- Corroborate @chefcohen/corroborate-mcpHonest claim corroboration for AI agents: syndication-aware independent-source counting.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- andon @gulmezeren2-byte/andonDeterministic verification for AI-generated analysis: run a spec, inspect or diff a workbook4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- groundcheck — decision-grade fact verification @beepboop2025/groundcheckVerify claims, resolve FIGI identity, extract claims, and sign x402 delivery receipts over MCP.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Citeguard @xiaweiyi713/citeguardFalsification-first citation auditor: existence, metadata, and claim-support checks via MCP.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Concordance @narrowhighway/concordanceDeterministic claim verification with receipts across ~60 domains. No model in the loop.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Stillos Notary @stillmarcus24/stillos-notary-mcpAttestation infrastructure for the agentic economy: signed, independently verifiable verdicts.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Opengate @nickjlamb/opengate-mcpCheck whether an AI answer is grounded in its context — deterministic, no LLM judge.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- eleata Claim Verifier @hernaninverso/eleata-verify-mcpGrounding/hallucination guard: verify a claim against evidence (Supported/Refuted/NEE).5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Grounded Reasoning @alexaquarius/grounded-reasoningVerify multi-hop relational claims before an agent asserts them — zero tokens, with proof paths.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Citation Verification @guptaprakhariitr/verification-mcpReal-time fact-check, citation verification, and source-freshness for AI agents.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Datumline Agent Guard @datumline/agent-guardChecks an AI agent's 'done' against the files and URLs it claims. Missing = FALSE_DONE.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- check-claim @piiiico/check-claimCheck that a source really says what your claim says, before you publish. Verbatim, multi-path.Not assessed yet.A remote server; no sign-in.
- Dunstan @barglabs/dunstanChecks a coding agent's handback against the pull request's GitHub record. No model decides.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Ransack @chancewalker165-dot/ransackWeb search & fetch MCP for AI agents: 12 engines, one key, flat $15/mo at ransack.tools.14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- POKT Agent tools @jsymen1290/pokt-agentPine Script backtest-trap checks, backtest reconciliation and official Korean finance data.Not assessed yet.A remote server; no sign-in.
- Rootpublish AI facts check @rootpublish/ai-factsCheck what an AI assistant tells buyers about a company against the company's own pricing pages.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Web Evidence @impanyu/web-evidencePaid claim verification with cited web evidence, source provenance, snapshots, and hashes.Not assessed yet.A remote server; no sign-in.
- ClaimGate - claim check before you publish @caseone115/claimgateFlag marketing claims your evidence cannot substantiate, before you publish.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- ClaimGate starter kit - set up a publish gate @caseone115/claimgate-kitSet up a publish gate for AI-assisted marketing copy: policy, evidence folder and CI job.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- honesty-mcp @lkopietz3-byte/honesty-mcpMCP server exposing 11 honesty-SDK kits (grounding, trust, audit, corroboration) as agent tools.Not assessed yet.Runs on your machine, installed from npm.
- Cyberwarex Council @cyberwarex/cyberwarex-councilSecond opinion for agents: 3-4 AI models answer, one verdict with confidence and dissent.12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- GAIP Procurement Evidence Agent @tjcgraham-rgb/gaip-procurement-verifyNow part of GAIP Witness: tests supplier claims and compares them with published metadata.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Stipple — Reference Verification @stipple/openwarrant-verifyFact-check citations: resolve, match, support claims. Arithmetic rechecked. Free to start.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- FDA import alert red lists @joelp22-maker/referencesource-import-alertsIs a foreign supplier on an FDA import alert red list, detained at the US border? 14,000+ listings.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
