pdffigures2-MCP-Server

Created By
JackKuo666a year ago
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

what is pdffigures2-MCP-Server?

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.

how to use pdffigures2-MCP-Server?

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.

key features of pdffigures2-MCP-Server?

  • High accuracy in extracting figures, tables, and captions from PDFs.
  • Supports a wide range of scholarly PDF formats.
  • Efficient processing for large academic documents.

use cases of pdffigures2-MCP-Server?

  1. Extracting data from research papers for meta-analysis.
  2. Compiling figures and tables for literature reviews.
  3. Assisting developers in creating tools for academic research.

FAQ from pdffigures2-MCP-Server?

  • 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.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
JackKuo666
Star
0
Language
-
License
-

Recommend Servers

View All
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

17 hours ago