Veritasgraph runs on your own machine — the client starts it, so there is no endpoint to ping. 53 installs a week from pypi. Last commit 18 Sep 2026.
Zero-trust, air-gapped Enterprise GraphRAG MCP server with offline, citation-grounded answers.
We read the source, 23 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
result = subprocess.run(
filepath = os.path.join(INPUT_DIR, filename)
should_update = (
(i + 1) % update_interval == 0 or
data = pickle.load(f)
"!pip install -q veritasreason"
"2. AWS credentials file (~/.aws/credentials)\n",
tr.innerHTML = cells;
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add veritasgraph -- uvx veritasgraph-mcp
{
"mcpServers": {
"veritasgraph": {
"args": [
"veritasgraph-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.veritasgraph]
command = "uvx"
args = ["veritasgraph-mcp"]
{
"mcpServers": {
"veritasgraph": {
"args": [
"veritasgraph-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"veritasgraph": {
"args": [
"veritasgraph-mcp"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
VERITASGRAPH_MODEL (Default local Ollama model for ingest/query (e.g. qwen3:latest).), OLLAMA_HOST (Local Ollama endpoint.), STUDIO_DATA_DIR (Directory where the knowledge-graph snapshot is persisted.).
The author declared them in the registry entry; get the values from the project itself.
Enterprise SAP OData to MCP Server with AI capabilities and Cloud Foundry integration
Governed support MCP: answers only KB-grounded questions with citations, escalates the rest.
Web search, scraping, RAG answers with citations, and translation as MCP tools.
Search, scrape, and crawl the web for AI agents. Batch scraping and answers with citations.
Android engineering MCP server with verified documentation grounding and AI validation tools.
Enterprise-grade MySQL MCP Server with OAuth 2.0, 106 tools, and Docker deployment
Web search and AI answers with real source citations and a confidence score.
MCP server for Godot game engine integration — control the Godot editor with AI
Answers built from our own checks of this server.