Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@packforai-mcp Convert ~/Downloads/Q4-report.pdf to clean Markdown."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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.
Node.js 18+
A PackForAI API key (Pro plan). Create one at packforai.com/account.
Related MCP server: document-converter-mcp
The server runs via npx, so there is nothing to install globally. Add it to your MCP client's config.
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.
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" }
}
}
}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."
convert_document
Param | Type | Description |
| string | Absolute path to a local document file. |
| string | Public https URL of a document to fetch and convert. |
| boolean | Force OCR for scanned / image-only PDFs (Pro). Default |
| boolean | Return the full |
Provide either path or url. Returns the Markdown plus a token-savings summary.
PACKFORAI_API_KEY (required) — your PackForAI API key.
PACKFORAI_BASE_URL (optional) — override the API base (defaults to https://packforai.com/api/v1).
Website: packforai.com
API docs: packforai.com/docs
MIT
Convert a document (PDF, DOCX, PPTX, XLSX, CSV, JSON) into clean, compact, AI-ready Markdown using PackForAI. Provide either a local file path or a public url. Returns the compact Markdown plus token-savings, ready to read or paste into a prompt. Use ocr: true for scanned / image-only PDFs.
| Name | Required | Description | Default |
|---|---|---|---|
| ocr | No | Force OCR for scanned or image-only PDFs (Pro). Defaults to false. | |
| url | No | Public https URL of a document to fetch and convert. | |
| full | No | Return the full document.md (e.g. complete spreadsheet tables) instead of the compact version. Defaults to false. | |
| path | No | Absolute path to a local document file to convert. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries the burden. It mentions returns (compact Markdown + token-savings) but does not disclose potential side effects, authentication needs, or rate limits, leaving some behavioral uncertainty.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise at three sentences, front-loaded with the main purpose, and every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite no output schema, the description adequately covers inputs, output format, and options, making it complete for the tool's straightforward functionality.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description adds practical guidance (e.g., 'Use ocr: true for scanned PDFs') and clarifies the output format, going beyond what the schema alone provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool converts documents (PDF, DOCX, etc.) into AI-ready Markdown, with explicit output format and supported input types, fully aligning with the title and name.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides usage context (e.g., 'ready to read or paste into a prompt') and differentiates options (path vs url, ocr for scanned PDFs), but lacks explicit contrast with sibling tools since none exist.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0convert_documentScored across 1 tool
With only one tool, there is no possibility of ambiguity between tools. The sole tool has a clear and distinct purpose.
With a single tool, naming consistency is trivially perfect. 'convert_document' follows a clear verb_noun pattern.
A single tool for document conversion is borderline appropriate. While it covers the core task, it may feel thin for a full server; additional tools like format listing or health check could be beneficial.
The single tool covers the main document conversion task well, handling multiple input formats and offering OCR. Minor gaps exist, such as no explicit listing of supported formats, but the tool is functionally complete for its stated purpose.
Convert documents and web pages to clean Markdown: PDF, DOCX, XLSX, EPUB, scanned files, any URL.
Convert PDF, DOCX, HTML, and URLs to clean, LLM-ready markdown with tables preserved
Parse PDF/Word/PPT/HTML to Markdown; tables as JSON, image extraction, RAG chunking, page ranges.
High-fidelity PDF to structured Markdown conversion and document field extraction.
