ModuleX
Integrations
MongoDB Atlas logo

MongoDB Atlas integration

Vector Database · 6 actions · Custom auth

MongoDB Atlas with Vector Search: semantic search on your existing data via native $vectorSearch aggregations, plus database/collection introspection and document insert/delete. Uses the PyMongo async driver with your own connection string.

Put MongoDB Atlas to workView MongoDB Atlas integration docs

The ModuleX MongoDB Atlas integration lets a ModuleX agent operate MongoDB Atlas on your behalf — running remove and list actions across queries, databases and collections — directly from a plain-English request, using your organization's own MongoDB Atlas credentials. No pre-built workflow is required: the agent picks the right MongoDB Atlas action for the task.

MongoDB Atlas is a vector database platform. ModuleX adds the agent layer: ask for an outcome and it selects and runs the right MongoDB Atlas action — or, when you want a repeatable process, the composer assembles a MongoDB Atlas workflow for you, streaming the nodes onto the canvas as it builds.

Drive MongoDB Atlas in plain English

Type what you want. A ModuleX agent picks the right MongoDB Atlas action, or chains several, and runs it. No workflow to build.

  • “Delete documents matching a non-empty MQL filter (empty filters are rejected)”
    resolves todelete_documents
  • “Show me the queries that match what I describe”
    resolves toquery

What you can automate with MongoDB Atlas

  • Query your queries from a plain-English questionquery
  • Pull a list of databases for a reportlist_databases
  • Remove a document you no longer needdelete_documents

MongoDB Atlas integration at a glance

VendorMongoDB Atlas
CategoryVector Database
Actions available6
AuthenticationCustom
Uses your own credentialsYes
Works with the assistantYes
Works in the composerYes
Multi-step / tool-chainingYes
Technical referenceView docs
Integration version1.0.0
Last updatedJul 2026

All 6 MongoDB Atlas actions

Queries1
query
Vector similarity search via an Atlas $vectorSearch aggregation. Takes a query VECTOR — Atlas has no server-side text embedding, so embed the query before calling. Returns native documents plus a score field, in MongoDB Relaxed Extended JSON.
Databases1
list_databases
List all databases in the cluster.
Collections1
list_collections
List collections in a database (native entries).
Search Indexes1
list_search_indexes
List Atlas Search / Vector Search indexes on a collection — discover the index name, vector path, and dimensions needed by query.
Documents2
insert_documents
Insert documents into a collection.
delete_documents
Delete documents matching a non-empty MQL filter (empty filters are rejected).

See full parameters and response schemas in the MongoDB Atlas integration docs

Two ways to use MongoDB Atlas in ModuleX

Ask the assistantType what you want done and a ModuleX agent picks the right MongoDB Atlas action and runs it. No workflow to build.
Compose a workflowNeed it to happen every time? Describe the process and the composer wires MongoDB Atlas into a repeatable workflow you can run on a schedule, from chat, or as an API.

Connecting MongoDB Atlas

CustomMongoDB Atlas uses a custom authentication flow. ModuleX encrypts whatever credentials you supply and scopes them to your organization.

Step-by-step setup in the MongoDB Atlas docs

Pairs well with MongoDB Atlas

Agents often chain MongoDB Atlas with these. Connect them once and the agent can use all of them in a single task.

Pinecone9 actionsQdrant7 actionsWeaviate7 actions

MongoDB Atlas + ModuleX FAQ

  • A ModuleX agent can run any of MongoDB Atlas's 6 actions — across queries, databases, collections and search indexes — from a plain-English request, using your organization's own MongoDB Atlas credentials.

Put MongoDB Atlas to work in ModuleX.

Put MongoDB Atlas to workView technical docs

Connect MongoDB Atlas once with your own credentials and let your agent run all 6 actions on demand.

Last updated: Jul 2026Browse all 179 integrations