A Model Context Protocol (MCP) server for indexing and semantically searching PDF research papers
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"pdf-indexer-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# PDF Indexer MCP Server A **Model Context Protocol (MCP) server** that enables AI agents to download, index, and semantically search PDF research papers. This server provides 8 tools that AI agents can discover and use autonomously to build research paper knowledge bases and answer questions. ## What is MCP? **Model Context Protocol (MCP)** is a standardized protocol that allows AI agents to discover and use tools. Instead of being limited to text generation, agents become **action-capable systems** that can: 1. **Discover Tools**: Agents automatically discover available tools from connected MCP servers 2. **Understand Capabilities**: Agents read tool descriptions and parameters to understand what each tool can do 3. **Execute Tasks**: Agents call tools with appropriate parameters to accomplish goals 4. **Compose Workflows**: Agents can combine multiple tools from different servers to solve complex problems ### How MCP Works ``` AI Agent → MCP Protocol → Tool Server → Execution → Results → Agent ``` When you connect this MCP server to an AI agent (like in Cursor, Claude Desktop, or via OpenAI Agents framework), the agent automatically: - Discovers all 8 tools available from this server - Understands what each tool does from their descriptions - Uses the tools when they're needed to complete tasks - Can combine tools in complex workflows ## Features - 📥 **PDF Download**: Download research papers from URLs - 📄 **Intelligent Chunking**: Two chunking strategies: - **Header-based**: Preserves document structure (ideal for academic papers) - **S2 chunking**: Spatial-semantic hybrid approach for optimal semantic chunks - 🗄️ **Database Indexing**: Store papers and chunks in SQLite with navigation indices - 🔍 **Semantic Search**: Search papers using MLX-optimized embeddings (Qwen3-Embedding-0.6B) - ⚡ **FAISS Vector Index**: Fast similarity search even for thousands of chunks - 🧠 **Context-Aware**: Retrieve surrounding chunks for better context ## Quick …
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.