Document Metadata Flattener Connector for AI agents.
3 live capabilities
Convert nested JSON into flat metadata for vector database filtering
Waiting for input…
Why people use Document Metadata Flattener
Solve nested JSON issues with Document Metadata Flattener
This MCP changes that by automating the transformation. Instead of writing custom logic for every new document type, you just hand the nested object to your agent. It flattens everything into a clean, single-level dictionary using standard notation. You get data that is immediately ready for high-performance filtering in your vector database.
What Vinkius changes
You get database-ready metadata without writing custom transformation scripts.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 6,100+ Connectors
- Real-world use case 01
Fixing broken RAG queries
An engineer finds that their agent can't filter by 'author' because it's buried in a nested object.
- Real-world use case 02
Preparing large datasets for FAISS
A developer needs to upload thousands of documents to FAISS and uses the flattening capability to ensure every attribute is a top-level key.
- Real-world use case 03
Validating incoming document streams
A data pipeline uses the schema validation capability to reject documents that are too deeply nested for the target database.
Complete set · 3capabilities
The complete Document Metadata Flattener capability set.
These are the exact actions your AI can choose when you ask it to work with Document Metadata Flattener.
01—03
3 capabilities in this set.
Part of 3 available through Document Metadata Flattener.
- 01 Capability
Flatten metadata
Turns complex nested objects into a flat dictionary using dot and bracket notation. This makes your data compatible with most vector stores.
- 02 Capability
Get metadata summary
Generates a statistical overview of your metadata's complexity. It helps you understand the structure before you process it.
- 03 Capability
Validate metadata schema
Checks if your metadata meets specific depth or structural rules. This prevents errors during database ingestion.
Set up in minutes
One URL. Then ask Document Metadata Flattener to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Document Metadata Flattener from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_In3DaGgXDVcW9RVIFpMfZTI206Iz8HGz6620407g/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Document Metadata Flattener, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Document Metadata Flattener for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_In3DaGgXDVcW9RVIFpMfZTI206Iz8HGz6620407g/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Document Metadata Flattener URL.
- Step 03
Save and start
Save the connection and enable Document Metadata Flattener in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"document-metadata-flattener": {
"url": "https://edge.vinkius.com/vk_preview_In3DaGgXDVcW9RVIFpMfZTI206Iz8HGz6620407g/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Document Metadata Flattener
Open Agent mode in chat and ask: "Using Document Metadata Flattener, help me...". 3 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"document-metadata-flattener": {
"url": "https://edge.vinkius.com/vk_preview_In3DaGgXDVcW9RVIFpMfZTI206Iz8HGz6620407g/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Document Metadata Flattener
Ask Copilot: "Using Document Metadata Flattener, help me...". 3 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"document-metadata-flattener": {
"url": "https://edge.vinkius.com/vk_preview_In3DaGgXDVcW9RVIFpMfZTI206Iz8HGz6620407g/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Document Metadata Flattener
Open Cascade and ask: "Using Document Metadata Flattener, help me...". 3 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"document-metadata-flattener": {
"url": "https://edge.vinkius.com/vk_preview_In3DaGgXDVcW9RVIFpMfZTI206Iz8HGz6620407g/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Document Metadata Flattener
Ask Cline: "Using Document Metadata Flattener, help me...". 3 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add document-metadata-flattener --transport http "https://edge.vinkius.com/vk_preview_In3DaGgXDVcW9RVIFpMfZTI206Iz8HGz6620407g/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Document Metadata Flattener
Ask Claude: "Using Document Metadata Flattener, show me...". 3 tools are ready
Where the request belongs
Work Document Metadata Flattener can move forward.
This is for data engineers and AI developers who are tired of their vector database queries failing because of nested JSON structures.
AI Engineer
Prepares document embeddings and metadata for RAG pipelines on a Tuesday afternoon.
Data Engineer
Cleans and transforms unstructured JSON data into formats compatible with FAISS or Chroma.
MLOps Engineer
Validates metadata schemas to ensure automated ingestion pipelines don't break.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsMongoDB Atlas Vector Search
Manage vector storage via MongoDB Atlas. perform similarity searches, query MQL documents, and audit collections.
Elasticsearch Vector
Empower vector search via Elasticsearch. perform dense vector kNN searches, handle index mappings, and index embedding documents directly from any AI agent.
ClickHouse (Vector Search)
Manage vector embeddings and SQL via ClickHouse. list databases, execute SQL, and perform high-speed vector searches directly from any AI agent.
Pinecone
Equip your AI agent to manage your Pinecone vector databases. Query embeddings, fetch metrics, manage collections, and run stats natively via chat.
X Ads (Twitter)
Connect your X Ads account to any AI agent. audit campaigns, analyze line item performance, and pull engagement reports through natural conversation.
Box
Store, share, and collaborate on files securely with enterprise-grade cloud content management and governance controls.
Bring your own AI
Change the model, client or framework. Keep Document Metadata Flattener connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Document Metadata Flattener.
The practical details behind the request, access and result.
How does Document Metadata Flattener help with vector databases?
It converts nested JSON into a flat format that databases like Chroma and FAISS can actually use for filtering. This makes your document searches much more accurate.
Can I use Document Metadata Flattener with any JSON data?
Yes, it is designed to handle complex, hierarchical JSON objects and turn them into single-level dictionaries using dot and bracket notation.
Will Document Metadata Flattener break my existing data?
No, it simply transforms the structure. You can use the validation capability to check your data before you perform any transformations to ensure it meets your needs.
What is the difference between dot-notation and bracket-notation here?
The capability uses dot-notation (like parent.child) for objects and bracket-notation (like array[0]) for lists, ensuring a standard way to access your flattened data.
How do I know if my metadata is too deep for my database?
You can use the summary capability to check the complexity or the validation capability to see if the nesting depth exceeds your specific requirements.
Why do I need to flatten my metadata?
Many vector databases, such as Chroma or FAISS, cannot filter based on nested JSON objects. Flattening converts these into a single level of keys, making them searchable.
How does the capability handle arrays?
The capability uses bracket-notation for array elements. For example, an array at tags becomes tags[0], tags[1], etc.
What happens if there is a key collision?
If two different paths result in the same flattened key, the capability detects the collision and prioritizes the first encountered value to prevent silent data loss.
One connection away
Give your agent a direct line to Document Metadata Flattener.
Connect Document Metadata Flattener once. Keep it beside 6,100+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available