Swiss Truth MCP
Swiss Truth MCP
面向 AI 智能体的验证知识基础设施 — 经过认证的事实,而非幻觉。
Swiss Truth 是一个专为 AI 智能体构建的人工 + AI 验证知识库。 每一条事实都经过 5 阶段验证流程,包含置信度评分、已验证的来源 URL 以及 SHA256 完整性哈希。 30 秒即可连接。无需 API 密钥。
为什么智能体使用 Swiss Truth
问题 | Swiss Truth 工具 |
🧠 LLM 在事实性问题上的幻觉 |
|
📎 无法引用来源或验证引用 |
|
⏰ 快速变化主题的训练数据陈旧 |
|
⚖️ 受监管领域的违规响应 |
|
✅ 发送响应前验证多项声明 |
|
🔍 完整响应的幻觉风险 |
|
Related MCP server: verification-mcp
快速设置
MCP (Claude Desktop, Cursor, Windsurf, 任何 MCP 客户端)
{
"mcpServers": {
"swiss-truth": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://swisstruth.org/mcp"]
}
}
}或直接通过 HTTP:
{
"mcpServers": {
"swiss-truth": {
"type": "http",
"url": "https://swisstruth.org/mcp"
}
}
}LangChain
pip install swiss-truth-langchainfrom swiss_truth_langchain import SwissTruthToolkit
toolkit = SwissTruthToolkit()
tools = toolkit.get_tools() # search, verify, batch verify, citations, freshness, complianceCrewAI
pip install swiss-truth-crewaifrom swiss_truth_crewai import SwissTruthSearchTool, SwissTruthVerifyTool
from crewai import Agent
researcher = Agent(
role="Research Agent",
tools=[SwissTruthSearchTool(), SwissTruthVerifyTool()]
)AutoGen
pip install swiss-truth-autogenfrom swiss_truth_autogen import register_swiss_truth_functions
register_swiss_truth_functions(assistant, user_proxy)
# Adds: search_knowledge, verify_claim, verify_claims_batch, get_knowledge_briefOpenAI 函数调用
import requests
tools = requests.get("https://swisstruth.org/openai-tools.json").json()
# Ready-to-use tool definitions for OpenAI API, LlamaIndex, etc.14 个 MCP 工具
🔍 检索
工具 | 描述 |
| 对 2000+ 条认证事实进行语义搜索。自动检测语言 (DE/EN/FR/IT/ES/ZH/AR/RU/JA/KO)。返回置信度评分、来源 URL、SHA256 哈希。 |
| 单项声明的完整来源:验证者、机构、审查日期、SHA256。 |
| 为 RAG 管道优化的结构化、可引用知识摘要。 |
| 浏览所有 30 个知识领域及其认证声明数量。 |
✅ 验证
工具 | 描述 |
| 事实核查:返回 |
| 并行验证多达 20 项声明。返回每项声明的结论 + 摘要。 |
| 检查完整 AI 响应的幻觉风险: |
| 查找所有与某陈述相矛盾的认证声明。 |
📎 引用与质量
工具 | 描述 |
| 格式正确的内联 + APA 引用,附带已验证的来源 URL。 |
| 检测陈旧的训练数据。返回 |
| 瑞士/欧盟合规性检查 (FINMA, BAG, GDPR, 欧盟 AI 法案)。 |
📥 贡献与反馈
工具 | 描述 |
| 提交缺失的事实以供专家审查。触发 AI 预筛选 + URL 验证。 |
| 跟踪审查流程: |
| 报告缺失的领域或功能 — 反馈将塑造路线图。 |
30 个知识领域
🇨🇭 瑞士 (11): swiss-health · swiss-law · swiss-finance · swiss-education · swiss-energy · swiss-transport · swiss-politics · swiss-agriculture · swiss-digital · swiss-environment · labor-employment
🇪🇺 欧盟与全球 (6): eu-law · eu-health · global-science · international-law · economics · us-law
🔬 科学与技术 (8): ai-ml · ai-safety · quantum-computing · cybersecurity · biotech · renewable-energy · space-science · blockchain-crypto
🌍 通用 (5): climate · world-science · world-history · mental-health · nutrition-food
智能体角色
智能体类型 | 主要工具 | 使用场景 |
研究智能体 |
| 基于已验证事实的研究 |
法律合规 |
| FINMA, BAG, GDPR, 欧盟 AI 法案 |
RAG 管道 |
| 用已验证事实丰富检索内容 |
事实核查 |
| 防止幻觉 |
健康咨询 |
| KVG, Krankenkasse, Swissmedic |
金融智能体 |
| 符合 FINMA 标准的信息 |
发现端点
智能体和爬虫可通过标准端点发现 Swiss Truth:
端点 | 标准 | 用途 |
| RFC 8615 | MCP 自动发现 |
| OpenAI | GPT / Assistants API 集成 |
| Swiss Truth | 智能体能力清单 |
| llmstxt.org | LLM 爬虫发现 |
| OpenAI | 函数调用工具定义 |
验证流程
每条声明在认证前均需通过 5 阶段流程:
Submit → AI Pre-Screen → URL Verification → Expert Review → Peer Review → Certified ✓SHA256 完整性哈希 — 检测篡改
区块链锚定 — 每周链上 Merkle 根
置信度评分 — 多维质量评分
自动更新 — 过期声明每日重新验证
符合欧盟 AI 法案 — 完整审计追踪
知识统计
指标 | 数值 |
认证声明 | 2000+ |
领域 | 30 |
语言 | 10 |
验证阶段 | 5 |
人工验证 | ✓ |
SHA256 完整性 | ✓ |
区块链锚定 | ✓ |
符合欧盟 AI 法案 | ✓ |
需要 API 密钥 | ✗ |
查询示例
"Is health insurance mandatory in Switzerland?"
"What does the EU AI Act require for high-risk AI systems?"
"How does RAG reduce LLM hallucinations?"
"What are the FINMA regulations for crypto assets?"
"What is the current status of quantum error correction?"
"How does Swiss mandatory health insurance work?"链接
🌐 网站: swisstruth.org
📊 信任与统计: swisstruth.org/trust
🔌 MCP 端点:
https://swisstruth.org/mcp📦 npm 包:
npx -y mcp-remote https://swisstruth.org/mcp🐍 PyPI LangChain:
pip install swiss-truth-langchain🐍 PyPI CrewAI:
pip install swiss-truth-crewai🐍 PyPI AutoGen:
pip install swiss-truth-autogen
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityBmaintenanceSearch 1,500+ pre-verified, cited knowledge units across 16 domains. 6 tools: query, batch query, get unit, list domains, suggest topics, report issues. Free, no API key required.62371MIT
- FlicenseNot gradedqualityBmaintenanceEnables AI agents to fact-check claims, verify citations, and check source freshness using Wikipedia, Wikidata, Crossref, and Wayback Machine.1

Qinisoofficial
AlicenseAqualityBmaintenanceThe deterministic fact-verification layer for AI agents. Validates the structured facts an agent emits — IBANs, payment cards, VAT and national tax IDs, crypto and bank addresses, domains, emails, phone numbers, securities and academic identifiers, plus dates, currencies and holidays — against checksums and curated authoritative data, not guesses.561Apache 2.0- AlicenseAqualityAmaintenanceLicensed, rights-cleared content for AI agents, 17 tools to discover, license, retrieve, and verify expert content with on-chain proof and EU AI Act Article 53 support.83911MIT
Related MCP Connectors
Verified, sourced, real-time intelligence layer for AI agents.
Real-time fact-check, citation verification, and source-freshness for AI agents.
Verified, citable German & EU law for any LLM. Daily updates from official sources, hosted in DE.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/swisstruthorg/swiss-truth-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server