Skills and Scars for AI agents - your agent records its failures and never repeats them.
Persistent memory + context layer for AI dev teams.
Search, install, publish & review security-scanned AI capabilities from ai-supply.store.
HREVN trust layer for baseline diagnostics and verifiable workflow integrity for AI agents.
Index your codebase.
AI E2E testing bridge — give AI eyes and hands inside any app.
Operate Notion with a single Markdown document — read, create, and update pages in one call.
Productivity framework for DevOps engineers using AI assistance (Claude Code) while working on PoCs
Architecture-aware MCP context with boundaries, seams, impact scope, and BGI-TWIN guidance.
Deterministic prose linter for LLM text — flags AI slop, filler, buzzwords, hedges, clichés.
Open eval leaderboard + CI gate for autonomous coding agents (solve, score, trace).
MCP server for context-aware royalty-free image search from Pexels and Unsplash
Play 1v1 arcade games vs AI agents & humans, ranked by ELO.
Request qualified humans for real-time cognitive micro-tasks on demand.
Check, compile, run, and test Sounio programs locally.
Structured Windows state for AI agents: processes, windows, UI trees.
Trust layer for AI agents: identity, guard, redact, escrow, and x402 payments.
MCP server for working with OASF agent records in the Agntcy Directory.
Private agent payments on Solana via ZK proofs: deposit, withdraw, list pools, estimate fees.
MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log.
Inspect AgentMark traces and drive AgentMark Cloud: apps, experiments, metrics, deployments.
Cross-agent memory over MCP: hybrid recall, knowledge graph, private/shared visibility, redaction.
Tamper-evident, SHA-256 hash-chained audit trail and observability for AI agents.
Human-in-the-loop approval gateway for AI agents over MCP: request, decide, approve.
Crypto market intelligence, evidence, watchlists, feedback, and paid x402 SKU routing.
Real email and SMS for AI agents — send mail, receive verification codes, drive a real inbox.
Check text for leaked credentials before an agent writes or commits it.
Develop firmware on the real board behind a debug probe: flash, reset, UART and CAN, policy-gated.
Safe, read-only database access for AI agents.
Jira & Confluence for AI agents.
Расскажите, какой сервис вам нужен, или добавьте свой MCP-сервер: проверим и опубликуем в каталоге.
Предложить коннектор