mcpField
P

Packforai Mcp

Local
github.com/zymsj8j9z9-ship-itProductivity0Updated 16w ago

About Packforai Mcp

PackForAI MCP converts common document formats into AI-ready Markdown for people working with documents in Claude, Cursor, and other MCP clients. It accepts local files or public URLs and supports OCR for scanned PDFs and full-document output.

Key features

  1. 01Converts six document formats
  2. 02Produces compact Markdown
  3. 03OCR for scanned PDFs
  4. 04Processes local files or URLs
  5. 05Can return full document content
  6. 06Includes a token-savings summary

Use cases

  1. 01Convert report PDFs to Markdown
  2. 02Convert DOCX files from public URLs
  3. 03Extract content from scanned PDFs with OCR

MCP support

The server exposes the `convert_document` tool to MCP clients. It converts documents from a local path or public HTTPS URL and returns Markdown with a token-savings summary.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"packforai": {
"command": "npx",
"args": [
"-y",
"packforai-mcp"
],
"env": {
"PACKFORAI_API_KEY": "<PACKFORAI_API_KEY>"
}
}
}
}
Run commandnpx -y packforai-mcp
Environment variables to set
PACKFORAI_API_KEYSecretYour PackForAI API key (Pro plan). Create one at https://packforai.com/account

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmpackforai-mcp0.1.1

Tools

1

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
pathstringNoAbsolute path to a local document file to convert.
urlstringNoPublic https URL of a document to fetch and convert.
ocrbooleanNoForce OCR for scanned or image-only PDFs (Pro). Defaults to false.
fullbooleanNoReturn the full document.md (e.g. complete spreadsheet tables) instead of the compact version. Defaults to false.

Details

From the project README

PackForAI MCP server

Convert PDF, DOCX, PPTX, XLSX, CSV and JSON into clean, compact, AI-ready Markdown, directly inside Claude, Cursor and any other MCP client. Powered by PackForAI.

Instead of pasting a messy PDF into your AI (broken text, lost tables, wasted tokens), ask your assistant to convert it first: it comes back as clean Markdown with up to 65% fewer tokens.

What you need

Install

The server runs via npx, so there is nothing to install globally. Add it to your MCP client's config.

Claude Desktop

Edit claude_desktop_config.json (Settings → Developer → Edit Config) and add:

{
  "mcpServers": {
    "packforai": {
      "command": "npx",
      "args": ["-y", "packforai-mcp"],
      "env": { "PACKFORAI_API_KEY": "your_key_here" }
    }
  }
}

Restart Claude Desktop.

Cursor

Add to .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):

{
  "mcpServers": {
    "packforai": {
      "command": "npx",
      "args": ["-y", "packforai-mcp"],
      "env": { "PACKFORAI_API_KEY": "your_key_here" }
    }
  }
}

Usage

Once connected, just ask your assistant, for example:

  • "Convert ~/Downloads/Q4-report.pdf to clean Markdown."
  • "Fetch https://example.com/spec.docx and give me the AI-ready version."
  • "Convert this scanned PDF with OCR: /path/to/scan.pdf."
Tool

convert_document

ParamTypeDescription
pathstringAbsolute path to a local document file.
urlstringPublic https URL of a document to fetch and convert.
ocrbooleanForce OCR for scanned / image-only PDFs (Pro). Default false.
fullbooleanReturn the full document.md (e.g. complete spreadsheet tables) instead of the compact version. Default false.

Provide either path or url. Returns the Markdown plus a token-savings summary.

Config

  • PACKFORAI_API_KEY (required) — your PackForAI API key.
  • PACKFORAI_BASE_URL (optional) — override the API base (defaults to https://packforai.com/api/v1).

Links

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.