Verified Knowledge Base for AI Agents — No More Hallucinations

@swisstruthorg

About Verified Knowledge Base for AI Agents — No More Hallucinations

Verified knowledge base for AI agents via MCP — certified facts with source references, confidence scores, and SHA256 integrity hashes

#knowledge #fact-checking #hallucination #rag #swiss #multilingual #verified #swiss-law #health #finance #climate #ai-ml

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "swiss-truth-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli@latest",
        "run",
        "martin111ma-za5d/swiss-truth-mcp",
        "--client",
        "claude"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Verified Knowledge Base for AI Agents — No More 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. It connects in 30 seconds with no API key required.

How to use Verified Knowledge Base for AI Agents — No More Hallucinations?

Integrate via MCP (Claude Desktop, Cursor, Windsurf) using a simple JSON config with npx -y mcp-remote https://swisstruth.org/mcp or as an HTTP server. Also available as Python packages for LangChain (pip install swiss-truth-langchain), CrewAI (pip install swiss-truth-crewai), and AutoGen (pip install swiss-truth-autogen). For OpenAI function-calling, fetch tool definitions from https://swisstruth.org/openai-tools.json.

Key features of Verified Knowledge Base for AI Agents — No More Hallucinations

2000+ certified facts across 30 domains
10 languages auto-detected
14 MCP tools: search, verify, cite, check freshness, regulatory compliance
5-stage validation pipeline with SHA256 integrity hashes
Blockchain anchoring and EU AI Act compliant
No API key required, free to start

Use cases of Verified Knowledge Base for AI Agents — No More Hallucinations

Ground AI research in verified facts to prevent hallucination
Ensure regulatory compliance (FINMA, BAG, GDPR, EU AI Act)
Enrich RAG pipelines with citable, validated knowledge briefs
Batch fact-check up to 20 claims in a single request
Detect stale training data with freshness checks

FAQ from Verified Knowledge Base for AI Agents — No More Hallucinations

What exactly is Swiss Truth?

Swiss Truth is a human + AI validated knowledge base that certifies facts through a 5-stage pipeline (AI pre-screen, URL verification, expert review, peer review). Each claim is assigned a confidence score, source URLs, and a SHA256 integrity hash.

Does it require an API key?

No. The service is open and free – no API key is needed to query the knowledge base.

What domains and languages are supported?

30 domains across Swiss, EU, global, science, and general topics (e.g., swiss-health, eu-law, ai-ml, climate). The system auto-detects 10 languages: German, English, French, Italian, Spanish, Chinese, Arabic, Russian, Japanese, Korean.

How do I integrate with my AI agent?

You can use the MCP endpoint (https://swisstruth.org/mcp) directly in any MCP-compatible client, or install Python packages for LangChain, CrewAI, and AutoGen. OpenAI function-calling tool definitions are available via a REST endpoint.

Is there a limit on the number of queries?

The README does not state explicit limits. Up to 20 claims can be verified in parallel using the verify_claims_batch tool.

Frequently asked questions

What exactly is Swiss Truth?

Does it require an API key?

No. The service is open and free – no API key is needed to query the knowledge base.

What domains and languages are supported?

How do I integrate with my AI agent?

You can use the MCP endpoint (`https://swisstruth.org/mcp`) directly in any MCP-compatible client, or install Python packages for LangChain, CrewAI, and AutoGen. OpenAI function-calling tool definitions are available via a REST endpoint.

Is there a limit on the number of queries?

The README does not state explicit limits. Up to 20 claims can be verified in parallel using the `verify_claims_batch` tool.

Comments

Basic information

More Memory & Knowledge MCP servers

Memory

modelcontextprotocol

Model Context Protocol Servers

88.1K

Rust Docs MCP Server

Govcraft

🦀 Prevents outdated Rust code suggestions from AI assistants. This MCP server fetches current crate docs, uses embeddings/LLMs, and provides accurate context via a tool call.

286

Tempreon

Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.

ctxfile

Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.

Docs MCP Server

arabold

Grounded Docs MCP Server: Open-Source Alternative to Context7, Nia, and Ref.Tools

1.5K