
Veritasgraph
io.github.bibinprathap由 GitHub 账号 bibinprathap 发布v0.2.0更新于 Nov 11, 2026
Zero-trust, air-gapped Enterprise GraphRAG MCP server with offline, citation-grounded answers.
概览
本地部署的 GraphRAG MCP 服务器,让助手查询受治理的知识图谱,获得带引用的答案,或在证据不足时明确表示无法回答。
- 可以做什么
- 以探索或受治理模式对本地知识图谱提问,返回引用、接地标记与弃答结果
- 在消耗模型调用前检查问题是否可回答,并回放历史答案及其回执与反馈
- 读取并提议本体条目、术语表词条与实体类型,并检索术语
- 摄取文档、导入导出图谱、合并实体,并管理快照与审计日志
- 通过受治理的语义层查询已连接的 SQL 数据源,以生成的 SQL 作答
- 适用场景
- 适合需要助手基于自有文档与内部数据库作答、且答案必须可核验引用的场景,并要求在无证据时明确弃答而非猜测。适用于必须留在本地环境的合规、科研与企业检索工作。
- 运行要求
- 以 Python 包形式本地运行(Python 3.10+),需要本地 Ollama 端点(由 OLLAMA_HOST 指定)并已拉取 VERITASGRAPH_MODEL 指定的模型。SQLite 存储路径由 VERITASGRAPH_DB 或 STUDIO_DATA_DIR 设置,工具层级由 VERITASGRAPH_MCP_MODE 选择。可选的结构化数据层还需单独的数据源连接串与密钥设置。
安装
在 SourceWeft 中
- 打开 控制台中的 Veritasgraph,将其添加到工作区。
- 为需要使用其工具的对话启用该服务。
Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。
其他 MCP 客户端
参照 仓库 中的启动说明。
README
VeritasGraph — The Governed, On-Prem GraphRAG & Agent Framework
A knowledge graph your agents can trust: every answer cites its sources, the vocabulary is governed by a certified ontology, and the system says "I don't know" instead of guessing. Runs 100% locally.
[VeritasGraph Logo][PyPI version] [Python 3.10+] [License: MIT] [CI] [GitHub Stars] [MCPVault: claimed] [M8ven Score]
🎯 Traditional RAG guesses based on similarity. VeritasGraph reasons based on structure — and refuses to answer when the evidence isn't there.
🌐 Live site · 🎮 Try the Studio live · ⭐ Star · 🍴 Fork · 💬 Discuss · 🐛 Report a bug
[Building Auditable Deep-Research Agents — Live at MBZUAI] [VeritasGraph Master Demo]
✨ What's new
📑 Table of contents
- Quick start
- Architecture
- Core concepts — attribution · ontology · compiler · governed mode · governance · PII · structured data
- VeritasGraph Studio
- Security model
- MCP server
- CLI
- Configuration
- API overview
- Deployment
- Development & tests
- Examples & ecosystem
- Vision RAG Python package (PyPI)
- Why VeritasGraph?
- Acknowledgments, awards & citation
🚀 Quick start
Option A — Local (Python + Ollama)
Studio asks for the token the first time you open it and keeps it for the browser session. To run a local demo without auth, set STUDIO_AUTH=off (Studio logs a warning on startup); never do this on a shared or public host.
Option B — Docker Compose
Studio is published on 127.0.0.1:8200 only.
Option C — MCP server for your IDE agent
See MCP server for IDE registration.
One-command end-to-end demo
This builds a graph and drives a fully wired agent through graph reasoning, memory recall, PII redaction and a guardrail block:
🏗️ Architecture
Studio, MCP and the CLI are thin layers over the same engine and store. A graph built in Studio can be queried from your IDE, and a compile run from the CLI shows up in the Studio Ontology tab. A shared job lock ensures only one compiler runs at a time.
🧠 Core concepts
Attribution, citations and abstention
- Attribution is a data model, not a prompt. Provenance is stored at write time: every entity and relation keeps the chunk it came from (
doc_xxx#n, orimp_xxx#nfor imported graphs). This prevents hallucinated citations at read time. - Deterministic retrieval. Graph traversal is reproducible, which separates the factual evidence trace from stochastic LLM generation.
- Strict citation check. Citations in the answer are compared with the sources that were actually retrieved. Mismatches are reported in
unknown_citationsand setgrounded: false. - Explicit abstention. If no entity matches the question, or governed mode can't ground the answer, the response sets
abstained: trueinstead of guessing.
Ontology & business glossary
The ontology is the governed vocabulary of the graph:
- Entity types, e.g.
Drug,Enzyme,Supplier. - Predicates, e.g.
inhibits, with optional domain/range constraints. - Glossary terms: business definitions with synonyms, linked to entities.
Once vocabulary is certified, it changes how the system behaves:
- Extraction limits entity types to the certified list and maps synonyms to the certified predicate.
- Compile uses the same mapping rules to clean up the existing graph.
- Governed mode answers only when certified terms cover the question.
Manage it in the Studio Ontology tab, through /ontology in the REST API, or with the MCP tools get_ontology, search_terms, get_term and propose_term.
The ontology compiler
veritasgraph compile, POST /graphrag/compile, or a timer set with VERITASGRAPH_COMPILE_INTERVAL runs these stages:
Only unambiguous mappings to certified vocabulary change the graph. Everything else is a suggestion that you accept or reject in Studio or via /graphrag/suggestions. Rejected suggestions are fingerprinted and don't come back. Every run is recorded (/graphrag/compile/runs) and audited.
Governed mode, answerability and receipts
POST /graphrag/answerable(MCP:check_answerable) tells an agent whether a question can be answered before it spends a model call.GET /graphrag/answers/{id}returns the receipt: question, mode, answer, citations, grounding and feedback.POST /graphrag/answers/{id}/feedbackrecords a rating for the answer so it can be reviewed later. Any viewer can rate an answer.
Governance: audit, snapshots, merge
- Hash-chained audit log. Every write (ingest, import, compile, certify, merge, clear, restore) appends a SHA-256-chained event.
GET /graphrag/audit/verifyrecomputes the chain and reports the event where it breaks (broken_at). - Snapshots. Create, list and restore snapshots (
/graphrag/snapshots). Clearing the graph always takes a snapshot first. Retention is set withVERITASGRAPH_SNAPSHOT_KEEP(default 20). - Entity merge.
POST /graphrag/entities/mergefolds duplicates together and keeps their relations and provenance. - Import / export. Bring in
graph.jsonfrom Graphify, Understand-Anything, AI-Atlas or a generic node/edge file. Merge strategies arepreserve_curated,skip_existingandoverwrite, with a--dry-runpreview.
PII policy
VERITASGRAPH_PII_POLICY controls what happens when ingested text contains email addresses, SSNs, credit card numbers (Luhn-validated), phone numbers or IP addresses:
PII in chunks is redacted on read for callers below VERITASGRAPH_PII_REVEAL_ROLE (default editor).
Structured data layer
Beyond documents, VeritasGraph can govern databases. Install with pip install -e ".[structured]" and set VG_STRUCTURED_DSN to a Postgres + pgvector store.
- Connect a source read-only: PostgreSQL, MySQL/MariaDB, SQLite, DuckDB, ClickHouse, Trino, Hive (
[structured-hive]), Snowflake or Databricks ([structured-saas]). Credentials are encrypted withVG_SECRET_KEY. - Sync the schema, then compile a semantic layer of datasets, fields, relationships, glossary terms and measures. These follow the same
proposed → certifiedworkflow. - Ask in natural language. The answer is generated SQL over certified objects, run under a statement timeout and a row cap, and returned with a receipt.
Source DSNs are guarded:
- A network allowlist (
VG_STRUCTURED_ALLOWED_NETWORKS) controls which hosts can be reached. - A file root (
VG_STRUCTURED_FILE_ROOT) limits SQLite and DuckDB to approved paths. - Dangerous driver options are refused.
See .env.structured.example for every setting, and the structured CLI / /structured API.
🖥️ VeritasGraph Studio
Studio is a local Agent Build Workspace (FastAPI + a single-page UI at /studio). You build a knowledge graph from your own documents, govern its vocabulary, and wire it into agents alongside tools, memory, data logging, guardrails and headroom-style context budgeting. You then chat with those agents and watch every stage of the orchestration pipeline.
🎮 Try the Studio live — a stable URL that always redirects to the currently running Studio tunnel.
Orchestration pipeline (per turn): Guardrails → Memory → Knowledge Graph → Headroom budget → Tools → Data log, with every step visible in the trace.
[Knowledge Graph builder and explorer] [Agent builder with capability toggles]
For full API details and curl recipes, see studio_api/README.md. For a guided enterprise scenario, see the Northwind Bank compliance playbook.
🔐 Security model
Auth is on by default. Studio refuses to start unless STUDIO_API_TOKENS is set or STUDIO_AUTH=off is set explicitly.
More controls:
- Public routes: only
/health,/readyand/studio; the UI shell holds no data. - SSRF protection: HTTP tools can't reach private, loopback or link-local addresses unless the address is listed in
STUDIO_TOOL_ALLOWED_NETWORKS. - CORS: set allowed origins with
STUDIO_CORS_ORIGINS. - MCP tiers:
VERITASGRAPH_MCP_MODElimits which tools an MCP client can see. In the Studio MCP bridge, tools are also limited by the caller's role. - PII: see PII policy.
🔌 MCP server
VeritasGraph ships a Model Context Protocol server: a zero-trust, air-gapped enterprise GraphRAG server for MCP. Claude Desktop, Cursor, VS Code, Windsurf, Cline and Continue connect over JSON-RPC 2.0 stdio with zero external data egress.
Resources: veritasgraph://graph, veritasgraph://stats, veritasgraph://ontology. Tools that aren't in the active mode are reported as unknown tools.
See veritasgraph_mcp/README.md for Claude Desktop, Cursor and VS Code registration snippets.
🏥 Use case — VeritasGraph MCP in production medical AI on Azure
Real-world deployment: the VeritasGraph MCP server runs on Azure Functions with Azure AI Foundry. It delivers GraphRAG-powered clinical decision support with verifiable citations and a compliance-ready architecture.
The challenge: 90% of Azure AI demos work. Most never ship. The gap isn't the model; it's architecture, security, state management and compliance.
The solution: VeritasGraph is deployed as a remote MCP server that Azure AI Foundry agents call to answer clinical questions with:
- ✅ Multi-hop GraphRAG reasoning: answers are assembled from separate graph edges.
- ✅ Verifiable citations: every claim traces to
[doc#chunk]sources. - ✅ Production-grade architecture: externalized state, identity at the boundary, observability.
- ✅ Compliance-ready: region-pinned, PHI-aware guardrails, semantic-layer RBAC.
Key production lessons:
- State externalization. Flex Consumption wiped in-memory graphs; this was fixed with a mounted Azure Files share.
- Identity at the boundary. Carry the Entra identity, and enforce Power BI RLS and Dataverse roles on behalf of the user.
- Self-correcting agents. Feed errors and the schema back, and retry up to 3× (e.g. for DAX generation).
- Compliance by design. Foundry guardrails block PHI-leaking requests before they reach the model.
- Observability layers. Application Insights, Foundry Traces, Evaluations and Alerts.
[Watch: VeritasGraph MCP on Azure AI Foundry]
- 📄 From Proof of Concept to Production: Azure AI That Actually Ships
- 💻 Azure AI Foundry + VeritasGraph implementation repository
💡 Key insight: the gap between proof of concept and production is architecture, not the model. Ground it, externalize state, secure it, observe it, make it resilient and keep it compliant.
🧰 CLI
pip install -e ".[studio]" installs the veritasgraph command:
The import command accepts --format values auto, graphify, understand_anything, ai_atlas and generic, and --source-type values curated, extracted and inferred.
⚙️ Configuration
The full reference is in studio_api/README.md.
🌐 API overview
The interactive OpenAPI docs are served at /docs. Main route groups:
🐳 Deployment
Share with your team (free)
*The free tier has some limitations. Always keep auth on for anything reachable from the internet, and rotate tokens that have been shared.
On-premise hardware guidance
Hardware: 16+ CPU cores, 64 GB+ RAM (128 GB recommended), and an NVIDIA GPU with 24 GB+ VRAM (A100 / H100 / RTX 4090) for larger local models.
Software: Docker and Docker Compose, Python 3.10+, NVIDIA Container Toolkit.
Copy .env.example to .env and fill in environment-specific values.
Provider support (OpenAI-compatible)
Studio talks to Ollama (OLLAMA_HOST). The structured layer and the GraphRAG pipeline in graphrag-ollama-config/ work with any OpenAI-compatible API. The structured layer stays local unless you set VG_LLM_ALLOW_REMOTE to allow a remote endpoint.
Azure OpenAI, OpenRouter, Anyscale and LocalAI are also supported.
⚠️ Embeddings must match your index. If you indexed with
nomic-embed-text(768 dims), you must query with the same model. Switching embedding models requires re-indexing.
🧪 Development & tests
CI runs ruff and pytest on Python 3.10 and 3.12. Browser end-to-end tests live in tests/studio-e2e (see VERITASGRAPH_PLAYWRIGHT_INTEGRATION_TESTS.md). Contributions are welcome; see CONTRIBUTING.md and SECURITY.md.
🧩 Examples & ecosystem
🏛️ Enterprise compliance — VeritasGraph + VeritasReason
GraphRAG is great at describing what documents say. Questions like "Which purchase orders violated our Segregation-of-Duties policy last quarter?" are rule-evaluation problems over structured records. VeritasReason is a deterministic reasoning engine (forward-chaining + Rete + SPARQL) that fires policy rules over a triple store and returns auditable answers with W3C PROV-O provenance.
[VeritasGraph + VeritasReason policy-compliance demo]
The rules live in rules/sod_policy.yaml and the SQL → triple mapping in ingest_structured.py. See veritas-reason/plan.md for a walkthrough.
Built with VeritasGraph
- MeAkash77 / VeritasGraph-Enterprise-GraphRAG-Verifiable-AI-Platform — enterprise GraphRAG adapter and verifiable AI platform patterns.
- PTP063 / veritas-graph — derivative project and live deployment.
- RahulSagar2005 / multi-hop-rag — multi-hop retrieval and reasoning workflows.
- lukehungngo / agentwall — agent security and governance-oriented reasoning flows.
- gajanan229 / Fact-checker-Agent — evidence-focused fact-checking.
- Minh-Tam-Solution / EndiorBot — enterprise chatbot built around graph-backed reasoning.
- NistorDorinGabriel / Proiect_Licenta — academic thesis extending VeritasGraph-inspired graph reasoning.
Building with VeritasGraph? Open a PR with a short repo description to be featured here.
📚 Guides & talks
- 📄 Build Governed AI Agents On-Prem (PDF): designing, wiring and shipping governed agents on your own infrastructure.
- ⚡ Live docs · 🎮 Live demo · 📖 Article · 📄 Research paper
[Build Governed AI Agents On-Prem — walkthrough] [Import any graph.json into VeritasGraph Studio — walkthrough]
[Watch VeritasGraph build reasoning paths in real time] [Convert charts & tables to knowledge graphs — Vision RAG tutorial]
📦 Vision RAG Python package (PyPI)
Note: the
veritasgraphpackage on PyPI is the Vision RAG / tree + graph library. It is separate from the Studio / MCP / governance stack in this repository. Both install averitasgraphcommand, so use separate virtual environments if you need both.
[Colab: Vectorless RAG] [Colab: Vision RAG] [Colab: Tree Accuracy]
Graph + Tree retrieval
The package also includes an interactive PyVis graph explorer. It shows a query-aware subgraph, colors nodes by community, highlights query entities in red, and sizes nodes by number of connections.
Why VeritasGraph?
[Traditional RAG vs VeritasGraph comparison]
Who is it for? Engineers building enterprise search, compliance assistants, research copilots, scientific literature explorers and agent memory systems: anywhere "the answer" depends on how facts connect, and where a wrong answer costs more than no answer.
🙌 Acknowledgments
Builds on the foundational work of HopRAG, Microsoft GraphRAG, LangChain & LlamaIndex, and Neo4j.
🏆 Awards & Citation
Presented at the International Conference on Applied Science and Future Technology (ICASF 2025) — 📄 Appreciation Certificate.
Star History
[stars] [issues] [forks] [license] [图片]
Licensed under MIT. ⭐ Star the repo to follow the roadmap for open-source, governed GraphRAG.
来源:README.md,提交 68552fd
工具
0版本历史
2- v0.2.0最新Nov 11, 2026
- v0.1.2Sep 16, 2026
评分
已满足适用检查项的 50%
该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。
- 近 30 天内可连通25 分
请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。
- 已声明认证方式10 分
请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。
- 已列出工具15 分
请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。
- 描述必需15 分
- 图标10 分
- 文档15 分
- 许可证10 分