_ registry / mcp http-sse · checked 1h ago

swiss-truth

https://swisstruth.org

Registry code: d2f72d24a437b7b7

api record

Verified knowledge base for AI agents delivering certified facts with confidence scores and source references.

from a public catalogue that lists it, not from the operator

endpoint
https://swisstruth.org/mcp
protocol
http-sse ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing
karma
0 · newcomer
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
100ms

last good check

priced tools
0

of 18 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ used through this hub 30 days

The one measurement on this page that an operator cannot produce by editing a file on its own server: somebody else chose it, and paid to. Read the accounts before the calls — volume from one account is one relationship, and calling yourself is the cheap half. Both are what the ranking is built from, printed so the order can be checked rather than taken on trust.

accounts
0

distinct, expensive to fake

calls served
0

successful, last 30 days

_ what it can do 18 tools
1 open 17 never probed 1 of 18 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • list_domains open 1h ago

    List all available knowledge domains with certified claim counts. USE THIS TOOL at the start of a session or when unsure which domain to search. Returns domain IDs (use in search_knowledge 'domain' parameter), names, and descriptions. Domains cover: Swiss law, health, finance, education, energy, transport, politics, agriculture, climate, AI/ML, world science, and world history.

    mcp-tool

    {
  "type": "object",
  "properties": {}
}
    arguments 4 lines
  • search_knowledge unknown never probed

    Search the Swiss Truth verified knowledge base for certified facts. USE THIS TOOL when you need reliable, source-backed information to avoid hallucination — covering 22+ domains: Swiss law, health, finance, politics, education, energy, transport, EU law & regulation, EU health, global science, AI/ML, AI safety, quantum computing, cybersecurity, biotech, renewable energy, space science, economics, international law, US law, climate, world history, and Swiss digitalization. Call this before answering factual questions where being wrong would matter. Returns per result: - 'claim': the verified statement - 'canonical_question': the exact question this claim answers (high match = high relevance) - 'confidence': certified score (0–1) - 'effective_confidence': age-adjusted score — lower means renewal is overdue - 'source_references': validated primary sources (no Wikipedia) - 'validated_by': expert name + institution - 'hash': SHA256 for tamper detection Examples: 'How does Swiss health insurance work?', 'What does the EU AI Act require?', 'How does RAG reduce hallucinations?', 'What are CRISPR gene therapy safety limits?', 'What is the current state of quantum error correction?'

    mcp-tool

    {
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "default": 5,
      "description": "Number of results to return (max 20, default 5)."
    },
    "query": {
      "type": "string",
      "description": "Natural language query in DE, EN, FR, or IT. Phrase it as a question for best results."
    },
    "domain": {
      "type": "string",
      "description": "Optional domain filter. Available domains: Swiss: 'swiss-health', 'swiss-law', 'swiss-finance', 'swiss-education', 'swiss-energy', 'swiss-transport', 'swiss-politics', 'swiss-agriculture', 'swiss-digital'. EU & Global: 'eu-law', 'eu-health', 'global-science', 'international-law', 'economics'. Science & Tech: 'ai-ml', 'ai-safety', 'quantum-computing', 'cybersecurity', 'biotech', 'renewable-energy', 'space-science'. General: 'climate', 'world-science', 'world-history', 'us-law'. Omit to search across all domains."
    },
    "language": {
      "type": "string",
      "description": "Optional language override: 'de', 'en', 'fr', 'it', 'es', 'zh'. If omitted, language is auto-detected from the query. Response includes 'detected_language' and 'language_fallback' (true if no results were found in detected language)."
    },
    "min_confidence": {
      "type": "number",
      "default": 0.8,
      "description": "Minimum confidence threshold 0.0–1.0. Default 0.8. Use 0.95+ for critical facts."
    }
  }
}
    arguments 30 lines
  • get_claim unknown never probed

    Retrieve a single verified claim with full provenance by its ID. USE THIS TOOL after search_knowledge when you need the complete citation: who validated it, which institution, on what date, and the SHA256 integrity hash. Also returns 'effective_confidence' (age-adjusted) to assess if renewal is needed.

    mcp-tool

    {
  "type": "object",
  "required": [
    "claim_id"
  ],
  "properties": {
    "claim_id": {
      "type": "string",
      "description": "UUID of the claim, obtained from search_knowledge results."
    }
  }
}
    arguments 12 lines
  • submit_claim unknown never probed

    Submit a new factual claim for expert review and certification. USE THIS TOOL when you identify a knowledge gap — a fact that should be in the knowledge base but isn't. The claim goes through: AI pre-screening → URL verification → source content check → human expert peer review → certification. Requirements: one atomic statement (not compound), factual (not opinion), at least one primary source URL (not Wikipedia). Returns a claim_id — use get_claim_status to track progress.

    mcp-tool

    {
  "type": "object",
  "required": [
    "claim_text",
    "domain_id"
  ],
  "properties": {
    "language": {
      "type": "string",
      "default": "de",
      "description": "Language code: 'de', 'en', 'fr', or 'it'. Default: 'de'."
    },
    "question": {
      "type": "string",
      "description": "The canonical question this claim answers (e.g. 'How does Swiss mandatory health insurance work?'). Significantly improves retrieval quality."
    },
    "domain_id": {
      "type": "string",
      "description": "Domain ID (e.g. 'ai-ml', 'swiss-health', 'climate'). Use list_domains to see all options."
    },
    "claim_text": {
      "type": "string",
      "description": "The factual statement — one single, clear, verifiable claim. Max 2000 characters."
    },
    "source_urls": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Primary source URLs that directly support the claim (e.g. arxiv.org, bag.admin.ch). Strongly recommended. No Wikipedia."
    }
  }
}
    arguments 33 lines
  • verify_claim unknown never probed

    Fact-check a claim against the Swiss Truth knowledge base. USE THIS TOOL in ReAct loops when you need to verify whether a statement is true, false, or unknown. Ideal for: checking AI-generated content, validating user inputs, or grounding responses. Returns: - 'verdict': 'supported' | 'contradicted' | 'unknown' - 'confidence': 0.0–1.0 — how certain the verdict is - 'explanation': brief reason - 'evidence': list of certified claims that support or contradict, each with source_references Examples: 'Health insurance is mandatory in Switzerland', 'The SNB sets negative interest rates', 'GPT-4 uses 1 trillion parameters'

    mcp-tool

    {
  "type": "object",
  "required": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "The factual statement to verify. One clear, atomic claim."
    },
    "domain": {
      "type": "string",
      "description": "Optional domain filter (e.g. 'swiss-health', 'ai-ml'). Omit to search all domains."
    },
    "language": {
      "type": "string",
      "description": "Optional language override ('de', 'en', 'fr', etc.). Auto-detected if omitted."
    }
  }
}
    arguments 20 lines
  • get_claim_status unknown never probed

    Check the current validation status of a submitted claim. USE THIS TOOL after submit_claim to track progress through the review pipeline: 'draft' → 'peer_review' → 'certified' (or back to 'draft' if rejected). Also returns confidence score and validator info once certified.

    mcp-tool

    {
  "type": "object",
  "required": [
    "claim_id"
  ],
  "properties": {
    "claim_id": {
      "type": "string",
      "description": "UUID returned by submit_claim."
    }
  }
}
    arguments 12 lines
  • verify_claims_batch unknown never probed

    Verify multiple factual claims in parallel against the Swiss Truth knowledge base. USE THIS TOOL when you need to fact-check several statements at once — e.g. before sending a response that contains multiple factual assertions. Much faster than calling verify_claim repeatedly. Returns per claim: - 'verdict': 'supported' | 'contradicted' | 'unknown' - 'confidence': 0.0–1.0 - 'evidence': certified claims that support or contradict Also returns a 'summary' with counts of supported/contradicted/unknown.

    mcp-tool

    {
  "type": "object",
  "required": [
    "claims"
  ],
  "properties": {
    "claims": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "List of factual statements to verify. Max 20 items."
    },
    "domain": {
      "type": "string",
      "description": "Optional domain filter applied to all claims (e.g. 'swiss-health', 'ai-ml')."
    }
  }
}
    arguments 19 lines
  • verify_response unknown never probed

    Check a full AI response paragraph for hallucination risk. USE THIS TOOL before sending a multi-sentence response to a user — it atomizes the text into individual claims, verifies each against the knowledge base, and returns an overall hallucination risk score. Returns: - 'hallucination_risk': 'low' | 'medium' | 'high' - 'verified': number of statements backed by certified facts - 'contradicted': number of statements contradicted by certified facts - 'unverified': number of statements with no evidence (knowledge gap) - 'coverage_rate': fraction of statements that are verified (0.0–1.0) - 'statements': per-statement breakdown with verdict and sources

    mcp-tool

    {
  "type": "object",
  "required": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "The full response text to check. Can be a paragraph or multiple sentences."
    },
    "domain": {
      "type": "string",
      "description": "Optional domain filter (e.g. 'swiss-health'). Omit to search all domains."
    }
  }
}
    arguments 16 lines
  • find_contradictions unknown never probed

    Find certified claims in the knowledge base that contradict a given statement. USE THIS TOOL as a safety check before publishing facts, or to surface knowledge conflicts. Unlike verify_claim (which gives a single verdict), this tool returns ALL contradicting certified claims with explanations — useful for understanding why a claim is disputed. Returns: - 'contradictions': list of certified claims that contradict the input - 'contradiction_confidence': how strongly each certified claim contradicts - 'explanation': why the certified claim contradicts - 'total': number of contradictions found

    mcp-tool

    {
  "type": "object",
  "required": [
    "claim_text"
  ],
  "properties": {
    "domain": {
      "type": "string",
      "description": "Optional domain filter (e.g. 'swiss-law', 'ai-ml')."
    },
    "claim_text": {
      "type": "string",
      "description": "The factual statement to check for contradictions."
    }
  }
}
    arguments 16 lines
  • get_knowledge_brief unknown never probed

    Get a structured, citable knowledge brief on any topic. USE THIS TOOL when you need to enrich your response with verified facts — returns a ready-to-use summary with key facts, source URLs, and confidence scores. Better than search_knowledge when you want a formatted, agent-ready output. Returns: - 'brief': formatted text ready to include in your response - 'key_facts': list of verified facts with claim_id, confidence, sources - 'sources': all verified source URLs - 'confidence': average confidence across all facts

    mcp-tool

    {
  "type": "object",
  "required": [
    "topic"
  ],
  "properties": {
    "topic": {
      "type": "string",
      "description": "The topic or question to get a knowledge brief on."
    },
    "domain": {
      "type": "string",
      "description": "Optional domain filter (e.g. 'swiss-health', 'ai-ml')."
    },
    "language": {
      "type": "string",
      "description": "Optional language filter ('de', 'en', 'fr', 'it'). Auto-detected if omitted."
    },
    "max_facts": {
      "type": "integer",
      "default": 5,
      "description": "Maximum number of key facts to include (default 5, max 10)."
    }
  }
}
    arguments 25 lines
  • get_citations unknown never probed

    Get properly formatted citations for a factual claim. USE THIS TOOL when you need to cite sources in your response — solves the #1 agent problem: inability to provide verified citations. Finds the best matching verified claim and returns formatted citations. Returns: - 'formatted.inline': inline citation e.g. '[Swiss Truth, 2025]' - 'formatted.apa': APA-style citation with source URL - 'citations': list of verified source URLs with metadata - 'best_match': the verified claim that best matches your statement

    mcp-tool

    {
  "type": "object",
  "required": [
    "claim_text"
  ],
  "properties": {
    "domain": {
      "type": "string",
      "description": "Optional domain filter."
    },
    "claim_text": {
      "type": "string",
      "description": "The factual statement you want to cite."
    },
    "citation_style": {
      "type": "string",
      "default": "inline",
      "description": "Citation format: 'inline' | 'apa' | 'all'. Default: 'inline'."
    }
  }
}
    arguments 21 lines
  • check_freshness unknown never probed

    Check if a factual claim is still current and up-to-date. USE THIS TOOL when you're unsure if your training data is outdated — especially for fast-changing topics (AI, regulations, statistics, policies). Returns: - 'freshness_status': 'current' | 'changed' | 'unknown' - 'latest_version': the current verified version of the fact (if changed) - 'last_reviewed': when this fact was last verified - 'recommendation': what to do with this information - 'age_warning': if the verified version itself is getting old

    mcp-tool

    {
  "type": "object",
  "required": [
    "claim_text"
  ],
  "properties": {
    "domain": {
      "type": "string",
      "description": "Optional domain filter."
    },
    "claim_text": {
      "type": "string",
      "description": "The factual statement to check for freshness."
    },
    "known_as_of": {
      "type": "string",
      "description": "ISO date string of when you last knew this fact (e.g. '2024-01-01'). Optional."
    }
  }
}
    arguments 20 lines
  • check_regulatory_compliance unknown never probed

    Check if agent-generated text complies with Swiss/EU regulations. USE THIS TOOL before sending responses in regulated domains: finance (FINMA), health (BAG/Swissmedic), law (OR/ZGB), EU law (GDPR/AI Act). Identifies potentially non-compliant statements and suggests corrections. Returns: - 'compliant': true if no factual conflicts found - 'issues': list of keyword flags and factual conflicts - 'recommendations': domain-specific compliance rules to follow - 'regulator': the relevant regulatory authority

    mcp-tool

    {
  "type": "object",
  "required": [
    "text",
    "domain"
  ],
  "properties": {
    "text": {
      "type": "string",
      "description": "The agent-generated text to check for compliance."
    },
    "domain": {
      "type": "string",
      "description": "Regulatory domain: 'swiss-finance' | 'swiss-health' | 'swiss-law' | 'eu-law'."
    }
  }
}
    arguments 17 lines
  • report_agent_need unknown never probed

    Report what you need from Swiss Truth that's currently missing. USE THIS TOOL when you can't find what you need — your feedback directly shapes what Swiss Truth builds next. We review all agent feedback weekly. Use when: - You searched but found nothing (request_type: 'missing_claim') - You need a domain that doesn't exist (request_type: 'missing_domain') - You found a wrong/outdated claim (request_type: 'quality_issue') - You need a feature that doesn't exist (request_type: 'feature_request') - A topic area has too few claims (request_type: 'coverage_gap')

    mcp-tool

    {
  "type": "object",
  "required": [
    "request_type",
    "details"
  ],
  "properties": {
    "details": {
      "type": "string",
      "description": "What do you need? Be specific — what topic, what use case, what's missing?"
    },
    "domain_hint": {
      "type": "string",
      "description": "Which domain/topic area? (e.g. 'swiss-mietrecht', 'quantum-error-correction')"
    },
    "request_type": {
      "type": "string",
      "description": "Type: 'missing_domain' | 'missing_claim' | 'quality_issue' | 'feature_request' | 'integration_issue' | 'coverage_gap'"
    },
    "agent_framework": {
      "type": "string",
      "default": "unknown",
      "description": "Your framework: 'langchain' | 'crewai' | 'autogen' | 'openai' | 'anthropic' | 'custom' | 'unknown'"
    },
    "query_that_failed": {
      "type": "string",
      "description": "The exact query that returned no results."
    }
  }
}
    arguments 30 lines
  • register_agent unknown never probed

    Register your AI agent with Swiss Truth to earn a public Trust Score badge. USE THIS TOOL once at agent startup to unlock: - 🏆 Trust Score badge (Bronze/Silver/Gold) — embed in your README - 🔔 Domain update alerts via webhook - 📊 Usage analytics and claim dependency tracking Registration is idempotent — safe to call on every startup. The agent_id must be stable across sessions.

    mcp-tool

    {
  "type": "object",
  "required": [
    "agent_id",
    "name"
  ],
  "properties": {
    "name": {
      "type": "string",
      "description": "Human-readable name for this agent."
    },
    "agent_id": {
      "type": "string",
      "description": "Stable unique identifier for this agent (e.g. 'my-research-agent-v2'). Must not change between sessions."
    },
    "framework": {
      "type": "string",
      "default": "unknown",
      "description": "Agent framework: 'langchain' | 'crewai' | 'autogen' | 'openai' | 'anthropic' | 'custom' | 'unknown'"
    },
    "description": {
      "type": "string",
      "description": "What does this agent do? (optional)"
    },
    "webhook_url": {
      "type": "string",
      "description": "URL to receive domain update alerts (optional)."
    },
    "primary_domains": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Domains this agent primarily works with (e.g. ['swiss-law', 'eu-law']). Optional."
    }
  }
}
    arguments 37 lines
  • subscribe_domains unknown never probed

    Subscribe to domain update alerts via webhook. USE THIS TOOL after register_agent to get notified when new claims are certified in your domains of interest. Your webhook receives a POST with the new claim whenever it's certified. This keeps your agent's knowledge current without polling. Earns +5 Trust Score points per active subscription.

    mcp-tool

    {
  "type": "object",
  "required": [
    "agent_id",
    "domains",
    "webhook_url"
  ],
  "properties": {
    "events": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Events: 'claim.certified' | 'claim.updated' | 'claim.expired'. Default: ['claim.certified', 'claim.updated']."
    },
    "domains": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Domain IDs to subscribe to (e.g. ['swiss-law', 'eu-law', 'swiss-health'])."
    },
    "agent_id": {
      "type": "string",
      "description": "Your registered agent_id (must call register_agent first)."
    },
    "webhook_url": {
      "type": "string",
      "description": "URL to receive POST notifications when new claims are certified."
    }
  }
}
    arguments 32 lines
  • get_trust_score unknown never probed

    Get your Swiss Truth Trust Score (0–100). USE THIS TOOL to check your current tier and see how to level up. Tiers: - 🔰 Starter (0+): Registered - 🥉 Bronze (20+): Regular user - 🥈 Silver (50+): Power user across multiple domains - 🥇 Gold (80+): Deep integration Returns badge URL to embed in your README.md.

    mcp-tool

    {
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string",
      "description": "Your registered agent_id."
    }
  }
}
    arguments 12 lines
  • get_my_usage unknown never probed

    Get your usage statistics and claim dependencies. USE THIS TOOL to see which claims your agent depends on, which domains you use most, and your Trust Score progress. Returns: query count, unique claims used, top domains, top 5 most-used claims, and Trust Score breakdown.

    mcp-tool

    {
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string",
      "description": "Your registered agent_id."
    }
  }
}
    arguments 12 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/d2f72d24a437b7b7/badge.svg)](https://brick.blue/agent/d2f72d24a437b7b7)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Own the domain? Prove it and the listing carries a verified badge here too: passport.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.