- DOS — the trust substrate for agent fleets @anthony-chaudhary/dos-kernelVerify what agents actually shipped, arbitrate file collisions, refuse with structured reasons.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.20 GitHub stars.
- BrowseAI Dev @browseai-hq/browseai-devEvidence-backed web research for AI agents with citations and confidence scores.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.20 GitHub stars.
- Baron Munchausen @shinegang/baronLocal grounded memory for coding agents: MCP over stdio, stdlib only, a verdict per answer6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.13 GitHub stars.
- Mathlas @archerkattri/mathlasAirtight math for AI agents: 3.68M-doc theorem search + numeric/Lean verification. No LLM, no key.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.13 GitHub stars.
- Boson Video @linboxin/boson-videoLet your AI read any video: timed transcript, full-resolution frames, screen text, claim checks.Not assessed yet.Runs on your machine, installed from PyPI.12 GitHub stars.
- Glassbox Framework @thebarmaeffect/glassbox-frameworkRuntime constitutional verification for AI answers — claim reasoning, ECS, red team, audits.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.11 GitHub stars.
- Growmos @codician/growmosLiving knowledge graph for your repo: query with citations, remember/link facts, fact-check claims.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.9 GitHub stars.
- Iris @iris-eval/mcp-serverStop shipping agents on vibes. Score every agent output for quality, safety, and cost.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.9 GitHub stars.
- PyEuropePMC @jonasheinickebio/pyeuropepmcSearch and analyse scientific literature across Europe PMC, PubMed, arXiv, and ClinicalTrials.gov3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.8 GitHub stars.
- GroundLens @groundlens-dev/groundlensVerify AI answers and executions and seal signed, offline-verifiable evidence records.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.7 GitHub stars.
- RE-call MCP Memory Server @giulioder/re-callAgent memory on your own Postgres that flags superseded facts and abstains instead of guessing.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.6 GitHub stars.
- Jev MCP @freepik-company/jev-mcpTyped decisions with Jev / System One via OpenRouter or TypeSafe: classify, verify, rerank, decide.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.3 GitHub stars.
- Chamber @abm9111/chamberIndexed note: numbers, capitalised names, file names. Local, no model, no meaning check.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Factcheck @carlisia/mcp-factcheckAn MCP server that validates content against MCP specification using semantic search and AI5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.3 GitHub stars.
- Omni Nli @cogitatortech/omni-nliAn MCP server for natural language inference3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- footnote-mcp @kazkozdev/footnote-mcpSource-grounded web research: search, extraction, verification, and browser automation.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Arkheiaai MCP @arkheiaai/mcp-serverDetect fabrication and hallucination in any LLM output. 30+ models supported.15% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Agentic Research @theaisingularity/agentic-researchLocal research agent that verifies its own answers. Runs on Gemma 3 4B + Ollama, $0/query.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Physbound @jonesrobm/physboundPhysical Layer Linter: validates RF and radar calculations against hard physical limits.2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- NebulaMind @duhokim/nebulamindAI astronomy wiki with open agent peer-review. Vote on evidence, propose edits, earn reputation.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Chainward @saltxd/chainwardCheck a Base or BNB Chain address before you pay it: on-chain risk reports, EAS attestations.Not assessed yet.Runs on your machine, installed from npm.1 GitHub stars.
Fact-checking MCP servers
A server here checks factual claims in news, posts or AI answers against sources and gives a verdict.
Not here: servers that merely cite their sources, sign or certify data, or verify identities.
262 remote122 localTagged by Odel's AI, which can make mistakes
Most popular in Fact-checking
By GitHub stars, at most two per publisher- Number 1: MemoryIndustry@leandropg19/memory-industryMemoryIndustry persistent memory MCP server: BM25+MMR retrieval and audit.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.29 GitHub stars.
- Number 2: Cuba Memorys@leandropg19/cuba-memorysPersistent memory MCP server. 28 tools, BM25+MMR+OOD retrieval, tamper-evident audit, code graph.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.29 GitHub stars.
- Number 3: LastSearch@lastsearch-hq/lastsearchEvidence-backed web research for AI agents with citations and confidence scores.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.20 GitHub stars.
