Read-only MCP server that lets an agent read and verify its own tamper-evident action log
Runs locally- Open source
- Security
Read-only MCP server that lets an agent read and verify its own tamper-evident action log
Runs locallyLocal ACT, BLOCK or ESCALATE check that runs before an AI agent takes an action
Runs locally
Read-only guarded SQL access to eight database engines for AI agents
Runs locallyRead-only library of 24 defensive security skills served over MCP
Not checked yetScreen documents for edits, failed redactions and prompt injection before agents read them
Runs locallyMove files into an end-to-end encrypted vault, verified first, and tidy local folders
Runs locallyRead-only crypto forensics for agents: token deployers, OFAC matches, exchange attribution
Not checked yetCheck who controls an EVM token and what admin powers it has, before you buy
Not checked yetSee who can upgrade, mint or pause an EVM contract or Safe, down to the signing keys
Not checked yetCheck an AI agent you did not build: identity, mandate and tamper-evident work record
Not checked yetScan AI images for marks, C2PA metadata and watermarks, then clean them with spend caps
Runs locallyShare agent skills across a team, scan them for risk and track which are used
Runs locallyPhone carrier, email, IP and DNS lookups billed from your LookupLab credits
Not checked yet
Reconciliation evidence for AI agent payments: declared, executed and observed onchain
Not checked yet
Public MCP tools to check payment policy and verify or create agent payment receipts
Not checked yetTamper-evident evidence log: signed heads, proofs and recorded SHA-256 digests
Not checked yetScreens wallets and names against OFAC lists before an AI agent pays or trusts anyone
Not checked yetGuard that holds risky MCP tool calls for human approval and signs the decisions
Not checked yetScore text and web pages for signs of AI writing, and check images for hidden instructions
Not checked yetCheck whether a product version is FIPS 140-3 validated, in NIST's queue or expiring
Runs locallyCheck a short or unknown URL before your agent fetches it, with a fetch or skip answer
Not checked yetMCP server for checking ERC-8004 agents on Base: track record, reputation and fraud flags
Not checked yetCaller ID, spam and fraud risk lookups for phone numbers, plus name and email search
Not checked yetThreat reports on files, URLs, domains and IPs for MCP clients, via VirusTotal's VTAI
Not checked yetStandards client that gives agents encrypted memory through your own SAIHM operator
Runs locallyCheck an x402 endpoint and its on-chain payer history before your agent pays it
Runs locallyCheck an AI agent's INAM reputation before trusting it and sign receipts for finished work
Not checked yet
Identity-aware AI tool gateway: every call runs as the requester, under rules, with audit
Not checked yetSend and read end-to-end encrypted documents from your own machine, by agent or CLI
Runs locallyPost-quantum ML-DSA-65 signatures, provenance seals and decision receipts paid via x402
Runs locallySee every kind of AI for security: tools, agents, MCP servers and skills.Ranked: the best AI for security.