Pg Readonly MCP
MCP serverRead-only Postgres access for agents that parses SQL and refuses write-capable roles
Runs locally- Open source
- Databases
Read-only Postgres access for agents that parses SQL and refuses write-capable roles
Runs locallyCheck an AI agent endpoint's reliability and get a trust decision before calling it
Not checked yetSeller trust checks and signed receipts for AI agents that pay x402 services
Not checked yetOn-premises document retrieval for agents, with folder-level access rules checked first
Runs locallyRead-only scam checks for messages, npm packages and crypto addresses before you act
Runs locallyRead-only npm preflight: reviews what install scripts do before packages run
Runs locallyPreflight x402 endpoints, check signed receipts and get settlement attestations in USDC
Not checked yetOWASP API Top 10 tests from your OpenAPI spec, plus scanner SARIF judged for release.
Runs locallyRedact EU personal data from text and files before an LLM sees it, and restore it later
Runs locallyCommit-time policy gate for AI agent writes: ALLOW, DENY or STEP_UP with audit receipts
Runs locallyTamper-evident local record of what your AI agent did, plus verifiable markdown memory
Runs locallyRug-risk checks for Solana and pump.fun tokens, free basics and USDC-paid depth
Runs locallySend passwords and API keys as encrypted links that open only once
Runs locallyGuard agents' PostgreSQL and MySQL access with SQL audit, masking and write approval
Not checked yetImage and video analysis over MCP: NSFW detection, object detection and thumbnails
Not checked yetRole-aware onboarding answers about a codebase, filtered to what the caller may see
Not checked yet
Remote MCP server that gives AI agents independently signed receipts for what they claim
Not checked yetMCP server for verifiable randomness, provably fair games and signed receipts via FairSeal
Runs locallyFind and strip zero-width, bidi and tag characters hidden in text, offline
Runs locallyCheck an agent work row, post one and preflight a no-spend cap before spending
Runs locallyAccess control for AI agents: allow, hold for approval or block each tool call
Runs locallyCNCF release intelligence: typed changes from release notes and local stack checks
Runs locallyNeutral witness that countersigns agent-to-agent messages and attests risky agent actions
Not checked yetMCP server and open protocol for signed messages between agents with human-gated approvals
Runs locally
34 agent tools: free prompt-injection scans and checks plus pay-per-call data via x402
Not checked yetDomain intelligence: compromised checks, new registrations, Top 1M ranks and zone stats
Not checked yetAnchor document hashes on the Doichain blockchain as tamper-evident timestamps
Not checked yetBreach, SIM swap, infostealer, lookalike domain and prompt-injection checks for agents
Runs locallyStep-order enforcement for AI agents: ALLOW or DENY each step, with signed receipts
Not checked yetSigned, hash-chained receipts of agent tool-call decisions, verifiable offline
Runs locally