documents.
02
Answering a question that needs a grouped aggregation
Check the field names first, then run the pipeline as written and get the grouped result back.
03
Checking whether a record exists before acting on it
Fetch the one document by filter, or count how many match, before anything is written.
04
Seeing the range of values a status field takes
Get the distinct values across the collection, which is faster than reading documents to find out.
05
Fixing one wrong document
Find the record by filter, confirm it is the right one, then update that single document.
06
Pulling a filtered, sorted page of records into the conversation
Query with a filter, a sort and a limit so the model reads a page rather than the collection.
10 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
count
Count documents in a MongoDB collection
deleteOne
Delete a single document from a MongoDB collection
distinct
Get distinct values for a field in a MongoDB collection
find
Find documents in a MongoDB collection
findOne
Find a single document in a MongoDB collection
getSchema
Analyze collection structure and return field names with types
insertOne
Insert a single document into a MongoDB collection
listCollections
List all collections in the database
updateOne
Update a single document in a MongoDB collection
BEFORE YOU INSTALL
What to know first
Tools you get
10 tools when we connected.
Requires
- npx on PATH
- MONGODB_URI in your environment
Optional
MONGODB_DATABASE in your environment
CONTEXT COST
Light Standing cost
Rated by the size of the 10 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Add the block to your client, or run the command directly.
Server setup
Configuration file
JSON
{
"mcpServers": {
"mongodb": {
"command": "npx",
"args": [
"-y",
"@sourabhshegane/mongodb-mcp-that-works@latest"
],
"env": {
"MONGODB_URI": "mongodb+srv://<YOUR_DB_USER>:<YOUR_DB_PASSWORD>@cluster.mongodb.net/<YOUR_DB_NAME>",
"MONGODB_DATABASE": "<YOUR_MONGODB_DATABASE>"
}
}
}
}npx
TERMINAL
npx -y @sourabhshegane/mongodb-mcp-that-works@latest
