A commerce-centric demo featuring Agent Development Kit with Paypal Agent Toolkit via MCPs

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

RollingGo-Flight-MCP is a native MCP plugin for global air ticketing services. Powered by the world’s 3rd largest travel B2B firm. Totally free with no call quota limits. Fully compatible with AI Agents including Claude, Cursor, Codex and mainstream MCP clients. It aggregates 500 airlines, covering flight routes across 200 countries and regions.

Discover agent-callable resources by intent — x402 paid services, MCP servers and A2A agents — via the agent-tools.cloud directory. 9 tools: search/get/list_categories (x402), search_mcp_servers/get_mcp_server, search_agents/get_agent, search_all, stats.

Create a QR code for Ukrainian domestic payments at a point of sale or online and accept cashless payments to IBAN

Pre-install trust scoring & safety scanning for MCP servers, AI skills & npm packages — 15 signals incl. OSV/KEV/EPSS vuln intel and an auto-gate go/no-go.

Static technical-debt analysis across 14 languages, exposed as MCP tools and resources

An open-source MCP server that makes government pet-food and veterinary-drug recall data queryable by AI assistants. Search and filter active recalls, fuzzy-match a specific product, and subscribe to email alerts — sourced daily from the Government of Canada (CFIA) and the US FDA (OpenFDA). Zero config: just npx.

A Model Context Protocol server bridging LLM agents to the Prolific public API. Built with FastMCP. Listed on the official MCP Registry — discoverable from Claude Desktop, Cursor, Claude Code, and other MCP-aware clients. Exposes a small set of tools so an LLM can help a researcher design and launch a study on Prolific.

Globestudio is an open-source, designer-first tool for creating dotted maps and animated 3D globes. Choose any region from a single country to the whole world, customize dot shapes and colors, layer on shader effects, and export to PNG, SVG, or animated WebM. Built on React and Three.js, it runs entirely client-side and can be embedded anywhere with a one-line script tag or iframe.

toflow.ai is an AI-native outreach platform for B2B sales teams. Find leads, enrich contacts, and run campaigns across email, LinkedIn, and WhatsApp by chatting with AI. Connect to Claude or ChatGPT via MCP and your AI assistant handles the entire outreach workflow. Prospecting: Search LinkedIn with classic and Sales Navigator-style filters. toflow builds your list instantly. Enrichment: Verify emails, find phone numbers, and pull LinkedIn data through waterfall enrichment across 8+ premium sources. Sequences: Launch multichannel sequences across email, LinkedIn, and WhatsApp from one workflow. Automates connection requests, messages, InMails, and follow-ups. AI Agents: Autonomous agents handle prospecting, follow-ups, and inbox management. Hot leads routed to reps automatically. Unified Inbox: All replies from every channel in one place. CRM: Connects to Salesforce and HubSpot. Every action syncs back automatically. Trusted by 100+ sales teams.

虎嗅嗅官方AI助手，可查询AI行业早报、投融资事件、产品动态、硬件与原生关键信号。

Race nutrition planning tools for endurance athletes. Get personalised carb, sodium and fluid targets for any race, browse Lecka's real-food product catalog, and calculate exactly how many gels you need — by distance, conditions, weight, and effort level.

Web content fetching and conversion for efficient LLM usage

An MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.

Gives your AI agent your story map and given/when/then acceptance criteria. Read-only.

The Meteomatics MCP (Model Context Protocol) server allows AI agents to securely access Meteomatics weather data tools. MCP is an open standard that lets AI applications connect to external tools and data sources. With the Meteomatics MCP, agents can request weather data directly from the Meteomatics API through a secure /mcp endpoint. The MCP server manages authentication using OAuth (client registration, authorization code + PKCE, and refresh tokens). Once connected, the AI agent can access data, models, parameters, time ranges that are available to your Meteomatics API account.

基于Anduin2017 / HowToCook （程序员在家做饭指南）的mcp server，帮你推荐菜谱、规划膳食，解决“今天吃什么“的世纪难题； Based on Anduin2017/HowToCook (Programmer's Guide to Cooking at Home), MCP Server helps you recommend recipes, plan meals, and solve the century old problem of "what to eat today"

Recruiting-ops MCP for asking Recruitee questions and finding bottleneck owners inside Claude, Cursor, or another AI workspace.

Retrieving and analyzing issues from Sentry.io

Recruiting-ops MCP for asking Teamtailor questions and finding bottleneck owners inside Claude, Cursor, or another AI workspace.

A Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.

A Model Context Protocol server that provides access to Redis databases. This server enables LLMs to interact with Redis key-value stores through a set of standardized tools.

Turn any published podcast into clean Markdown with real speaker names — not "Speaker 1." Three tools: search_podcasts (by text query or a pasted Spotify/YouTube URL), get_transcript (named, timestamped Markdown ready for LLMs and RAG), and get_balance. It's a transcript-retrieval API, not speech-to-text: it works on already-published shows, so you skip uploading audio and diarization — typically 5–10× cheaper. Try it free with the demo key pt_demo (no signup).

Commerce infrastructure for AI agents — 43 MCP tools to search, compare, and purchase across 36 verified retailers in 8 countries. 45,000+ real shelf prices refreshed every 4h. MIT.