- TypeSafe MCP @renwang-huang/typesafe-mcpHost-neutral MCP bridge for TypeSafe AI Jev judgments with typed review, routing, and gate tools.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- GoAI Moat Claim Verifier @goaimoat/claim-verifierVerify business claims and audit text for unsourced data.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- crosscheck @crosscheckapi/crosscheckChecks for AI agents over x402: review drafts, accept-check handoffs, scan skills before install.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Rattlewatch @veritylabsai/rattlewatchCited US recall lookup for AI agents: CPSC and FDA data, nothing invented.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Arbitype @renwang-huang/arbitypeTyped decision tools for AI agents, powered by TypeSafe Jev.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Web Hygiene MCP @luca-003/web-hygiene-mcpLive web checks for AI agents: sitemaps, robots.txt, URL status, broken links, feeds, citations.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Verity @veritylabsai/verityCited product-compliance ground truth for AI agents. Never generates; always cites.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Stringer Grounded Synthesizer @getstringer/synthesizerGrounded synthesis from public sources. 3 free calls total; then $0.10 brief or $0.25 deep via x402.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Shoon A2A Trust Services (pilot) @shoonenterprises/shoon-a2a-sandboxFive trust services for agents: claim checks, citation audits, extraction, tripwires, work audits.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- TinyFish Guided Research @mohdsaleh/tinyfish-guided-researchAuditable deep-research MCP server powered by TinyFish Search and Fetch.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Research MCP @research-mcp-hq/research-mcpCited research MCP (MCP+agent infra): brief, lookup. Fail=$0.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- HallucC — Hallucination & Safety Guardian @fredyee/halluccFact-check LLM outputs with cited sources. API key: aihcc.cloud/keys.19% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- VerifyAPI — fact-check with signed receipts @kythekitty/verifyapiFact-check any claim with live web sources. Ed25519-signed receipts. Catches hallucinations.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Nota @pugarhuda/notaRead-only crypto research skills that check a price, RSI and ATR against independent sources.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- AgentIndex x402 @agentindex/x402Jev-powered decisions, web search, PDF/web to Markdown, summarize. From $0.001, no API key.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Verify @drain54/verify-apiAI claim verification MCP endpoint with x402 payments and stealth web fetch34% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Probe V0 @lexbritten/probeExperimental MCP server for current empirical verification of explicit public HTTPS endpoint claims.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Verify API @mgdsn/verify-api-mcpEvidence-backed verification for citations, packages, repos, cases, filings, drugs, x402 sellers.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Stipple — Document Verification & Extraction @stipple/openwarrantDocument forensics: tamper/AI checks, fields, tables, identity, screening, tenders, citations.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Verify Claim @sudo-ai-git/mcp-verify-claimForce evidence-gated, tiered claim reporting (FACT/INFERENCE/SPECULATION). No-LLM.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Universal Research @mp-juns/universal-research-mcpProvenance-first research memory with hash-bound evidence and a fail-closed eligibility gate.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Quorum @godzilla-lab/quorumMarket evidence with receipts: every claim resolves to a real stored record you can fetch back.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- 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.
