{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_ehftnpdm2g3n","handle":"mcp-neo4j-lexical-graph","url":"https://wellknown.network/agents/mcp-neo4j-lexical-graph","links":{"self":"https://wellknown.network/agents/mcp-neo4j-lexical-graph/record.json","html":"https://wellknown.network/agents/mcp-neo4j-lexical-graph","markdown":"https://wellknown.network/agents/mcp-neo4j-lexical-graph/record.md","api":"https://wellknown.network/api/v1/agents/mcp-neo4j-lexical-graph","status":"https://wellknown.network/api/v1/agents/mcp-neo4j-lexical-graph/status","claim":"https://wellknown.network/agents/mcp-neo4j-lexical-graph/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-neo4j-lexical-graph/claim.json","badge":"https://wellknown.network/agents/mcp-neo4j-lexical-graph/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-neo4j-lexical-graph/history","tools":"https://wellknown.network/api/v1/agents/mcp-neo4j-lexical-graph/tools"},"ard":{"identifier":"urn:air::server:mcp-neo4j-lexical-graph","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-neo4j-lexical-graph","summary":"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.","description":"# mcp-neo4j-lexical-graph\n\nMCP 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.\n\nSupports 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.\n\n## Graph Model\n\n```mermaid\ngraph LR\n    Doc[Document] -->|HAS_PAGE| Page\n    Doc -->|HAS_ELEMENT| Img[Image]\n    Doc -->|HAS_ELEMENT| Tbl[Table]\n    Doc -->|HAS_SECTION| Sec[Section]\n    Sec -->|HAS_SUBSECTION| Sec\n    Chunk -->|PART_OF| Doc\n    Chunk -->|NEXT_CHUNK| Chunk\n    Chunk -->|HAS_ELEMENT| Img\n    Chunk -->|HAS_ELEMENT| Tbl\n    Page -->|NEXT_PAGE| Page\n```\n\nNode types depend on the parse mode used. See [Parse Modes](#parse-modes) below.\n\n## Parse Modes\n\n| Mode | Nodes created | Best for |\n|------|--------------|----------|\n| `pymupdf` | Document, Chunk, Image, Table | General-purpose text + visual extraction |\n| `docling` | Document, Page, Element, Section, (then Chunk via chunking tool) | Complex layouts, section-aware chunking |\n| `page_image` | Document, Page | Slides/presentations for VLM-based extraction |\n| `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. |\n\n## Quick Start\n\n```bash\ncd mcp-neo4j-lexical-graph\nuv sync\n```\n\n### Cursor MCP Configuration\n\nAdd to your `.cursor/mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"neo4j-lexical-graph\": {\n      \"command\": \"uv\",\n      \"args\": [\n        \"--directory\",\n        \"/path/to/mcp-neo4j-lexical-graph\",\n        \"run\",\n        \"mcp-neo4j-lexical-graph\"\n      ],\n      \"env\": {\n        \"NEO4J_URI\": \"bolt://localhost:7687\",\n        \"NEO4J_USERNAME\": \"neo4j\",\n        \"NEO4J_PASSWORD\": \"your-password\",\n        \"NEO4J_DATABA…","publisher":null,"homepage":"https://github.com/neo4j-field/neo4j-mcp-workspace-template","repository":"https://github.com/neo4j-field/neo4j-mcp-workspace-template","version":"0.2.1","license":"MIT","protocols":["mcp"],"tags":["docling","embeddings","lexical-graph","mcp","neo4j","pdf","rag","vector-search"],"pricing":null,"endpoints":[{"url":"pypi:mcp-neo4j-lexical-graph","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"declared"},{"slug":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":1,"provenance":"declared"},{"slug":"documents.presentations","name":"Presentations","confidence":0.848,"provenance":"derived"}],"categories":["data","documents","knowledge"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"mcp-neo4j-lexical-graph","registry":"pypi","observedAt":"2026-10-22T10:32:00.356Z","publishedAt":"2026-07-17T09:25:19.652136Z","latestVersion":"0.2.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-neo4j-lexical-graph","url":"https://pypi.org/project/mcp-neo4j-lexical-graph/","firstSeenAt":"2026-09-10T02:24:08.277Z","fetchedAt":"2026-10-22T10:30:09.882Z","normalizedAt":"2026-10-22T10:30:09.882Z"}]},"firstSeenAt":"2026-09-10T02:24:08.277Z","updatedAt":"2026-10-22T10:32:00.356Z"}