
Universal DB (read-only)
MCP serverRead-only guarded SQL access to eight database engines for AI agents
Runs locally- 11 tools
- Open source
- Databases

Read-only guarded SQL access to eight database engines for AI agents
Runs locally
Check whether an AI agent holds TAP certifications, read live from the chain
Not checked yetSearch plain-English Web3 security articles and a glossary of about 230 terms
Not checked yetRead-only library of 24 defensive security skills served over MCP
Not checked yetFree public registry that proves a document or web page existed on a given date
Not checked yetCheck whether an existing content-use grant is still valid, without fetching content
Not checked yetGuard that holds risky MCP tool calls for human approval and signs the decisions
Not checked yetTLS certificate, DNS and web security checks with an OK, WARN or CRITICAL verdict
Not checked yetEmbed a text box that proves a human typed the text, with signed proof tokens
Not checked yetScore a website for AI-agent safety, llms.txt and machine-readable signals
Runs locallyRead-only access to Cyber Library, a free structured cybersecurity knowledge base
Not checked yetStandards client that gives agents encrypted memory through your own SAIHM operator
Runs locallyCheck an agent's proposed action against its operator's mandate: permit, deny or escalate
Not checked yetLook up malicious and vulnerable npm packages, free and without an API key
Not checked yetKeyless access to verified AI voice-clone scam incidents, loss statistics and guidance
Not checked yetCheck 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 yetDecode ERC-20 approvals and token calls and compare them with the amount you expect
Not checked yetRecords a buyer's service request and checks what the service actually delivered
Not checked yetChecks A2A, MCP and OpenAPI declarations and logs dated changes to what suppliers publish
Not checked yetSelf-check MCP server giving AI agents that spend money an indicative A-D risk grade
Not checked yetLocal scanner that checks webhook handlers for missing or unsafe signature verification
Runs locallySelf-hosted AI memory on Postgres and pgvector, with hybrid search and a knowledge graph
Runs locallyFree network, auth and web utilities for agents with no key and a zero-log policy
Not checked yetAuthorization checks that decide whether an AI agent may make an x402 payment
Not checked yetMCP server that checks whether an x402 seller actually delivered before an agent pays
Runs locallyConsent-based, end-to-end encrypted messaging between AI agents with a public ledger
Runs locallyCheck what an npm package or file does at install time before your agent installs it
Not checked yetOffline secret scanning MCP server that returns redacted findings to coding agents
Runs locallymacOS Keychain secret broker where an agent can use your API keys but never read them
Runs locally