What languages are supported?
Japanese, English, and Chinese (Simplified/Traditional). If the detected language is not one of these, the server returns an error.
@KunihiroS
Basic information
No overview available yet
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"kv-extractor-mcp-server": {
"command": "pipx",
"args": [
"run",
"kv-extractor-mcp-server",
"--log=off"
],
"env": {
"OPENAI_API_KEY": "<your-api-key>"
}
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
A Model Context Protocol (MCP) server that extracts key-value pairs from arbitrary, noisy, or unstructured text using GPT-4.1-mini and pydantic-ai. It ensures type safety and supports multiple output formats (JSON, YAML, TOML). Perfect extraction is not guaranteed.
Requires Python 3.9+ and an OpenAI API key set in settings.json. Run python server.py. The server exposes three tools: extract_json, extract_yaml, and extract_toml. When configuring the MCP host you must specify log mode via --log=off or --log=on --logfile=<absolute path>.
Japanese, English, and Chinese (Simplified/Traditional). If the detected language is not one of these, the server returns an error.
No. Extraction relies on LLMs and pydantic-ai, so perfect extraction is not guaranteed, especially with highly ambiguous or broken input.
TOML cannot represent arrays of objects or deeply nested structures. In such cases, complex values are stored as JSON strings in TOML. JSON and YAML can represent nested structures as-is.
Python 3.9+, an OpenAI API key, and an internet connection for LLM calls. On first launch, spaCy language models are downloaded automatically, which may take extra time.
Processing time varies. A sample measurement for 200 input tokens (~400 characters) took about 15 seconds with GPT-4.1-mini. Longer inputs and network conditions can increase time.
Open-source MCP to use Blender with any LLM
Senso MCP turns a Joomla 5 or 6 site into a remote MCP server. It runs inside Joomla itself (no extra server, no Node.js bridge) and is secured with OAuth 2.1 and Joomla's own ACL. The free pack lets an AI assistant crea

Soar Flight Booking MCP is a remote MCP server available at https://mcp.soar.flights.

Model Context Protocol Servers

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
Comments