DocuForge MCP Server
Provides automatic upload of generated PDFs to Cloudinary, returning public URLs for hosting and sharing.
Allows deployment of the MCP server and REST API to Render cloud platform via a Blueprint configuration.
Provides persistent storage for documents, citations, and versions using a SQLite database.
Click on "Install 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., "@DocuForge MCP Servercreate an IEEE paper on machine learning and export PDF"
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.
DocuForge MCP Server
AI-powered document creation, editing, and PDF generation via MCP (Model Context Protocol). DocuForge allows AI agents, IDEs, and user-facing dashboards to programmatically orchestrate the creation of complex documents (specifically tailored for IEEE Research Papers), compile them to PDFs via Puppeteer, and host them.
๐ Features Added in this Project
DocuForge has been heavily upgraded with production-ready features tailored for academic and professional document workflows:
IEEE Research Paper Pipeline: Full support for formatting documents into the official IEEE template (two-column, justified, specialized Abstract/Index Terms, and Reference sections).
Citation Management: Native support for BibTeX importing/exporting, and inline citation marker resolution (e.g.
[cite:jones2023]auto-converts to[1]with an aggregated References list).SQLite Persistence: Transitioned from purely in-memory storage to a production-ready SQLite database for documents, citations, and versions.
Cloudinary Asset Hosting: Automatically uploads generated PDFs to Cloudinary when API keys are provided, returning public URLs instead of local file paths.
Remote MCP via HTTP/SSE: Run the MCP server remotely behind an Express REST API with token authentication, allowing secure remote integration with clients like Claude Desktop.
Multi-stage Docker Builds: Optimized
Dockerfileanddocker-compose.ymlfor running the REST API and MCP services side-by-side in production.VS Code Extension: A functional VS Code extension bundled into the repository for IDE integration.
Related MCP server: Asta MCP Servers
๐ Getting Started
1. Clone the Repository
git clone https://github.com/Ramanand-tomar/Docuforge-mcp-server.git
cd Docuforge-mcp-server2. Configure Environment
Create a .env file in the root based on .env.example:
cp .env.example .envYou should configure the following important variables in your .env:
STORAGE_TYPE=sqlite(Use sqlite for persistence)MCP_API_KEY=your_secure_mcp_api_key_here(For remote MCP)JWT_SECRET=your_secure_jwt_secret_here(For Dashboard auth)CLOUDINARY_CLOUD_NAME,CLOUDINARY_API_KEY,CLOUDINARY_API_SECRET(For PDF uploads)GEMINI_API_KEY(For AI suggestion capabilities)
3. Local Installation & Development
This project uses pnpm workspaces.
# Install dependencies
pnpm install
# Run MCP server (stdio - for local Claude Desktop testing)
pnpm dev:mcp
# Run REST API & Remote MCP HTTP Server
pnpm dev:api
# Run React dashboard
cd packages/dashboard && pnpm dev4. Running with Docker Compose
To spin up the entire production stack locally (REST API + MCP SSE server):
docker compose up --buildโ๏ธ Cloud Deployment (Render)
This repository includes a render.yaml Blueprint file, making it extremely easy to deploy to Render.
Push this code to your GitHub repository.
Sign in to Render and click New+ -> Blueprint.
Connect your GitHub repository.
Render will automatically detect the
render.yamlfile and provision the web services.Set your secret environment variables (
MCP_API_KEY,JWT_SECRET,CLOUDINARY_*) in the Render dashboard for the service.
๐ Connecting Remote MCP Clients
Once deployed, you can connect AI clients like Claude Desktop to your remote MCP server using the official MCP CLI tool:
{
"mcpServers": {
"docuforge": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/inspector",
"https://your-render-url.onrender.com/mcp"
],
"env": {
"MCP_API_KEY": "your_secure_mcp_api_key_here"
}
}
}
}๐ System Architecture
DocuForge acts as a multi-tier monorepo:
@docuforge/core: Document/citation models, SQLite storage layer, and IEEE rendering engine.@docuforge/pdf-engine: Puppeteer-based HTML-to-PDF compilation.@docuforge/mcp-server: Registers 9+ core MCP tools (e.g.create_ieee_paper,import_bibtex,export_pdf).@docuforge/rest-api: Express app serving the REST endpoints and the MCP SSE/mcpproxy.@docuforge/dashboard: Vite + React frontend.docuforge-vscode: VS Code extension client.
๐งช Testing
The repository features comprehensive testing via Vitest, encompassing unit tests, citation integration tests, and HTTP endpoint verification.
pnpm test๐ License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Ramanand-tomar/Docuforge-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server