- verifiable-claim-seed @elwsls/verifiable-claim-seedZero-dependency verifiable-claims MCP: validate safely, verify with allow_execution, self-test.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Greenlit Books @greenlitbooks/catalogSearch the Greenlit AI books, read any chapter one free, and look up the terms they define.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- retriEVAL @hcarrillo001/retrieval-mcpLLM evals as MCP tools: score outputs for faithfulness, relevancy, and hallucination.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- Infobroker @flukeatzerocool/infobrokerMulti-provider research MCP server: unified web search, fact-checking, personal knowledge base.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- MCP x402 - Evidence-Backed Web Verification @diogoup26/mcp-x402Evidence-backed x402 web verification for AI agents, with auditable decisions for every condition.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Andreax @moralito311-andr/andreax270 pay-per-call AI tools for agents, paid via x402 (USDC on Base). No signup, no API keys.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- referencesource.org @joelp22-maker/referencesourceVerified reference data; each record carries its source URL and quote. verify_quote checks claims.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- FinanceRateCalc HMDA statistics @financeratecalc/frc-mcp2025 US FHA mortgage record statistics, with a gate that checks AI sentences preserve the evidence19% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Kaval @usekaval/kavalVerify the facts an agent's action depends on before it acts — ALLOW, REVIEW, or BLOCK.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Tru8 Evidence Research @samyatessmith/tru8Source-traced evidence research for AI agents. We organise the evidence; you decide.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- GeniusFlow Evidence @kaydeep0/geniusflow-federationRe-check pinned sources, package and cite. Live Federation MCP. No account.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Scrapecheck @fieldmodellc/scrapecheckVerify before your agent acts on data it paid for. Signed verdicts, checkable offline, via x402.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Truth Bear - GAUGE verifiable signals @changchinfu/mcp-gaugeVerify official facts with Bitcoin-anchored proof. 180+ signals, x402 pay-per-call.15% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Muffed — verified NFL stats and fantasy context @muffed/muffedVerified NFL stats and Sleeper league context. Every figure carries its own source rank.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Oathlayer @oathlayer/oathlayerVerify AI outputs against real sources. Returns a trust signal and permanent doc number.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Zetesis Scientific Due Diligence @reutavidan/zetesisDue diligence on life-science claims: omics, trials, gene therapy. Dimension by dimension.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agent Toolbox @solhammer/agent-toolbox26 deterministic, offline pre-action safety gates for AI agents, each with a signed verdict.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Verifi @verifi/human-verificationGet a real human to verify, decide, or improve an AI agent's work. Pay per review via x402 on Base.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Off-Nadir Delta @offnadir-delta/mcpFrom first signal to satellite evidence: live world-event intelligence and collection planning.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Lenz Fact-Check @lenz/fact-checkCheck the factual claims in a draft or an answer: a quick verdict, or a deep check with sources.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Verity Skills @cchurctrip/verityReal-time social media and prediction market integrity layer for traders, funds, and quant desks.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Swiss Truth @swisstruthorg/swiss-truth-mcpVerified knowledge base for AI agents — stop hallucinations with certified facts.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- vuln-intel @rozetyp/vuln-intelFree hosted CVE intel for bug-bounty agents: CVE fact-check, attack approaches from paid H1 reports19% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Sprout MCP @mepsopti/sprout-mcpModel-tiered content pipeline — cheap models seed, expensive models verify5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
