"Information about CAD (Computer-Aided Design or related topics)" matching MCP connectors:

Pre-transaction token risk checks for autonomous agents. Read-only; never signs or moves funds. Paid per call in USDC via x402. Supporting Base, Solana, Ethereum, Arbitrum, BSC and HyperEVM

Evidence-gated task verification for AI agents. Decompose goals into acceptance criteria, attach proof (screenshot, curl, file), independent LLM judge accepts or rejects. 24 tools. Hosted remote MCP (streamable-http, OAuth 2.1 + DCR).

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.

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.

Public agentic AI doctrine tools plus authenticated architecture, design, and spec validators.

Run and manage H Company's Computer-Use Agents from any MCP client.

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

Turns a phone into a camera+Bluetooth remote so AI assistants can see and control any computer. No install on the target machine — 12 tools for screenshots, click, type, scroll, key press, and monitor-corner calibration.

Is this AI agent or x402 service real and settlement-backed before you pay it? Trust check.

Give your AI agent a phone. Place outbound calls to US businesses to ask, book, or confirm.

Competitive intelligence for autonomous AI agents. Analyze any URL or company and get structured JSON with market positioning, competitors, pain points, battlecard, and executable Market Score. 10 context modes: regulatory_compliance, venture_screening, crypto_protocol, sales_enablement, and more. Pay-per-call via x402 on Base and Solana.

Marketplace where AI agents ask AI agents that have live or proprietary data.

The industry standard reference for safe, observable, and steerable AI agent UX. Browse and search the 10 Blueprint principles, principle clusters, curated implementation examples, and application guides. 13 public tools require no credentials. Tools for learning path, coaching context, and handoffs require a Firebase Bearer token. Validation and usage summary tools require a Pro or Teams membership.

Native Solana staking infrastructure for AI agents. 18 MCP tools for complete staking workflows — stake, unstake, withdraw, verify transactions, check balances, simulate projections, and more. Zero custody design: returns unsigned transactions for client-side signing. ~6% APY via Blueprint's enterprise bare-metal validator with Jito MEV. Built by Blueprint (Hivemind Capital Partners).

An MCP server for deep research or task groups

PhoboMail gives AI agents their own @phobomail.com email address with zero human involvement. Agents call `register_email` to get an address and API key, then use `send_email`, `read_inbox`, `wait_for_email` and more — all over MCP. Ideal for agent workflows that need to sign up for services, handle OTP verification, or communicate across sessions. Hosted on Cloudflare.

Build and manage AI-native customer support agents from Claude or any MCP client.

Chat Thing is the fastest way to build AI-native customer support. This official MCP server lets you create and run support agents straight from Claude or any MCP client. Point it at your website or docs and it builds an agent grounded in your real content, adds human hand-off and custom actions, and lets you test answers before they reach a customer. No dashboard required.

fomox402 is a last-bidder-wins on-chain game on Solana, designed to be played autonomously by AI agents. Every bid mints a key that earns passive $fomox402 dividends; the last bidder when the timer hits zero wins the pot. Drop our MCP server into Claude Desktop, Cursor, Goose, or any HTTP-speaking client to play.

Liminality takes a hard question, a decision, or a multi-step task and breaks it into its real sub-questions, ties each to a real tool or source, and returns a worked, reusable result: a scored decision frame for a choice, or a grounded synthesized answer. It is built for hard, multi-step, and decision work rather than quick lookups, and its shared library of solved routes makes repeat work cheaper.