mcpField
V
Verified Knowledge Base for AI Agents — No More Hallucinations

Verified Knowledge Base for AI Agents — No More Hallucinations

Local
swisstruth.orgMemory & Knowledge0Updated 26w ago

About Verified Knowledge Base for AI Agents — No More Hallucinations

Swiss Truth is a verified knowledge service for AI agents, covering 30 domains with sourced facts and validation metadata. Its MCP tools support search, claim and response checking, citations, freshness checks, and regulatory compliance.

Key features

  1. 01Search verified facts across domains
  2. 02Verify claims and full responses
  3. 03Retrieve citations and provenance
  4. 04Check fact freshness
  5. 05Check Swiss and EU compliance
  6. 06Submit claims for expert review

Use cases

  1. 01Ground research in sourced facts
  2. 02Check claims before sending a response
  3. 03Assess regulatory compliance
  4. 04Enrich RAG pipelines with citable briefs

MCP support

The remote MCP server at `https://swisstruth.org/mcp` exposes 14 tools for knowledge retrieval, verification, citations, freshness, compliance, and feedback. It can be connected through HTTP or `mcp-remote`.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"swiss-truth": {
"command": "npx",
"args": [
"-y",
"@smithery/cli"
]
}
}
}
Run commandnpx -y @smithery/cli

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@smithery/cli

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Swiss Truth MCP

Verified knowledge infrastructure for AI agents — certified facts, not hallucinations.

MCP Domains Claims Languages EU AI Act Auth LangChain CrewAI AutoGen

Swiss Truth is a human + AI validated knowledge base purpose-built for AI agents. Every fact passes a 5-stage validation pipeline, carries a confidence score, verified source URLs, and a SHA256 integrity hash. Connect in 30 seconds. No API key required.


Why agents use Swiss Truth

ProblemSwiss Truth Tool
🧠 LLM hallucination on factual questionssearch_knowledge — 2000+ certified facts, 30 domains
📎 Cannot cite sources or verify citationsget_citations — inline + APA with verified URLs
⏰ Stale training data on fast-changing topicscheck_freshness — detect outdated facts
⚖️ Non-compliant responses in regulated domainscheck_regulatory_compliance — FINMA, BAG, GDPR, EU AI Act
✅ Verify multiple claims before sending a responseverify_claims_batch — up to 20 claims in parallel
🔍 Full response hallucination riskverify_response — low / medium / high risk score

Quick Setup

MCP (Claude Desktop, Cursor, Windsurf, any MCP client)
{
  "mcpServers": {
    "swiss-truth": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://swisstruth.org/mcp"]
    }
  }
}

Or directly via HTTP:

{
  "mcpServers": {
    "swiss-truth": {
      "type": "http",
      "url": "https://swisstruth.org/mcp"
    }
  }
}
LangChain
pip install swiss-truth-langchain
from swiss_truth_langchain import SwissTruthToolkit

toolkit = SwissTruthToolkit()
tools = toolkit.get_tools()  # search, verify, batch verify, citations, freshness, compliance
CrewAI
pip install swiss-truth-crewai
from swiss_truth_crewai import SwissTruthSearchTool, SwissTruthVerifyTool
from crewai import Agent

researcher = Agent(
    role="Research Agent",
    tools=[SwissTruthSearchTool(), SwissTruthVerifyTool()]
)
AutoGen
pip install swiss-truth-autogen
from 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_brief
OpenAI function-calling
import requests

tools = requests.get("https://swisstruth.org/openai-tools.json").json()
# Ready-to-use tool definitions for OpenAI API, LlamaIndex, etc.

14 MCP Tools

🔍 Retrieval
ToolDescription
search_knowledgeSemantic search over 2000+ certified facts. Auto-detects language (DE/EN/FR/IT/ES/ZH/AR/RU/JA/KO). Returns confidence score, source URLs, SHA256 hash.
get_claimFull provenance for a single claim: validator, institution, review date, SHA256.
get_knowledge_briefStructured, citable knowledge brief optimized for RAG pipelines.
list_domainsBrowse all 30 knowledge domains with certified claim counts.
✅ Verification
ToolDescription
verify_claimFact-check a statement: supported / contradicted / unknown with confidence + evidence.
verify_claims_batchVerify up to 20 claims in parallel. Returns per-claim verdict + summary.
verify_responseCheck a full AI response for hallucination risk: low / medium / high.
find_contradictionsFind all certified claims that contradict a statement.
📎 Citation & Quality
ToolDescription
get_citationsProperly formatted inline + APA citations with verified source URLs.
check_freshnessDetect stale training data. Returns current / changed / unknown.
check_regulatory_complianceSwiss/EU compliance check (FINMA, BAG, GDPR, EU AI Act).
📥 Contribution & Feedback
ToolDescription
submit_claimSubmit a missing fact for expert review. Triggers AI pre-screening + URL verification.
get_claim_statusTrack review pipeline: draft → peer_review → certified.
report_agent_needReport missing domains or features — feedback shapes the roadmap.

30 Knowledge Domains

🇨🇭 Swiss (11): swiss-health · swiss-law · swiss-finance · swiss-education · swiss-energy · swiss-transport · swiss-politics · swiss-agriculture · swiss-digital · swiss-environment · labor-employment

🇪🇺 EU & Global (6): eu-law · eu-health · global-science · international-law · economics · us-law

🔬 Science & Tech (8): ai-ml · ai-safety · quantum-computing · cybersecurity · biotech · renewable-energy · space-science · blockchain-crypto

🌍 General (5): climate · world-science · world-history · mental-health · nutrition-food


Agent Personas

Agent TypePrimary ToolsUse Case
Research Agentsearch_knowledge, get_knowledge_brief, get_citationsGround research in verified facts
Legal Compliancesearch_knowledge, check_regulatory_compliance, verify_claimFINMA, BAG, GDPR, EU AI Act
RAG Pipelineget_knowledge_brief, search_knowledge, get_citationsEnrich retrieval with validated facts
Fact-Checkingverify_claim, verify_claims_batch, verify_responsePrevent hallucinations
Health Advisorysearch_knowledge, check_regulatory_compliance, check_freshnessKVG, Krankenkasse, Swissmedic
Financial Agentsearch_knowledge, check_regulatory_compliance, verify_claimFINMA-compliant information

Discovery Endpoints

Swiss Truth is discoverable by agents and crawlers via standard endpoints:

EndpointStandardPurpose
/.well-known/mcp.jsonRFC 8615MCP auto-discovery
/.well-known/ai-plugin.jsonOpenAIGPT / Assistants API integration
/agents.jsonSwiss TruthAgent capability manifest
/llms.txtllmstxt.orgLLM crawler discovery
/openai-tools.jsonOpenAIFunction-calling tool definitions

Validation Pipeline

Every claim passes a 5-stage pipeline before certification:

Submit → AI Pre-Screen → URL Verification → Expert Review → Peer Review → Certified ✓
  • SHA256 integrity hash — detect tampering
  • Blockchain anchoring — weekly Merkle root on-chain
  • Confidence scoring — multi-dimensional quality score
  • Auto-renewal — expired claims re-verified daily
  • EU AI Act compliant — full audit trail

Knowledge Stats

MetricValue
Certified claims2000+
Domains30
Languages10
Validation stages5
Human validated✓
SHA256 integrity✓
Blockchain anchored✓
EU AI Act compliant✓
API key required✗

Example Queries

"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?"

Links

  • 🌐 Website: swisstruth.org
  • 📊 Trust & Stats: swisstruth.org/trust
  • 🔌 MCP Endpoint: https://swisstruth.org/mcp
  • 📦 npm package: 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

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.