Document OperationsSAFE
MCP server for seamless document format conversion and processing
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://www.npmjs.com/package/doc-ops-mcp) [](https://opensource.org/licenses/MIT) [](https://www.npmjs.com/package/doc-ops-mcp)
Language / 语言: English | 中文
Document Operations MCP Server - A universal MCP server for document processing, conversion, and automation. Handle PDF, DOCX, HTML, Markdown, and more through a unified API and toolset.
Demo
Video
In this demo, we showcase how to:
- Configure doc-ops-mcp in MCP clients
- Convert DOCX documents to PDF format
- Add default watermarks to converted PDF files
Table of Contents
- Quick Start
- System Architecture
- Optional Integration
- Features
- Open Source Licenses
- Future Roadmap
- Docker Deployment
- Development Guide
- Troubleshooting
- Contributing
1. Quick Start
First, add the Document Operations MCP server to your MCP client.
Standard config works in most MCP clients:
{
"mcpServers": {
"doc-ops-mcp": {
"command": "npx",
"args": ["-y", "doc-ops-mcp"],
"env": {
"OUTPUT_DIR": "/path/to/your/output/directory",
"CACHE_DIR": "/path/to/your/cache/directory",
}
}
}
}Claude Desktop
Follow the MCP install guide, use the standard config above.
VS Code
Follow the MCP install [guide](https://code.visualstudio.com/docs/copilot/chat/mcp
f492d70ed7e9OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add doc-ops-mcp -- npx -y [email protected]
{
"mcpServers": {
"doc-ops-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (8)
4 read · 4 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
add_qrcode | write | Add QR code to PDF documents with friendly text below. QR code must be an image file (PNG/JPG). Priority: user provided path > environment variable QR_CODE_IMAGE |
add_watermark | write | Add watermarks to PDF documents. Supports both text and image watermarks. Priority: user text > user image > environment variable image > default text |
convert_docx_to_pdf | read | Enhanced DOCX to PDF conversion with perfect Word style replication and Playwright integration. Watermark can be added by setting addWatermark=true (uses WATERMARK_IMAGE environment variable or default text |
convert_markdown_to_pdf | read | Enhanced Markdown to PDF conversion with beautiful styling and theme support. Watermark can be added by setting addWatermark=true (uses WATERMARK_IMAGE environment variable or default text |
plan_conversion | read | 🎯 **MANDATORY FIRST STEP** - Smart Document Conversion Planner - ⚠️ CRITICAL: This tool MUST be executed BEFORE any document conversion operation! When users request any format conversion (e.g., |
process_pdf_post_conversion | write | 🔧 PDF Post-Processing Unified Tool - ⚠️ IMPORTANT: This is a necessary follow-up step for playwright-mcp\ |
read_document | read | Read various document formats (DOCX, DOC, TXT, MD, HTML, etc.) |
write_document | write | Write content to document files in specified formats. Output directory is controlled by OUTPUT_DIR environment variable. Files will be automatically saved to OUTPUT_DIR with auto-generated names based on content type (HTML, Markdown, or plain text). Supports intelligent format detection. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
.eslintrc.js
.prettierignore
@modelcontextprotocol/sdk, @types/fontkit, @types/marked, cheerio, docx, fontkit, jszip, marked
Gates applied: no_behavioural_pass.
f492d70ed7e9full audit observations/trust-audit/mcp-server/tele-ai__document-operations.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | f492d70ed7e9 | SAFE | B | 89 | first audit |
Questions
What is the Document Operations MCP server?
MCP server for seamless document format conversion and processing
What tools does Document Operations expose?
8 in total: 4 read-only, 4 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Document Operations safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Document Operations need?
No credential environment variables were found in its source, so it appears to need none.
How does Document Operations run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as doc-ops-mcp at 0.3.8.
How current is this page?
The grade is for one exact copy of the source (f492d70ed7e9), read on 2026-10-07. The repository is watched and re-audited when it changes.