pdffigures2-MCP-Server
A MCP Server for pdffigures2: This server processes scholarly PDFs to extract figures, tables, captions, and section titles with high accuracy. It is designed to support researchers and developers in efficiently analyzing academic documents.
Overview
pdffigures2-MCP-Server is a server designed to process scholarly PDFs, extracting figures, tables, captions, and section titles with high accuracy to assist researchers and developers in analyzing academic documents.
To use the pdffigures2-MCP-Server, send a scholarly PDF document to the server endpoint, and it will return the extracted figures, tables, captions, and section titles in a structured format.
- High accuracy in extracting figures, tables, and captions from PDFs. - Supports a wide range of scholarly PDF formats. - Efficient processing for large academic documents.
- Extracting data from research papers for meta-analysis.
- Compiling figures and tables for literature reviews.
- Assisting developers in creating tools for academic research.
Add to your AI client
Use these steps to connect pdffigures2-MCP-Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.
Cursor
Add this to your .cursor/mcp.json file in your project root, then restart Cursor.
.cursor/mcp.json
{
"mcpServers": {
"pdffigures2-mcp-server-jackkuo666": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-pdffigures2-mcp-server-jackkuo666"
]
}
}
}Claude Desktop
Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.
~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
{
"mcpServers": {
"pdffigures2-mcp-server-jackkuo666": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-pdffigures2-mcp-server-jackkuo666"
]
}
}
}Claude Code
Add this to your project's .mcp.json file. Claude Code will detect it automatically.
.mcp.json (project root)
{
"mcpServers": {
"pdffigures2-mcp-server-jackkuo666": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-pdffigures2-mcp-server-jackkuo666"
]
}
}
}VS Code (Copilot)
Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.
.vscode/mcp.json
{
"servers": {
"pdffigures2-mcp-server-jackkuo666": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-pdffigures2-mcp-server-jackkuo666"
]
}
}
}Windsurf
Add this to your Windsurf MCP config file, then restart Windsurf.
~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"pdffigures2-mcp-server-jackkuo666": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-pdffigures2-mcp-server-jackkuo666"
]
}
}
}Cline
Open Cline settings, navigate to MCP Servers, and add this server configuration.
Cline MCP Settings (via UI)
{
"mcpServers": {
"pdffigures2-mcp-server-jackkuo666": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-pdffigures2-mcp-server-jackkuo666"
]
}
}
}FAQ
What types of PDFs can be processed?
The server can process a variety of scholarly PDF formats, including articles, theses, and reports.
Is there a limit to the size of the PDF?
While there is no strict limit, very large PDFs may take longer to process.
How accurate is the extraction?
The server is designed for high accuracy, but results may vary based on the quality of the PDF.