"An open-source penetration testing framework" matching MCP connectors:

Open scientific and engineering knowledge for AI agents: search, evidence, document publishing.

Audit agent-distribution surfaces and create an evidence-based distribution plan.

Read-only MCP server for turva.dev, an agent-readiness audit and advisory service.

Canonical vocabulary server for autonomous business design. Exposes the Arco Lexicon as seven MCP tools: term lookup, related terms, alignment verification, citation formatting, source retrieval, term listing, and term suggestion. No authentication required. Streamable HTTP transport.

Autonomous research agent that pays every source it cites in USDC on Arc via x402 micropayments.

Self-destructing secret sharing for AI agents: encrypted burn links for credentials, plus an agent-to-agent dead-drop with exactly-once claim semantics. RAM-only, no database, open source (MIT). Source: https://github.com/mmmpym/flashpaper

Quant tools + an NFL fantasy draft assistant for AI agents — Kalshi & Polymarket EV, edge, ADP.

Reliable async execution for agent tool calls: schema-gate hallucinated payloads before they run, absorb rate limits and outages with retries and circuit breakers, and add idempotency, human approval gates, encrypted credentials, and signed-webhook results. Failed calls return an llm_hint the agent can self-correct from.

Third-party signed reads of how an AI agent behaved: drift, vows, and the town it works in.

A place, not an API: public 0-9 block commons — spark(), agent-to-agent meet, model-free text RPG.

Get a real human to verify, decide, or improve an AI agent's work.

Trust signals for AI agents: an open agent-readiness standard and developer tool guide. Read-only.

Trust infrastructure for AI agents: read a verifiable Trust Rating, claim an identity, earn a badge.

Learn and adopt the Capability Host Protocol — the agentic web's open evidence layer.

Hand off AI work with a signed Verification Receipt — an independent verifier proves it runs.

Read-only tools over the Safer Agentic AI framework: 238 patterns + 14 heuristics.

AI task cockpit: an agent does your tasks and asks before anything irreversible.

Zero-Ops deploy of a private AI workspace to your own VPS — from your AI chat. Free and open-source.

Give an AI agent a body in a Zero 3D voxel world: perceive, move, build, chat, remember.

MCP-native AI browser testing for coding agents. Submit a URL + goal, get back action trail, bugs, screenshots, and WebM video your agent patches from directly. 43 tools, 12 AI evaluation personalities, combo tiers with auto-pause-on-bugs, throwaway email + SMS inboxes.