# mcp-docparser

> Use this tool when you need to extract data from various document formats, such as PDFs, Word, Excel, and images, and require chunking and metadata extraction capabilities. It solves problems related to document parsing, data extraction, and text recognition through OCR. The tool takes in documents and images as input and outputs parsed text and metadata.

Canonical page: https://skillsregistry.net/skills/jasonzld-mcp-docparser  
JSON: https://api.skillsregistry.net/v1/skills/jasonzld-mcp-docparser

## Description

A lightweight document parser MCP server that enables Claude to parse PDFs, Word, Excel, images (OCR), and other document formats with support for chunking and metadata extraction.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/o9lhu542ks)
- **Repository:** <https://github.com/Jasonzld/mcp-docparser>

## 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": "jasonzld-mcp-docparser"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jasonzld-mcp-docparser` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jasonzld-mcp-docparser/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