{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_jzjeckmkxey9","handle":"mcp-neo4j-entity-graph","url":"https://wellknown.network/agents/mcp-neo4j-entity-graph","links":{"self":"https://wellknown.network/agents/mcp-neo4j-entity-graph/record.json","html":"https://wellknown.network/agents/mcp-neo4j-entity-graph","markdown":"https://wellknown.network/agents/mcp-neo4j-entity-graph/record.md","api":"https://wellknown.network/api/v1/agents/mcp-neo4j-entity-graph","status":"https://wellknown.network/api/v1/agents/mcp-neo4j-entity-graph/status","claim":"https://wellknown.network/agents/mcp-neo4j-entity-graph/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-neo4j-entity-graph/claim.json","badge":"https://wellknown.network/agents/mcp-neo4j-entity-graph/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-neo4j-entity-graph/history","tools":"https://wellknown.network/api/v1/agents/mcp-neo4j-entity-graph/tools"},"ard":{"identifier":"urn:air::server:mcp-neo4j-entity-graph","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-neo4j-entity-graph","summary":"MCP server for extracting entities from text chunks and creating entity graphs in Neo4j. Supports 100+ LLM providers via LiteLLM.","description":"# MCP Neo4j Entity Graph Server\n\n[![PyPI version](https://badge.fury.io/py/mcp-neo4j-entity-graph.svg)](https://pypi.org/project/mcp-neo4j-entity-graph/)\n[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n\nMCP server for extracting entities and relationships from graph nodes using LLM structured output, creating entity graphs directly in Neo4j.\n\n**Supports 100+ LLM providers via LiteLLM** (OpenAI, Anthropic, Google, Azure, Bedrock, Ollama, etc.)\n\n## Features\n\n- **Dual extraction pipeline**: Text-only (LLM) and visual (VLM) extraction auto-routed per chunk\n- **Grammar-enforced structured output**: Pydantic models used as `response_format` — the LLM cannot violate the schema\n- **Async background processing**: Long extractions run in background with job tracking\n- **Multi-provider LLM support**: Use any LLM via LiteLLM (OpenAI, Claude, Gemini, etc.)\n- **Schema-driven**: Define entity types and relationships to extract\n- **Provenance tracking**: `EXTRACTED_FROM` relationships link entities to source chunks\n- **High parallelism**: Configurable concurrency (text: up to 50, VLM: up to 50)\n- **Batched writes**: Optimized Neo4j writes (configurable batch size)\n- **Incremental**: Only processes nodes without prior extraction (unless `force=true`)\n- **Multi-pass ready**: Architecture supports entity-only, relationship-only, and corrective passes (v2)\n\n## Tools\n\n### `convert_schema`\n\nConverts data model output from the Data Modeling MCP to a Pydantic extraction schema.\n\n**Parameters:**\n\n| Parameter | Required | Description |\n|-----------|----------|-------------|\n| `modeling_output` | Yes | JSON output from the Data Modeling MCP server |\n| `output_path` | Yes | Path to save the Pydantic `.py` file (e.g. `/path/to/schema.py`) |\n\n**Output:**\n- `{output_path}` — Strongly-typed Pydantic models used as `response_format` fo…","publisher":null,"homepage":"https://github.com/neo4j-field/neo4j-mcp-workspace-template#readme","repository":"https://github.com/neo4j-field/neo4j-mcp-workspace-template#readme","version":"0.4.1","license":"MIT","protocols":["mcp"],"tags":["entity-extraction","knowledge-graph","litellm","llm","mcp","neo4j","rag"],"pricing":null,"endpoints":[{"url":"pypi:mcp-neo4j-entity-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":"documents.extraction","name":"Data Extraction","confidence":1,"provenance":"derived"},{"slug":"knowledge.knowledge-graph","name":"Knowledge Graphs","confidence":1,"provenance":"declared"},{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"declared"}],"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-entity-graph","registry":"pypi","observedAt":"2026-10-22T10:31:59.949Z","publishedAt":"2026-07-17T09:25:16.492900Z","latestVersion":"0.4.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-neo4j-entity-graph","url":"https://pypi.org/project/mcp-neo4j-entity-graph/","firstSeenAt":"2026-09-10T02:24:07.382Z","fetchedAt":"2026-10-22T10:30:08.975Z","normalizedAt":"2026-10-22T10:30:08.975Z"}]},"firstSeenAt":"2026-09-10T02:24:07.382Z","updatedAt":"2026-10-22T10:31:59.949Z"}