Log inSubmit server
Veritasgraph logo

Veritasgraph

Offline GraphRAG MCP server for citation-grounded retrieval, graph reasoning, and governed agent workflows.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Veritasgraph

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "veritasgraph": {
      "command": "uvx",
      "args": [
        "veritasgraph-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 5 tools correctly (Today).

Overview

veritasgraph MCP server combines tree-search structure with knowledge-graph reasoning for document ingestion and query workflows. It can run locally with Ollama, use OpenAI or Anthropic APIs in lite mode, or use Docker and Neo4j for a full deployment. Retrieval is designed around graph traversal, provenance, and explicit insufficient-evidence responses rather than similarity search alone. Reach for it when on-premises operation, offline use, and traceable answers matter.

Use cases

  • Run offline document question answering with Ollama
  • Build citation-grounded enterprise GraphRAG workflows
  • Extract floorplan data for quantity takeoffs
  • Test governed agent patterns with auditable evidence

Key features

  • Graph-based retrieval with tree-search structure
  • Offline Ollama mode
  • OpenAI and Anthropic API support in lite mode
  • Provenance-backed citations
  • Explicit insufficient-evidence responses
  • Docker and Neo4j full deployment

Tools5

What Veritasgraph lets your agent do. Expand a tool for its parameters.

Verified live~432 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

7/7 checks healthy over the last 42d

What it can do

From the 5 tools this server returned when we ran it.

Read-only tools · 5
Network at startup2 connections
Files written at startupNone

Observed 2026-10-24 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 1d ago via OSV.dev · veritasgraph-mcp (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars325Stargazers on the source repository.
Last commit2d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed5Callable tools this server registers over MCP.

How Veritasgraph works

What veritasgraph does

veritasgraph provides a GraphRAG workflow exposed through MCP for agents that need structured retrieval and evidence-backed answers. Instead of relying only on vector similarity, it combines tree-search organization with knowledge-graph relationships. The project emphasizes provenance recorded during ingestion, reproducible graph traversal, and answers that can abstain when the available evidence is insufficient.

The server is intended for enterprise and governed-agent scenarios where source attribution and local deployment are important. Its examples include medical and pharmaceutical workflows, fact-checking, agent orchestration, and construction-drawing analysis. The construction example turns floorplan PDFs into structured rooms, dimensions, openings, fixtures, and schedules, then builds a graph that supports quantity-takeoff queries with source-sheet provenance.

How it works

Queries use graph relationships and tree structure to identify connected evidence. The retrieval trace is deterministic, while language-model generation remains separate from the evidence path.

When required graph relationships or supporting evidence are unavailable, the workflow can return an insufficient-evidence result instead of filling the gap with a guess. The MedTrust example extends this approach with mandatory document-and-chunk citations, authorization checks, and a tamper-evident audit log.

Setup and configuration

Install the package with pip and start the lightweight demonstration with:

Terminal
pip install veritasgraph
veritasgraph demo --mode=lite

Lite mode uses cloud APIs and requires an OpenAI or Anthropic API key; the quick-start example shows OPENAI_API_KEY. Local mode uses Ollama and can run offline, with the example specifying the llama3.2 model:

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

The repository also shows python -m veritasgraph_mcp for running from the repository root, with local Ollama required for ingestion and querying. Full mode uses Docker and Neo4j:

bash
veritasgraph start --mode=full

The project targets Python 3.10 or newer. Local use is described as requiring Ollama and 8 GB of RAM.

Tools and capabilities

  • Ingest and query graph-backed knowledge using local Ollama-based workflows.
  • Run a cloud-backed lite mode with OpenAI or Anthropic APIs.
  • Run an offline mode for privacy-sensitive deployments.
  • Use graph traversal and tree-search structure for multi-step retrieval.
  • Preserve provenance for citation-grounded responses.
  • Abstain when the graph lacks sufficient evidence.
  • Support a full deployment using Docker and Neo4j.
  • Process floorplan PDFs into graph data and quantity-takeoff outputs in the featured example.

Limitations and notes

The available modes have different dependencies. Lite mode needs a cloud-provider API key, local mode needs Ollama and suitable local resources, and full mode needs Docker and Neo4j. The repository presents the MedTrust Agent as an example implementation of the governed-agent architecture, rather than as a general description of every deployment.

The server is released under the MIT license. Python 3.10 or later is required for the package.

Read the full README View source on GitHub

Reviews

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

Frequently Asked Questions about Veritasgraph

veritasgraph is an MCP server that connects agents to a GraphRAG pipeline using local Ollama, cloud OpenAI or Anthropic APIs, and optionally Neo4j. Its main operations support document ingestion and graph-backed querying, with tree-search structure, provenance tracking, citation-grounded answers, and insufficient-evidence responses.

Install it with `pip install veritasgraph`, then run `veritasgraph demo --mode=lite` for the quick-start demonstration. The project also supports starting the module directly with `python -m veritasgraph_mcp` from the repository root.

Yes, veritasgraph supports an offline local mode using Ollama. Run `veritasgraph demo --mode=local --model=llama3.2`; the local setup is described as requiring Ollama and 8 GB of RAM.

Full mode requires Docker and Neo4j. Start it with `veritasgraph start --mode=full` to use the full GraphRAG pipeline.

Yes, veritasgraph stores provenance during ingestion and uses it to support source-grounded answers. Its retrieval design can return insufficient evidence instead of guessing when the graph lacks the required supporting relationships.

Related MCP servers

All in Search & Data Extraction All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

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 PreviewVeritasgraph AllMCPs Directory Badge
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>