# LangExtract

> Use this tool when you need to extract structured information from unstructured text, such as in healthcare document processing, legal contract analysis, or research paper extraction. LangExtract provides fast and accurate text extraction with precise source grounding, mapping every extraction to its exact location in the original text. It accepts unstructured text inputs and outputs structured information, making it ideal for use cases where maintaining traceability between extracted data and source text is critical.

Canonical page: https://skillsregistry.net/skills/larsenweigle-langextract  
JSON: https://api.skillsregistry.net/v1/skills/larsenweigle-langextract

## Description

FastMCP server implementation by Larsen Weigle that provides structured information extraction from unstructured text using Google's LangExtract library and Gemini models. The server maintains persistent connections and intelligent caching for optimal performance in long-running environments like Claude Code, offering tools for text extraction, URL processing, result visualization, and file operations with precise source grounding that maps every extraction to its exact location in the original text. Built with server-side credential management and optimized for Google Gemini models (gemini-2.5-flash and gemini-2.5-pro), it serves use cases across healthcare document processing, legal contract analysis, research paper extraction, and business intelligence workflows where maintaining traceability between extracted structured data and source text is critical.

## Trust

- **Trust score (0–1):** 0.96
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** maps-location
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/larsenweigle-langextract)
- **Repository:** <https://github.com/larsenweigle/langextract-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "larsenweigle-langextract"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/larsenweigle-langextract` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/larsenweigle-langextract/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt