KunihiroS_kv-extractor-mcp-server

KunihiroS_kv-extractor-mcp-server

3.2

If you are the rightful owner of KunihiroS_kv-extractor-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

The Flexible Key-Value Extracting MCP Server is designed to extract key-value pairs from unstructured text using LLMs and pydantic-ai, supporting multiple output formats.

The Flexible Key-Value Extracting MCP Server is a robust solution for extracting key-value pairs from arbitrary, noisy, or unstructured text. Utilizing LLMs (GPT-4.1-mini) and pydantic-ai, it ensures type safety and supports output in JSON, YAML, and TOML formats. The server is designed to handle complex inputs and provides consistent, predictable outputs, even when faced with challenging data. It features automatic key discovery, advanced multi-lingual preprocessing, and iterative refinement processes to enhance extraction accuracy. The server is particularly useful for applications requiring reliable data structuring from unpredictable text sources.

Features

  • Flexible extraction: Handles any input, including noisy or broken data.
  • JP / EN / ZH-CN / ZH-TW full support: Preprocessing with spaCy NER by automatic language detection.
  • Type-safe output: Uses Pydantic for output validation.
  • Multiple formats: Returns results as JSON, YAML, or TOML.
  • Robust error handling: Always returns a well-formed response, even on failure.

Tools

  1. /extract_json

    Extract type-safe key-value pairs from the input text, returning to JSON format

  2. /extract_yaml

    Extract type-safe key-value pairs from the input text and return to YAML format

  3. /extract_toml

    Extract type-safe key-value pairs from the input text and return to TOML format