MCP For Claude Marketplace
Document Metadata Flattener

Document Metadata Flattener MCP Connector for Claude

A+

Flattens nested JSON metadata into dot-notation keys for vector store compatibility.

3 tools Official Updated Oct 1, 2026 Official Vinkius Partner
More Details Connect to Claude

This MCP server provides essential utilities to transform deeply nested JSON metadata structures into a flat, single-level dictionary. By converting hierarchical data into dot-notation (e.g., parent.child) and bracket-notation for arrays (e.g., tags[0]), it ensures compatibility with vector databases like Chroma and FAISS that require flat metadata for efficient filtering. Use flatten_metadata to perform the transformation, validate_metadata_schema to check nesting depth, or get_metadata_summary to analyze structural complexity.

jsonmetadataflatteninglangchainvector-store

3 tools expose this connector's capabilities to your AI agent.

flatten_metadata

Converts a complex nested metadata object into a flat dictionary with dot/bracket notation keys

get_metadata_summary

Provides a high-level statistical overview of a metadata object complexity

validate_metadata_schema

Checks if a metadata object meets depth or structural constraints

See how to talk to your AI agent using Document Metadata Flattener.

Flatten this metadata: {"source": {"url": "https://example.com", "page": 1}, "tags": ["news", "tech"]}

{"source.url": "https://example.com", "source.page": 1, "tags[0]": "news", "tags[1]": "tech"}

Check the complexity of this metadata object.

The metadata has a nesting complexity of 'moderate' with 5 leaf nodes and contains arrays.

Is this metadata object too deep for processing?

The object is valid and meets the required depth constraints for processing.

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.

Related Connectors

Statamic

Statamic MCP

14 tools Official

Manage your Statamic CMS content—list entries, fetch taxonomy terms, inspect global sets, and explore site navigation directly from your AI agent.

A+ View details →
Statistics Engine

Statistics Engine MCP

5 tools Official

A zero-latency statistical engine to process datasets. Instantly compute the exact mean, median, mode, standard deviation, and percentiles completely local.

A+ View details →
OpenStreetMap

OpenStreetMap MCP

33 tools Official

Access and edit OpenStreetMap data — manage changesets, query map elements, and retrieve geospatial data directly from any AI agent.

A+ View details →
OpenStreetMap (Geocoding & Places)

OpenStreetMap (Geocoding & Places) MCP

4 tools Official

Geocode any city or address to coordinates and back — forward/reverse geocoding, place search and location details via OpenStreetMap. No API key.

A+ View details →