No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by stevereiner · MCP Server · ★ 185
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is flexible-graphrag safe to install? View the security audit →
New 5/6/26: 15 property graph databases total: 8 supported on both LlamaIndex and LangChain, 1 LI-only (Google Cloud Spanner Graph), 6 LC-only (ArangoDB, Apache AGE, Azure Cosmos DB for Gremlin, Apache HugeGraph, SurrealDB, TigerGraph). AWS Neptune RDF/SPARQL added. All 10 vector databases, all 3 search engines, and all LLM/embedding providers work with both LlamaIndex and LangChain. Every pipeline stage (chunking, KG extraction, graph write, vector write, search write, and retrieval fusion) can be configured independently. (Data source reading is LlamaIndex only; RDF stores use framework-independent adapters with LangChain Text-to-SPARQL retrieval.) New: Flexible GraphRAG now supports RDF-based ontologies for both property graph databases and RDF triple store databases (Graphwise Ontotext GraphDB, Fuseki, and Oxigraph). Document ingestion with KG extraction, auto incremental data source change detection, and UI search (hybrid search, AI query, and AI chat) are all supported with both database types.
| Stars | 185 |
| Forks | 34 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 56.9721542977398/100 |
| Open Issues | 3 |
| Last Updated | 2026-09-16 |
| Created | 2025-08-05 |
| Platforms | cli, mcp, python |
| Est. Tokens | ~25k |
Looking for a flexible-graphrag alternative? If you're comparing flexible-graphrag with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
PDF extraction that audits its own output — and certifies any other extractor's, catching pages they silently
Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in o
Open-source protocol suite standardizing LLM, Vector, Graph, and Embedding infrastructure across LangChain, Ll
Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embed
Local-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP o
Build, Improve Performance, and Productionize your LLM Application with an Integrated Framework
Explore other popular mcp server tools:
flexible-graphrag is Python, LlamaIndex, LangChain, 15 Property Graph, 4 RDF , 10 Vector, OpenSearch, Elasticsearch, Alfresco, Nuxeo DBs. 14 data sources (10 auto-sync), KG auto-building, Ontologies, LLMs, Docling, LlamaP. It is categorized as a MCP Server with 185 GitHub stars.
flexible-graphrag is primarily written in Python. It covers topics such as ai-chat, ai-context-management, alfresco.
You can find installation instructions and usage details in the flexible-graphrag GitHub repository at github.com/stevereiner/flexible-graphrag. The project has 185 stars and 34 forks, indicating an active community.
flexible-graphrag is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to flexible-graphrag on Agent Skills Hub include pdfmux, octocode, corpusos. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: