Veritasgraph

Zero-trust, air-gapped Enterprise GraphRAG MCP server with offline, citation-grounded answers.

Quick Install

Automated & IDE Setup

Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.

Add to Cursor Add to VS Code

Manual Client & Custom JSON ConfigExpand JSON ▾

Client Config & Setup

Choose your client or environment

Target File:~/Library/Application Support/Claude/claude_desktop_config.json

claude_desktop_config.json

{
  "mcpServers": {
    "veritasgraph": {
      "command": "npx",
      "args": [
        "-y",
        "veritasgraph"
      ]
    }
  }
}

💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.

Documentation Overview

VeritasGraph: The All-in-One GraphRAG Framework

Stop chunking blindly. Combine the structure of Tree-Search with the reasoning of Knowledge Graphs. Runs locally or in the cloud.

🎯 Traditional RAG guesses based on similarity. VeritasGraph reasons based on structure.
Don't just find the document—understand the connection.

🌳 + 🔗 Graph + Tree: The Ultimate Retrieval

Why choose? VeritasGraph includes the hierarchical "Table of Contents" navigation of PageIndex PLUS the semantic reasoning of a Knowledge Graph.

Code

Document Root

├── [1] Introduction

│   ├── [1.1] Background ←── Tree Navigation

│   └── [1.2] Objectives

├── [2] Methodology ←───────── Graph Links

│   └── relates_to ──────────→ [3.1] Findings

└── [3] Results

📊 Feature Comparison

Feature	Vector RAG	PageIndex	VeritasGraph
Retrieval Type	Similarity	Tree Search	🏆 Tree + Graph Reasoning
Attribution	❌ Low	⚠️ Medium	✅ 100% Verifiable
Multi-hop Reasoning	❌	❌	✅
Tree Navigation (TOC)	❌	✅	✅
Semantic Search	✅	❌	✅
Cross-section Linking	❌	❌	✅
Visual Graph Explorer	❌	❌	✅ Built-in UI
100% Local/Private	⚠️ Varies	❌ Cloud	✅ On-Premise
Open Source	⚠️ Varies	❌ Proprietary	✅ MIT License
Cross-section linking	❌	❌	✅

VeritasGraph is a production-ready framework that solves the fundamental problem with vector-search RAG: context blindness. While traditional RAG chunks your documents into isolated fragments and hopes cosine similarity finds the right one, VeritasGraph builds a knowledge graph that actually understands how your information connects.

The result? Multi-hop reasoning that answers complex questions, transparent attribution for every claim, and a hierarchical tree structure that navigates documents like a human would—all running on your own infrastructure.

Traditional RAG vs VeritasGraph comparison

🚀 Get Started in 2 Lines

No GPU? No problem. Try VeritasGraph instantly:

Terminal

pip install veritasgraph

veritasgraph demo --mode=lite

That's it. This launches an interactive demo using cloud APIs (OpenAI/Anthropic)—no local models required.

🎬 See It In Action

▶️ Watch VeritasGraph build reasoning paths in real-time.

▶️ Convert Charts & Tables to Knowledge Graphs in Minutes | Vision RAG Tutorial

💡 What you're seeing: A query triggers multi-hop reasoning across the knowledge graph. Nodes light up as connections are discovered, showing exactly how the answer was found—not just what was found.

Choose Your Path

Mode	Best For	Requirements
`--mode=lite`	Quick demo, no GPU	OpenAI/Anthropic API key
`--mode=local`	Privacy, offline use	Ollama + 8GB RAM
`--mode=full`	Production, all features	Docker + Neo4j

server.ts

# Lite mode (cloud APIs, zero setup)

export OPENAI_API_KEY="sk-..."

veritasgraph demo --mode=lite



# Local mode (100% offline with Ollama)

veritasgraph demo --mode=local --model=llama3.2



# Full mode (complete GraphRAG pipeline)

veritasgraph start --mode=full

📦 Installation

bash

# Basic install (includes lite mode)

pip install veritasgraph



# With optional dependencies

pip install veritasgraph[web]      # Gradio UI + visualization

pip install veritasgraph[graphrag] # Microsoft GraphRAG integration  

pip install veritasgraph[ingest]   # YouTube & web article ingestion

pip install veritasgraph[all]      # Everything

📖 Quick Start (Python API)

Once you're ready to integrate VeritasGraph into your code:

server.ts

from veritasgraph import VisionRAGPipeline



# Simplest usage - auto-detects available models

pipeline = VisionRAGPipeline()

doc = pipeline.ingest_pdf("document.pdf")

result = pipeline.query("What are the key findings?")

print(result.answer)

🔧 Advanced: Custom Configuration

server.ts

from veritasgraph import VisionRAGPipeline, VisionRAGConfig



# Configure for local Ollama models

config = VisionRAGConfig(vision_model="llama3.2-vision:11b")

pipeline = VisionRAGPipeline(config)



# Ingest a PDF document (automatically extracts hierarchical structure)

doc = pipeline.ingest_pdf("document.pdf")



# Query with full visual context

result = pipeline.query("What are the key findings in the tables?")

🌳 Hierarchical Tree Support

The Power of PageIndex's Tree + The Flexibility of a Graph

VeritasGraph now combines two powerful retrieval paradigms:

Tree-based navigation - Human-like retrieval through Table of Contents structure
Graph-based search - Semantic similarity across the entire document

server.ts

from veritasgraph import VisionRAGPipeline



pipeline = VisionRAGPipeline()

doc = pipeline.ingest_pdf("report.pdf")



# View the document's hierarchical structure (like a Table of Contents)

print(pipeline.get_document_tree())

# Output:

# Document Root

# ├── [1] Introduction (pp. 1-5)

# │   ├── [1.1] Background (pp. 1-2)

# │   └── [1.2] Objectives (pp. 3-5)

# ├── [2] Methodology (pp. 6-15)

# │   ├── [2.1] Data Collection (pp. 6-10)

# │   └── [2.2] Analysis Framework (pp. 11-15)

# └── [3] Results (pp. 16-30)



# Navigate to a specific section (tree-based retrieval)

section = pipeline.navigate_to_section("Methodology")

print(section['breadcrumb'])  # ['Document Root', 'Methodology']

print(section['children'])    # [Data Collection, Analysis Framework]



# Or use graph-based semantic search

result = pipeline.query("What methodology was used?")

# Returns answer with section context: "📍 Location: Document > Methodology > Analysis Framework"

Why Hierarchical Trees Matter

Traditional RAG	VeritasGraph with Trees
Chunks documents randomly	Preserves document structure
Loses section context	Maintains parent-child relationships
Can't navigate by structure	Supports TOC-style navigation
No hierarchy awareness	Full tree traversal (ancestors, siblings, children)

CLI Usage

bash

veritasgraph --version                                    # Show version

veritasgraph info                                         # Check dependencies  

veritasgraph init my_project                              # Initialize new project

veritasgraph ingest document.pdf --ingest-mode=document-centric  # Don't Chunk. Graph.

� Ingestion Capabilities

VeritasGraph offers multiple ways to ingest content into your knowledge graph:

"Don't Chunk. Graph." - Document-Centric Mode

Traditional RAG splits documents into arbitrary 500-token chunks, destroying context. VeritasGraph's document-centric mode treats whole pages or sections as single retrievable nodes:

server.ts

from veritasgraph import VisionRAGPipeline, VisionRAGConfig



config = VisionRAGConfig(ingest_mode="document-centric")  # Tables stay intact!

pipeline = VisionRAGPipeline(config)

doc = pipeline.ingest_pdf("annual_report.pdf")

⚡ Instant Knowledge Ingest

Add content to your knowledge graph with one click:

Source	How It Works
📺 YouTube	Paste URL → auto-extracts transcript
📰 Web Articles	Paste URL → extracts main content
📄 PDFs	Upload → document-centric extraction
📝 Text	Paste directly → instant indexing

bash

# CLI ingestion

veritasgraph ingest https://youtube.com/watch?v=xxx

veritasgraph ingest https://example.com/article

Read the full README →View source on GitHub →

Related MCP Servers

View all in Developer Tools View all alternatives

Reviews

No reviews yet — be the first to share how this listing worked for you.

Frequently Asked Questions about Veritasgraph

Add the following block to your claude_desktop_config.json under mcpServers: "mcpServers": { "veritasgraph": { "command": "npx", "args": ["-y", "veritasgraph"] } }

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:

Live Dynamic SVG Preview

Markdown (GitHub README)

[![AllMCPs](https://allmcps.com/api/badge/veritasgraph?style=directory)](https://allmcps.com/mcp/veritasgraph)

HTML Embed

<a href="https://allmcps.com/mcp/veritasgraph"><img src="https://allmcps.com/api/badge/veritasgraph?style=directory" alt="Veritasgraph on AllMCPs" /></a>

Technical Specs & Signals

CategoryDeveloper Tools

27Quality signal: Emerging · 27/100How this signal is calculated ▾

Server availabilityNot measured

Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.

Verified ownership8/20

Documentation & tools11/30

Adoption & activity1/15

Community engagement0/10

A guidance signal from public completeness & health data — not a user rating. New listings start lower and rise as they add docs, get verified, and grow adoption. Signals we can't observe for a listing are skipped, not counted against it.

★ Featured

Moxie Docs MCP

MCP & Agent Skills for Automated Documentation, and codebase conventions + context

Explore Server →

Own this project?

This directory is pre-filled from public sources. Claim via GitHub README, site badge, or DNS TXT to unlock edit access and the Official badge — proof is checked automatically, then reviewed by our team.

Free dofollow backlink: add your website and place the AllMCPs badge on it — no claim needed. We detect it automatically and keep it verified as long as the badge stays live.

Claim & get free dofollow

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.

Explore more

More in 💻 Developer Tools →Best MCP servers for Developers →Alternatives to Veritasgraph →Install in Claude Desktop Install in Cursor Install in VS Code

Veritasgraph

Zero-trust, air-gapped Enterprise GraphRAG MCP server with offline, citation-grounded answers.

Quick Install

Automated & IDE Setup

Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.

Add to Cursor Add to VS Code

Manual Client & Custom JSON ConfigExpand JSON ▾

Client Config & Setup

Choose your client or environment

Target File:~/Library/Application Support/Claude/claude_desktop_config.json

claude_desktop_config.json

{
  "mcpServers": {
    "veritasgraph": {
      "command": "npx",
      "args": [
        "-y",
        "veritasgraph"
      ]
    }
  }
}

💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.

Documentation Overview

VeritasGraph: The All-in-One GraphRAG Framework

Stop chunking blindly. Combine the structure of Tree-Search with the reasoning of Knowledge Graphs. Runs locally or in the cloud.

🎯 Traditional RAG guesses based on similarity. VeritasGraph reasons based on structure.
Don't just find the document—understand the connection.

🌳 + 🔗 Graph + Tree: The Ultimate Retrieval

Why choose? VeritasGraph includes the hierarchical "Table of Contents" navigation of PageIndex PLUS the semantic reasoning of a Knowledge Graph.

Code

Document Root

├── [1] Introduction

│   ├── [1.1] Background ←── Tree Navigation

│   └── [1.2] Objectives

├── [2] Methodology ←───────── Graph Links

│   └── relates_to ──────────→ [3.1] Findings

└── [3] Results

📊 Feature Comparison

Feature	Vector RAG	PageIndex	VeritasGraph
Retrieval Type	Similarity	Tree Search	🏆 Tree + Graph Reasoning
Attribution	❌ Low	⚠️ Medium	✅ 100% Verifiable
Multi-hop Reasoning	❌	❌	✅
Tree Navigation (TOC)	❌	✅	✅
Semantic Search	✅	❌	✅
Cross-section Linking	❌	❌	✅
Visual Graph Explorer	❌	❌	✅ Built-in UI
100% Local/Private	⚠️ Varies	❌ Cloud	✅ On-Premise
Open Source	⚠️ Varies	❌ Proprietary	✅ MIT License
Cross-section linking	❌	❌	✅

Traditional RAG vs VeritasGraph comparison

🚀 Get Started in 2 Lines

No GPU? No problem. Try VeritasGraph instantly:

Terminal

pip install veritasgraph

veritasgraph demo --mode=lite

That's it. This launches an interactive demo using cloud APIs (OpenAI/Anthropic)—no local models required.

🎬 See It In Action

▶️ Watch VeritasGraph build reasoning paths in real-time.

▶️ Convert Charts & Tables to Knowledge Graphs in Minutes | Vision RAG Tutorial

💡 What you're seeing: A query triggers multi-hop reasoning across the knowledge graph. Nodes light up as connections are discovered, showing exactly how the answer was found—not just what was found.

Choose Your Path

Mode	Best For	Requirements
`--mode=lite`	Quick demo, no GPU	OpenAI/Anthropic API key
`--mode=local`	Privacy, offline use	Ollama + 8GB RAM
`--mode=full`	Production, all features	Docker + Neo4j

server.ts

# Lite mode (cloud APIs, zero setup)

export OPENAI_API_KEY="sk-..."

veritasgraph demo --mode=lite



# Local mode (100% offline with Ollama)

veritasgraph demo --mode=local --model=llama3.2



# Full mode (complete GraphRAG pipeline)

veritasgraph start --mode=full

📦 Installation

bash

# Basic install (includes lite mode)

pip install veritasgraph



# With optional dependencies

pip install veritasgraph[web]      # Gradio UI + visualization

pip install veritasgraph[graphrag] # Microsoft GraphRAG integration  

pip install veritasgraph[ingest]   # YouTube & web article ingestion

pip install veritasgraph[all]      # Everything

📖 Quick Start (Python API)

Once you're ready to integrate VeritasGraph into your code:

server.ts

from veritasgraph import VisionRAGPipeline



# Simplest usage - auto-detects available models

pipeline = VisionRAGPipeline()

doc = pipeline.ingest_pdf("document.pdf")

result = pipeline.query("What are the key findings?")

print(result.answer)

🔧 Advanced: Custom Configuration

server.ts

from veritasgraph import VisionRAGPipeline, VisionRAGConfig



# Configure for local Ollama models

config = VisionRAGConfig(vision_model="llama3.2-vision:11b")

pipeline = VisionRAGPipeline(config)



# Ingest a PDF document (automatically extracts hierarchical structure)

doc = pipeline.ingest_pdf("document.pdf")



# Query with full visual context

result = pipeline.query("What are the key findings in the tables?")

🌳 Hierarchical Tree Support

The Power of PageIndex's Tree + The Flexibility of a Graph

VeritasGraph now combines two powerful retrieval paradigms:

Tree-based navigation - Human-like retrieval through Table of Contents structure
Graph-based search - Semantic similarity across the entire document

server.ts

from veritasgraph import VisionRAGPipeline



pipeline = VisionRAGPipeline()

doc = pipeline.ingest_pdf("report.pdf")



# View the document's hierarchical structure (like a Table of Contents)

print(pipeline.get_document_tree())

# Output:

# Document Root

# ├── [1] Introduction (pp. 1-5)

# │   ├── [1.1] Background (pp. 1-2)

# │   └── [1.2] Objectives (pp. 3-5)

# ├── [2] Methodology (pp. 6-15)

# │   ├── [2.1] Data Collection (pp. 6-10)

# │   └── [2.2] Analysis Framework (pp. 11-15)

# └── [3] Results (pp. 16-30)



# Navigate to a specific section (tree-based retrieval)

section = pipeline.navigate_to_section("Methodology")

print(section['breadcrumb'])  # ['Document Root', 'Methodology']

print(section['children'])    # [Data Collection, Analysis Framework]



# Or use graph-based semantic search

result = pipeline.query("What methodology was used?")

# Returns answer with section context: "📍 Location: Document > Methodology > Analysis Framework"

Why Hierarchical Trees Matter

Traditional RAG	VeritasGraph with Trees
Chunks documents randomly	Preserves document structure
Loses section context	Maintains parent-child relationships
Can't navigate by structure	Supports TOC-style navigation
No hierarchy awareness	Full tree traversal (ancestors, siblings, children)

CLI Usage

bash

veritasgraph --version                                    # Show version

veritasgraph info                                         # Check dependencies  

veritasgraph init my_project                              # Initialize new project

veritasgraph ingest document.pdf --ingest-mode=document-centric  # Don't Chunk. Graph.

� Ingestion Capabilities

VeritasGraph offers multiple ways to ingest content into your knowledge graph:

"Don't Chunk. Graph." - Document-Centric Mode

Traditional RAG splits documents into arbitrary 500-token chunks, destroying context. VeritasGraph's document-centric mode treats whole pages or sections as single retrievable nodes:

server.ts

from veritasgraph import VisionRAGPipeline, VisionRAGConfig



config = VisionRAGConfig(ingest_mode="document-centric")  # Tables stay intact!

pipeline = VisionRAGPipeline(config)

doc = pipeline.ingest_pdf("annual_report.pdf")

⚡ Instant Knowledge Ingest

Add content to your knowledge graph with one click:

Source	How It Works
📺 YouTube	Paste URL → auto-extracts transcript
📰 Web Articles	Paste URL → extracts main content
📄 PDFs	Upload → document-centric extraction
📝 Text	Paste directly → instant indexing

bash

# CLI ingestion

veritasgraph ingest https://youtube.com/watch?v=xxx

veritasgraph ingest https://example.com/article

Read the full README →View source on GitHub →

Related MCP Servers

View all in Developer Tools View all alternatives

Reviews

No reviews yet — be the first to share how this listing worked for you.

Frequently Asked Questions about Veritasgraph

Add the following block to your claude_desktop_config.json under mcpServers: "mcpServers": { "veritasgraph": { "command": "npx", "args": ["-y", "veritasgraph"] } }

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:

Live Dynamic SVG Preview

Markdown (GitHub README)

[![AllMCPs](https://allmcps.com/api/badge/veritasgraph?style=directory)](https://allmcps.com/mcp/veritasgraph)

HTML Embed

<a href="https://allmcps.com/mcp/veritasgraph"><img src="https://allmcps.com/api/badge/veritasgraph?style=directory" alt="Veritasgraph on AllMCPs" /></a>

Technical Specs & Signals

CategoryDeveloper Tools

27Quality signal: Emerging · 27/100How this signal is calculated ▾

Server availabilityNot measured

Not scored for repo-hosted servers — we can't reach the running server, only its GitHub page. Hosted MCP endpoints are health-checked live.

Verified ownership8/20

Documentation & tools11/30

Adoption & activity1/15

Community engagement0/10

★ Featured

Moxie Docs MCP

MCP & Agent Skills for Automated Documentation, and codebase conventions + context

Explore Server →

Own this project?

Free dofollow backlink: add your website and place the AllMCPs badge on it — no claim needed. We detect it automatically and keep it verified as long as the badge stays live.

Claim & get free dofollow

Share & Embed

Add our SVG badge (dark/light directory styles) or embeddable widget to your site.

Explore more

More in 💻 Developer Tools →Best MCP servers for Developers →Alternatives to Veritasgraph →Install in Claude Desktop Install in Cursor Install in VS Code