"OCR agent" matching MCP connectors:

Signed machine messages + wallet trust gates via x402; free verifiable agent passports.

Agent intake desk for property renovation. Read only, CORS open, fail closed, receipts recompute.

AI-agent image generation: cohesive sets & illustrations. PNG/WebP (optional transparency) or JPEG.

Goal decomposition where every "done" is proven by evidence and checked by a judge.

AI infrastructure design agent. Describe your app in plain English; Riley designs, prices, and deploys AWS or GCP infrastructure with generated Terraform.

The PropelAuth Integration MCP Server helps you and your favorite AI agent integrate PropelAuth as quickly and easily as possible into your project. Whether you're integrating PropelAuth into your Next.js project or your FastAPI backend, the Integration MCP Server will ensure your AI agent has the best context possible for a successful integration.

Pay-per-use tool API for AI agents. Free tier, x402 USDC micropayments, or API key.

Search and get install details on MCP servers, right from your agent -- a unified marketplace index.

Shopping MCP for AI agents: search, compare, Amazon buy links. Auto-register.

EU AI Act Art-14 runtime oversight: allow / flag / gate-to-human on an agent action, with receipt.

Bi-temporal memory-as-a-service and paid agent labor. Pay-per-call USDC via x402; signed receipts.

AI agents find, message & book SMBs; pay per call in USDC on Base via x402. 14 tools, compliant.

Socializioz AI agent for creating, approving, scheduling, and managing social media content.

Deterministic, receipted digital microservices. Gate A is simulation-only.

Sovereign Agent OS — Persistent Memory, Governance & Compliance for AI Agents.

Designs, prices, and deploys AWS/GCP cloud infrastructure from plain-English requirements.

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.

Solana transaction diagnosis, simulation, token-risk evidence, and priority fees via x402 USDC.

Reliable async execution for agent tool calls: schema gating, retries, idempotency, audit trail.

Web search, AI agent, and content extraction via You.com APIs