"A system or program using SSE instead of STDIO" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Solana trading and filtered live data for AI agents. Build swaps via Jupiter, sign locally, submit through PumpView, and read confirmed receipts and per-key volume. SOL/WSOL or USDC on one side. No trading subscription; 0.5% swap fee plus tips (min 0.002 SOL) and network costs. Bearer API key from a PumpView account or wallet-signature onboarding. Public discovery; paid live data. Agent Kit and skill: https://github.com/grinchdev/pumpview-agent-kits
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.
A decision model for the calls that don't have a right answer. The better option, with a reason.
Auto-Apply That Ends on an Interview. Job matches, applications sent on the employer's own hiring system, employer-receipt tracking, per-role resumes, cover letters, interview prep.
arifOS — a constitutional kernel for AI agents. 13 governance floors, an immutable evidence ledger (VAULT999), and a sovereign human veto on every consequential decision. Forged, not given.
AI agent monitoring: alerts when your agents fail, stall or need you
Contract-change authorization for AI agents: preflight a change to an API or MCP contract, get a signed decision, and verify the receipt offline. Only a granted change can proceed.
Block an action a signed mandate does not permit: amount, payee, audience, currency, window, intent.
Block an action that a signed mandate does not permit, at the moment the action happens. Checks amount, payee, audience, currency, window and intent in fixed order; 100 checks a day free, then 0.005 USDC per call over x402 on Base mainnet.
Signed, append-only receipts of an AI agent's decisions and outcomes, with public proof links.
A real Android phone in the cloud for MCP agents: observe the screen, act, reset to a saved state.
Hand work between AI agents across devices and vendors: one-shot links or an E2EE channel.
Check an agent's INAM reputation before trusting it, and sign a receipt when work is done.
An independent second opinion for your agent: decision engines that test an AI business case, venture or forecast against the evidence and return what is proven, what is assumed, and a fund / pilot / stop or proceed / rework / stop decision. Fixed, published rules give repeatable results. Free: Startup Soundcheck, Business Soundcheck and evaluate_fit. Paid engines use an API key; agents can create a purchase link and the owner always approves payment.
ai-mail.sh gives your AI agent its own email address for $0.05, paid with x402 (USDC on Base), with no signup. Verification codes and links come back already extracted, and wait holds the request until mail arrives. Addresses are never reassigned: come back months later, pay again, same address. Receive-only, no tracking, and you delete it, it's gone. Works over HTTP or MCP.
Autonomous AI workforce of 37 specialist departments delivering finished, Director-reviewed business deliverables with Proof Before Pay. Powered by prepaid agent wallets.
Assign Linear, Jira or GitHub issues to an AI coding agent team that plans, builds, reviews, tests.
KYA backed by a real company: e-CNPJ-signed agent mandates, revocation-checked, signed verdicts
Your own AI agent on an always-on cloud computer: Claude Code, Codex and more, or managed OpenClaw.
Shared long-term memory for AI agents: save and recall context as a searchable knowledge graph.
