Skip to main content
Glama
yooumuu

ParseJet - Universal File & URL Parser

by yooumuu
README.md
# @parsejet/mcp-server

MCP (Model Context Protocol) server for the [ParseJet](https://parsejet.com) API. Lets AI agents like Claude Code and Cursor parse files, URLs, and YouTube transcripts.

## Tools

| Tool | Description |
|------|-------------|
| `parse_url` | Parse any URL (web page, YouTube, PDF link, etc.) |
| `parse_file` | Parse a local file (PDF, DOCX, image, etc.) |
| `get_youtube_transcript` | Get a YouTube video transcript |

## Installation

```bash
npm install -g @parsejet/mcp-server
```

Or run directly with npx:

```bash
npx @parsejet/mcp-server
```

## Configuration

### API Key (optional)

Set the `PARSEJET_API_KEY` environment variable to authenticate. Without it, the server works anonymously with a limit of 3 requests per day.

Get your API key at [parsejet.com/dashboard](https://parsejet.com/dashboard).

### Claude Code

Add to your project's `.claude/settings.json` (or global `~/.claude/settings.json`):

```json
{
  "mcpServers": {
    "parsejet": {
      "command": "npx",
      "args": ["-y", "@parsejet/mcp-server"],
      "env": {
        "PARSEJET_API_KEY": "your-api-key"
      }
    }
  }
}
```

### Cursor

Add to your Cursor MCP config (Settings > MCP Servers):

```json
{
  "mcpServers": {
    "parsejet": {
      "command": "npx",
      "args": ["-y", "@parsejet/mcp-server"],
      "env": {
        "PARSEJET_API_KEY": "your-api-key"
      }
    }
  }
}
```

If installed globally, you can use `parsejet-mcp` instead of `npx`:

```json
{
  "mcpServers": {
    "parsejet": {
      "command": "parsejet-mcp",
      "env": {
        "PARSEJET_API_KEY": "your-api-key"
      }
    }
  }
}
```

## Usage Examples

Once configured, your AI agent can use these tools:

**Parse a web page:**
> "Parse https://example.com and give me a summary"

**Parse a local PDF:**
> "Parse the file at /path/to/document.pdf as markdown"

**Get a YouTube transcript:**
> "Get the transcript of https://www.youtube.com/watch?v=dQw4w9WgXcQ"

**Parse with specific output format:**
> "Parse https://example.com as markdown"

## Development

```bash
# Install dependencies
npm install

# Build
npm run build

# Run locally
node dist/index.js
```

## Links

- [ParseJet](https://parsejet.com) — Official website
- [Documentation](https://parsejet.com/docs) — API reference and guides
- [Get API Key](https://parsejet.com/dashboard) — Free API key (300 credits/month)
- [Pricing](https://parsejet.com/pricing) — Plans and pricing
- [TypeScript SDK](https://www.npmjs.com/package/parsejet) — `npm install parsejet`
- [Supported Formats](https://parsejet.com/docs#formats) — PDF, DOCX, YouTube, web pages, images, and 25+ more

## License

MIT

TDQS

B3.4/5.0

Scored across 3 tools

Disambiguation4/5

Tools mostly distinct: parse_file handles local files, parse_url handles any URL, get_youtube_transcript is specialized for YouTube transcripts. There is slight overlap between get_youtube_transcript and parse_url for YouTube videos, but descriptions clarify different intents.

Naming Consistency4/5

Two tools follow a parse_* pattern, while get_youtube_transcript breaks consistency with a get_ prefix. This is a minor deviation but still understandable.

Tool Count3/5

3 tools for a 'Universal File & URL Parser' feels slightly thin but not unreasonable. The scope is covered by the two parse tools, with the transcript tool as an additional feature.

Completeness4/5

Core functionality (parsing local files and URLs) is covered. Missing explicit tools for structured data parsing (e.g., JSON, XML) but the parse_file and parse_url tools claim broad support. Minor gaps but adequate for common tasks.

Maintenance

ActivityInactive
ResponsivenessNo issues