ParseJet - Universal File & URL Parser
# @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
Scored across 3 tools
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.
Two tools follow a parse_* pattern, while get_youtube_transcript breaks consistency with a get_ prefix. This is a minor deviation but still understandable.
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.
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.