io.github.swisstruthorg/swiss-truth-mcp

Registre officiel IA et agents

Verified knowledge base for AI agents — stop hallucinations with certified facts.

Installation

Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).

NPM package swiss-truth-mcp

Claude Code

claude mcp add swiss-truth-mcp -e 'SWISS_TRUTH_API_KEY=<your swiss_truth_api_key>' -- npx -y swiss-truth-mcp@0.1.4

Configuration JSON (Claude Desktop, Cursor, VS Code)

{
    "mcpServers": {
        "swiss-truth-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "swiss-truth-mcp@0.1.4"
            ],
            "env": {
                "SWISS_TRUTH_API_KEY": "<your swiss_truth_api_key>"
            }
        }
    }
}

Variables d'environnement

SWISS_TRUTH_API_KEY secret Optional API key for write operations (submit_claim). Not required for read-only tools.

Documentation

Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.

Sommaire

Swiss Truth MCP
Why agents use Swiss Truth
Quick Setup
14 MCP Tools
30 Knowledge Domains
Agent Personas
Discovery Endpoints
Validation Pipeline
Knowledge Stats
Example Queries
Links

Swiss Truth MCP

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

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

Problem	Swiss Truth Tool
🧠 LLM hallucination on factual questions	`search_knowledge` — 2000+ certified facts, 30 domains
📎 Cannot cite sources or verify citations	`get_citations` — inline + APA with verified URLs
⏰ Stale training data on fast-changing topics	`check_freshness` — detect outdated facts
⚖️ Non-compliant responses in regulated domains	`check_regulatory_compliance` — FINMA, BAG, GDPR, EU AI Act
✅ Verify multiple claims before sending a response	`verify_claims_batch` — up to 20 claims in parallel
🔍 Full response hallucination risk	`verify_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

Tool	Description
`search_knowledge`	Semantic 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_claim`	Full provenance for a single claim: validator, institution, review date, SHA256.
`get_knowledge_brief`	Structured, citable knowledge brief optimized for RAG pipelines.
`list_domains`	Browse all 30 knowledge domains with certified claim counts.

✅ Verification

Tool	Description
`verify_claim`	Fact-check a statement: `supported` / `contradicted` / `unknown` with confidence + evidence.
`verify_claims_batch`	Verify up to 20 claims in parallel. Returns per-claim verdict + summary.
`verify_response`	Check a full AI response for hallucination risk: `low` / `medium` / `high`.
`find_contradictions`	Find all certified claims that contradict a statement.

📎 Citation & Quality

Tool	Description
`get_citations`	Properly formatted inline + APA citations with verified source URLs.
`check_freshness`	Detect stale training data. Returns `current` / `changed` / `unknown`.
`check_regulatory_compliance`	Swiss/EU compliance check (FINMA, BAG, GDPR, EU AI Act).

📥 Contribution & Feedback

Tool	Description
`submit_claim`	Submit a missing fact for expert review. Triggers AI pre-screening + URL verification.
`get_claim_status`	Track review pipeline: `draft` → `peer_review` → `certified`.
`report_agent_need`	Report 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 Type	Primary Tools	Use Case
Research Agent	`search_knowledge`, `get_knowledge_brief`, `get_citations`	Ground research in verified facts
Legal Compliance	`search_knowledge`, `check_regulatory_compliance`, `verify_claim`	FINMA, BAG, GDPR, EU AI Act
RAG Pipeline	`get_knowledge_brief`, `search_knowledge`, `get_citations`	Enrich retrieval with validated facts
Fact-Checking	`verify_claim`, `verify_claims_batch`, `verify_response`	Prevent hallucinations
Health Advisory	`search_knowledge`, `check_regulatory_compliance`, `check_freshness`	KVG, Krankenkasse, Swissmedic
Financial Agent	`search_knowledge`, `check_regulatory_compliance`, `verify_claim`	FINMA-compliant information

Discovery Endpoints

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

Endpoint	Standard	Purpose
`/.well-known/mcp.json`	RFC 8615	MCP auto-discovery
`/.well-known/ai-plugin.json`	OpenAI	GPT / Assistants API integration
`/agents.json`	Swiss Truth	Agent capability manifest
`/llms.txt`	llmstxt.org	LLM crawler discovery
`/openai-tools.json`	OpenAI	Function-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

Metric	Value
Certified claims	2000+
Domains	30
Languages	10
Validation stages	5
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?"

Questions fréquentes

Qu'est-ce que io.github.swisstruthorg/swiss-truth-mcp ?

Verified knowledge base for AI agents — stop hallucinations with certified facts.

Comment installer io.github.swisstruthorg/swiss-truth-mcp ?

Il s'exécute sur votre machine. Dans Claude Code : claude mcp add swiss-truth-mcp -e 'SWISS_TRUTH_API_KEY=<your swiss_truth_api_key>' -- npx -y swiss-truth-mcp@0.1.4. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.

Faut-il une clé API pour io.github.swisstruthorg/swiss-truth-mcp ?

Oui. Il attend SWISS_TRUTH_API_KEY, à renseigner dans sa configuration.

io.github.swisstruthorg/swiss-truth-mcp est-il open source ?

Son code est public sur GitHub, mais le dépôt ne déclare pas de licence standard.

Qui maintient io.github.swisstruthorg/swiss-truth-mcp ?

Il est publié par swisstruthorg. AI.tn le référence sans le maintenir ni le recommander.

Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.

Détails du serveur

Référencé dans: Registre MCP officiel
Éditeur: swisstruthorg
Catégorie: IA et agents
Exécution: Local
Étoiles GitHub: ★ 0
Langage: Python
Dernier commit: 30 avr. 2026
Tickets ouverts: 0
Version: 0.1.4
Publié le: 13 avr. 2026

io.github.swisstruthorg/swiss-truth-mcp

Serveurs similaires

WorkFlow Companion Claude on Windows or Linux works in your WorkFlow tasks, notes and projects via your ow...
Myndock Pulse Explore agent polls and discover private collaboration. Public read-only MCP; no API ke...
Chenfeng AI Public Information MCP Read-only public services, cases, resources and FAQ from Chenfeng AI.
GreatWait Reliable one-off and recurring HTTPS callbacks for apps and agents.
Demo Bakery (fictional AgentVisibly demo) Fictional demo business showing an AgentVisibly-hosted small-business MCP server. Not r...
Jpo Patent Info JPO patent information: Japanese patent, utility model and trademark status from the Ja...
Z1N MCP server for the Z1N Protocol - on-chain identity for AI agents on Polygon
Pollinations Access Pollinations models and API capabilities through agent tools.

IA et agents