feat(mongodb): add MongoDB Atlas Tool and Voyage AI plugins

[Pash10g]

Toolset 1 — MongoDB Atlas Tool

1. Metadata

• Plugin Author: mongodb
• Plugin Name: mongodb_atlas_tool
• Repository URL: https://github.com/Pash10g/dify-plugins

2. Submission Type

• New plugin submission
• Version update for existing plugin

3. Description

MongoDB Atlas Tool plugin for Dify. Enables Chatflow, Workflow, and Agent applications to query, search, and write documents directly in MongoDB Atlas. Includes 7 tools: find, full_text_search, vector_search, aggregate, insert_one, update_many, and delete_many.

4. Checklist

• I have read and followed the Publish to Dify Marketplace guidelines
• I have read and comply with the Plugin Developer Agreement
• I confirm my plugin works properly on both Dify Community Edition and Cloud Version
• I confirm my plugin has been thoroughly tested for completeness and functionality
• My plugin brings new value to Dify

5. Documentation Checklist

• Step-by-step setup instructions
• Detailed usage instructions
• All required APIs and credentials are clearly listed
• Connection requirements and configuration details
• Link to the repository for the plugin source code

6. Privacy Protection Information

Data Collection

The plugin collects a MongoDB Atlas connection string (URI) and optionally a database name. No personal user data is collected or stored by the plugin itself. All data operations occur directly between the Dify runtime and the user's own MongoDB Atlas cluster.

Privacy Policy

• I confirm that I have prepared and included a privacy policy in my plugin package based on the Plugin Privacy Protection Guidelines

---

Toolset 2 — Voyage AI

1. Metadata

• Plugin Author: mongodb
• Plugin Name: voyage_ai
• Repository URL: https://github.com/Pash10g/dify-plugins

2. Submission Type

• New plugin submission
• Version update for existing plugin

3. Description

Voyage AI plugin for Dify. Generates vector embeddings and reranks documents using Voyage AI models hosted on MongoDB Atlas. Includes 2 tools: embed (text → float-array embedding with input_type support) and rerank (scored document relevance ranking). Designed to chain with the MongoDB Atlas Tool plugin for vector search workflows.

4. Checklist

• I have read and followed the Publish to Dify Marketplace guidelines
• I have read and comply with the Plugin Developer Agreement
• I confirm my plugin works properly on both Dify Community Edition and Cloud Version
• I confirm my plugin has been thoroughly tested for completeness and functionality
• My plugin brings new value to Dify

5. Documentation Checklist

• Step-by-step setup instructions
• Detailed usage instructions
• All required APIs and credentials are clearly listed
• Connection requirements and configuration details
• Link to the repository for the plugin source code

6. Privacy Protection Information

Data Collection

The plugin collects a MongoDB Atlas API key (public + private) and Group ID for authentication. No personal user data is collected or stored by the plugin itself. Embedding and rerank requests are sent to the user's own MongoDB Atlas Voyage AI endpoint.

Privacy Policy

• I confirm that I have prepared and included a privacy policy in my plugin package based on the Plugin Privacy Protection Guidelines