Pandoc Bridge
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., "@Pandoc Bridgeconvert this markdown to a Word document"
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.
Pandoc Bridge
A document format conversion service using Pandoc, supporting both REST (OpenAPI 3.1) and MCP (Model Context Protocol) interfaces.
Features
40+ Format Support: Convert between Markdown, HTML, LaTeX, DOCX, PDF, and many more formats
Dual Protocol: REST API with OpenAPI documentation and MCP server for AI assistants
Bearer Token Auth: Shared JWT authentication across both protocols
Streaming Support: Server-Sent Events for progress tracking
Rate Limiting: Built-in protection against abuse
Docker Ready: Production-ready containerization with multi-arch support
Documentation
API Reference - Detailed REST API documentation
MCP Integration - Model Context Protocol guide
Container Registry Guide - Docker deployment guide
OpenAPI Spec - Interactive Swagger UI (when running)
Quick Start
Using Docker Compose
# Start the service
docker-compose up -d
# Check health
curl http://localhost:8000/healthLocal Development
# Install dependencies
pip install -e ".[dev]"
# Run the server
uvicorn src.main:app --reload
# Or use the CLI
pandoc-bridgeAPI Endpoints
Public Endpoints
Endpoint | Description |
| Service information |
| Health check with Pandoc version |
| List supported formats |
| Swagger UI documentation |
Protected Endpoints (Require Bearer Token)
Endpoint | Description |
| Convert text content |
| Convert uploaded file |
| Stream conversion with SSE |
MCP Endpoint
Endpoint | Description |
| MCP Streamable HTTP transport |
Usage Examples
Convert Text (REST)
# Get a token (for development, tokens are pre-configured)
TOKEN="your-jwt-token"
# Convert Markdown to HTML
curl -X POST http://localhost:8000/api/v1/convert/text \
-H "Authorization: Bearer $TOKEN" \
-H "Content-Type: application/json" \
-d '{
"content": "# Hello World\n\nThis is **bold** text.",
"from_format": "markdown",
"to_format": "html"
}'Convert File (REST)
curl -X POST http://localhost:8000/api/v1/convert/file \
-H "Authorization: Bearer $TOKEN" \
-F "file=@document.md" \
-F "to_format=docx" \
-o converted.docxUsing with Claude Desktop (MCP)
Add to your Claude Desktop configuration:
{
"mcpServers": {
"pandoc-bridge": {
"command": "npx",
"args": ["-y", "mcp-remote", "http://localhost:8000/mcp"]
}
}
}Or with authentication:
{
"mcpServers": {
"pandoc-bridge": {
"command": "npx",
"args": [
"-y", "mcp-remote",
"--header", "Authorization: Bearer ${PANDOC_TOKEN}",
"http://localhost:8000/mcp"
]
}
}
}MCP Tools
Tool | Description |
| Convert text between formats |
| Convert base64-encoded files |
| Get supported formats |
| Get version information |
MCP Resources
Resource | Description |
| JSON list of supported formats |
| Format conversion compatibility matrix |
Authentication
Scopes
Scope | Description |
| Query formats (public) |
| Text conversion |
| File conversion |
| Full access |
Token Format
{
"sub": "client-id",
"scopes": ["formats:read", "convert:text", "convert:file"],
"exp": 1735600000,
"iat": 1735513600
}Configuration
Environment variables (see .env.example):
Variable | Default | Description |
|
| Server host |
|
| Server port |
|
| Logging level |
|
| Environment (development/production) |
| (required in prod) | JWT signing key (min 32 chars) |
|
| Token expiration time |
|
| Maximum file size |
|
| Conversion timeout in seconds |
⚠️ Security Note: Always set
JWT_SECRET_KEYin production. Generate one with:python -c "import secrets; print(secrets.token_urlsafe(32))"
Development
Run Tests
# Install dev dependencies
pip install -e ".[dev]"
# Run tests
pytest
# Run with coverage
pytest --cov=src --cov-report=htmlLint Code
# Run ruff
ruff check src tests
ruff format src testsType Check
mypy srcSecurity Scan
# Install security tools
pip install bandit safety
# Run security scan
bandit -r src -ll
# Check dependencies
safety checkCI/CD
The project uses GitHub Actions for continuous integration and deployment:
CI Pipeline (
pipeline.yml):Runs on Python 3.12 and 3.13
Linting with ruff
Type checking with mypy
Tests with pytest and coverage
Security scanning with bandit
Deploys documentation to GitHub Pages
Container Publishing (
publish-container.yml):Triggered on version tags (
v*.*.*)Multi-arch builds (amd64, arm64)
Publishes to GitHub Container Registry
Running Locally
# Copy environment template
cp .env.example .env
# Edit .env with your settings
vim .env
# Start with Docker
docker-compose up --buildArchitecture
┌─────────────────────────────────────────────────────┐
│ FastAPI App │
│ (Port 8000) │
├─────────────────────┬───────────────────────────────┤
│ REST API │ MCP Server │
│ /api/v1/* │ /mcp │
│ (OpenAPI 3.1) │ (Streamable HTTP) │
├─────────────────────┴───────────────────────────────┤
│ Shared Auth (Bearer Token) │
├─────────────────────────────────────────────────────┤
│ ConversionService (Core) │
├─────────────────────────────────────────────────────┤
│ Pandoc CLI │
└─────────────────────────────────────────────────────┘License
MIT License - see LICENSE for details.
Related MCP Connectors
Markdown in, any format out. PDFs merged, split, watermarked. Runs on our own doc engines.
Convert documents and web pages to clean Markdown: PDF, DOCX, XLSX, EPUB, scanned files, any URL.
Parse PDF/Word/PPT/HTML to Markdown; tables as JSON, image extraction, RAG chunking, page ranges.
Convert between 200+ format pairs: JSON, CSV, XML, YAML, PDF, Excel, DOCX and more.