Chaos Cypher MCP server

Chaos Cypher Knowledge Engine

Turn your documents into a knowledge graph you can inspect, search, chat with, and take with you — all running on your own machine.

Chaos Cypher is a local-first GraphRAG platform — knowledge you can see, trust, and own. Point it at your sources (documents, audio, video, images, pasted text, web pages — 30+ formats, auto-detected), and it extracts entities and relationships into a knowledge graph you can actually see and explore — not a black-box vector blob. Search it, chat with it, refine it, and export the result as a portable Lexicon knowledge package (.ccx) you can back up, share, or load into another instance.

Why Chaos Cypher

embeddings generated on your own system. Bring your own LLM, or run fully offline with Ollama.

• Local-first GraphRAG — sources → extraction → graph → search & chat, with

and traceable back to its source. You can correct extractions, not just trust them.

• Inspectable knowledge graphs — every entity and relationship is visible

self-contained package. Your knowledge is yours to move, version, and keep.

• Portable knowledge packages — import and export your graph as a

MCP client straight into your graph: 36 tools for search, traversal, and graph building.

• MCP server built in — plug Claude Desktop, Cursor, or any

it. The all-in-one container runs the whole stack on hardware you control.

• Self-hosted control — you choose where data lives and which models touch

Feature highlights

Core intelligence

typed, filterable, zoomable from corpus overview down to a single entity and its sources

• Knowledge graph canvas —

traversal fused with vector search (Personalized PageRank + Reciprocal Rank Fusion), plus keyword, semantic, and hybrid modes

• GraphRAG search — graph

answers grounded in your content, traceable back to the sources that produced them

• AI chat with citations —

Data foundation

score graph richness on a 0–100 scale, with breakdowns that flag weak sources

• Quality analysis —

PDF, DOCX, Markdown, HTML, EPUB, audio (MP3/WAV/FLAC), video (MP4/MKV/MOV), images, ZIP archives, and more

• 30+ source formats —

Ollama, OpenAI, Anthropic, or Gemini, configurable per operation

• Mix-and-match LLMs —

Automation & integration

visual workflow builder with triggers and conditional logic

• Automations —

Claude Desktop, Cursor, ChatGPT, and other MCP clients

• MCP server — 36 tools for

drop-in Python document loaders, extraction domains, and workflow tools

• Plugin system —

What data leaves your machine?

Shortened. The full README is on GitHub.