302AI File Parser MCP Server
# 302AI File Parser MCP Server
## Development
Install dependencies:
```bash
npm install
```
Build the server:
```bash
npm run build
```
For development with auto-rebuild:
```bash
npm run watch
```
## Installation
To use with Claude Desktop, add the server config:
On MacOS: `~/Library/Application Support/Claude/claude_desktop_config.json`
On Windows: `%APPDATA%/Claude/claude_desktop_config.json`
```json
{
"mcpServers": {
"302ai-file-parser-mcp": {
"command": "npx",
"args": ["-y", "@302ai/file-parser-mcp"],
"env": {
"302AI_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}
```
Find Your 302AI_API_KEY [here](https://dash.302.ai/apis/list)
### Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the [MCP Inspector](https://github.com/modelcontextprotocol/inspector), which is available as a package script:
```bash
npm run inspector
```
The Inspector will provide a URL to access debugging tools in your browser.TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly distinct as it is the sole operation available.
The single tool name follows a clear verb_noun pattern (parseFileToText), and with only one tool, consistency is inherently perfect as there are no other names to compare against.
A single tool is generally too few for a server named 'File Parser', as this suggests a domain that might include operations like parsing different file types, handling errors, or extracting metadata. The scope feels incomplete with just one basic parsing function.
The server's name implies a broader file parsing capability, but the tool set only includes parsing files to text. Obvious gaps include support for different file formats (e.g., PDF, DOCX), structured data extraction, or error handling, making the surface severely incomplete for the apparent purpose.