MongoDB Atlas Tool Plugin for Dify

A Tool-type Dify plugin that lets Chatflow, Workflow, and Agent applications query, search, and write documents in MongoDB Atlas directly from a workflow node or agent tool call.

Companion plugins:

Use the Voyage AI plugin to generate real vector embeddings and pipe them into the Vector Search tool's Query Vector field.

Use the MongoDB Atlas Datasource plugin to feed Atlas collections into the Dify Knowledge Base / RAG pipeline.

Features

Tool	Description
Find Documents	Query a collection with an optional MongoDB filter and projection
Full-Text Search	Atlas full-text search (requires an Atlas Search index)
Vector Search	Atlas ANN search — accepts a pre-computed embedding vector
Aggregate	Run any raw aggregation pipeline
Insert Document	Insert a single document and get back its
Update Documents	with a filter + update operator JSON
Delete Documents	with a filter JSON

Prerequisites

A MongoDB Atlas cluster (M0 free tier is sufficient for testing)
A connection string:
For Full-Text Search: an Atlas Search index on the target collection
For Vector Search: an Atlas Vector Search index on the target collection

Installation

From Dify Marketplace

Search for MongoDB Atlas Tool in the Dify Plugin Marketplace and click Install.

Local / Debug Install

Clone or download this repository.
Copy to and fill in your Dify remote debug URL and key.
Install dependencies:
Run the plugin:
The plugin will appear in your Dify workspace under Plugins.

Package for distribution

Configuration

When installing the plugin, you will be prompted for:

Credential	Required	Description
Connection String	✅

Tool Reference

Find Documents

Query documents using a MongoDB filter.

Type	Required	Form	Description
string	✅	form	Database to query
string	✅	llm	Collection to query
string	❌	llm	JSON filter, e.g.
string	❌	llm	JSON projection, e.g.
number	❌	form	Max documents to return (default 20, max 1000)

Output (JSON): Each document is yielded as its own JSON message — is the first document, is the second, etc. Results are directly iterable in Dify's Iterate/Loop nodes.

Full-Text Search

Atlas across all text fields. Requires an Atlas Search index.

Output (JSON): Each document is yielded as its own JSON message — directly iterable.
Output (text): A JSON array of stringified documents, pipeable to the Rerank tool's parameter.
Each document includes a field.

Vector Search

Atlas approximate nearest-neighbour search. Requires an Atlas Vector Search index.

Type	Required	Form	Description
string	✅	form	Database
string	✅	llm	Collection
string	✅*	llm	Pre-computed embedding as a JSON float array
string	✅*	llm	Fallback text query (uses placeholder zero-vector — use Voyage AI plugin for real embeddings)
string	❌	form	Vector Search index name (default )
string	❌	form	Embedding field name (default )
number	❌	form	ANN candidates (default 150, must be ≥ limit)
number	❌	form	Max results (default 20)

* Provide either or .

Tip: Use the Voyage AI plugin's Embed Text tool to generate . The output variable can be piped directly into — the plugin automatically handles the array format.

Aggregate

Run a raw MongoDB aggregation pipeline.

Type	Required	Form	Description
string	✅	form	Database
string	✅	llm	Collection
string	✅	llm	Pipeline as JSON array, e.g.
number	❌	form	Safety cap — appended automatically if no stage present (default 100)

Output (JSON): Each result document is yielded as its own JSON message — directly iterable.

Insert Document

Output:

Update Documents

Output:

Delete Documents

⚠️ Passing as deletes all documents in the collection.

Output:

Recommended Workflow (with Voyage AI)

Note: All query/search tools yield one JSON message per document. This means , , etc. are individual documents — you can pipe the output directly to an Iterate or Loop node without extracting a nested field.

Observability

All connections use , which appears in Atlas logs and the Atlas Monitoring dashboard under Application Names.

Support

GitHub Issues: https://github.com/mongodb-developer/dify-plugins-mongodbatlas-tool/issues
MongoDB Developer Community: https://www.mongodb.com/community/forums/

License

Apache 2.0 — see LICENSE [blocked] for details.