MCP server for creating rich lexical graphs from PDFs in Neo4j. Supports multiple parse modes (pymupdf, docling, page-image), pluggable chunking strategies, document versioning, and structural verification.
Listed on its own since 2026-09-26. Until then it was part of mcp-neo4j-entity-graph, where its earlier checks remain.
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":"mcp-neo4j-lexical-graph","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.
# mcp-neo4j-lexical-graph MCP server for creating rich lexical graphs from PDF documents in Neo4j. Designed for Neo4j sales engineers to quickly build PDF-to-graph and GraphRAG agent chatbot POCs. Supports four parsing strategies (PyMuPDF, Docling, page-image, VLM block ordering), pluggable chunking, document versioning, VLM-based description generation, and vector/fulltext search with Neo4j 2026.01 native VECTOR type and document-name prefiltering. ## Graph Model ```mermaid graph LR Doc[Document] -->|HAS_PAGE| Page Doc -->|HAS_ELEMENT| Img[Image] Doc -->|HAS_ELEMENT| Tbl[Table] Doc -->|HAS_SECTION| Sec[Section] Sec -->|HAS_SUBSECTION| Sec Chunk -->|PART_OF| Doc Chunk -->|NEXT_CHUNK| Chunk Chunk -->|HAS_ELEMENT| Img Chunk -->|HAS_ELEMENT| Tbl Page -->|NEXT_PAGE| Page ``` Node types depend on the parse mode used. See [Parse Modes](#parse-modes) below. ## Parse Modes | Mode | Nodes created | Best for | |------|--------------|----------| | `pymupdf` | Document, Chunk, Image, Table | General-purpose text + visual extraction | | `docling` | Document, Page, Element, Section, (then Chunk via chunking tool) | Complex layouts, section-aware chunking | | `page_image` | Document, Page | Slides/presentations for VLM-based extraction | | `vlm_blocks` | Document, Page, Element, Section, (then Chunk via chunking tool) | **Experimental.** Complex layouts without docling dependency (uses VLM API). Prefer `docling` for production use. | ## Quick Start ```bash cd mcp-neo4j-lexical-graph uv sync ``` ### Cursor MCP Configuration Add to your `.cursor/mcp.json`: ```json { "mcpServers": { "neo4j-lexical-graph": { "command": "uv", "args": [ "--directory", "/path/to/mcp-neo4j-lexical-graph", "run", "mcp-neo4j-lexical-graph" ], "env": { "NEO4J_URI": "bolt://localhost:7687", "NEO4J_USERNAME": "neo4j", "NEO4J_PASSWORD": "your-password", "NEO4J_DATABA…
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.