Let AI agents accept payments in the Netherlands (EUR) — iDEAL (the Dutch standard), cards, Apple Pay, bank transfer — via Mollie. Stateless, bring-your-own credentials (x-mollie-api-key), never holds funds. Owner policy guardrails: x-agentpay-max-amount / x-agentpay-approval-above.
63-layer continuous-time Symplectic Neural ODE computing topological invariants of real market signals. 256-dim feature space with non-Abelian gauge field geometry. 27 data products with autonomous Stripe purchase — AI agents can discover, evaluate, and buy autonomously. Property intelligence, DAG manifold computation, federal contracts, distressed real estate. 500K out-of-pocket validated embeddings. Statistical proof: +35.8σ symplectic norm.
In zero-click / agent-mediated commerce, the scarce inventory isn't a human's eyeballs — it's the AI agent's own context and recommendation path. MoltAd lets advertisers promote coupons, discounts, SKUs, and offers directly into the agent that's deciding on a person's or company's behalf, so it can prefer, rank, or apply the promo while it works. That's CPR (Cost Per Recommendation), CPIA (Cost Per Agent Impression), CPPromo (agent coupon/promo unit), and CPD (Cost Per Decisi
Personal Knowledge Base MCP — 26 tools that let AI agents search and read a user's curated reading, triage reading stages, organize collections, and write analysis back. Hosted Streamable HTTP and local npx install.
Execute Parallel.ai Tasks in Parallel for extremely powerful data enrichment from the web
Agent-native task management: your AI agent is the interface. Create, prioritize and snooze tasks in conversation, delegate to workspace members or to any email address (guests get an email link, no account needed), and answer status questions from each task's complete, immutable history.
Task management your AI agents can actually run. Write one line and Dazbench fills in the purpose, background, and acceptance criteria, then agents like Claude Code, Codex, and Cursor pick up the work over MCP. Connect with OAuth — no API keys to manage.
Work data synthesizer and project tracking platform seeking to close the gap between work and the people who care about it - giving every audience, from craftsman to business layer, a complete view without information losing nuance across boundaries. It shapes itself to how people already work through modular augments, deep natural language processing for automated distillation of information, automated workflows, and adaptive interfaces, rather than imposing process.
PAPI gives your AI coding assistant a persistent plan → build → review cycle that survives across sessions. It breaks work into cycles, hands your agent structured build instructions, records what actually shipped, and carries project context forward so nothing gets lost between conversations. **What it does** - Plans your work into cycles with effort estimates and build handoffs - Tracks build execution task by task - Runs a review and release flow, all persisted in one pla
Enable natural language task and project management by integrating your Todoist account with an LLM via MCP tools. Create, update, organize, and search tasks, projects, labels, and sections effortlessly using everyday language. Optimize your workflow with batch operations and flexible filtering designed for AI interaction.
Query time entries, projects, tasks, and team productivity data from any AI assistant.
Enable your LLM to interact seamlessly with Todoist by connecting to this server. Manage tasks, projects, and more using the full Todoist API through natural language commands. Simplify productivity workflows by integrating Todoist capabilities directly into your AI assistant.
Turn any AI assistant into an expert prompt engineer. Ultra Prompt gives your AI a library of **1,000+ professionally written prompts** for real, everyday work, writing, marketing, business, creative, coding, and more. Just describe what you're trying to do, and it finds the right template, fills in the details, and hands back a polished, ready-to-run prompt, expert-quality results without wasting time writing the best prompt yourself. It can also chain templates into multi-
The x402 A2A Hub is the single discovery point for a growing pipeline of paid AI microservices running on Base mainnet via x402 v2 micropayments. Call get_capabilities to retrieve a structured manifest of every available service — including endpoint URLs, supported input/output formats, per-call pricing ($0.005 USDC), and free trial endpoints. Current services: Data Formatter (converts CSV, XML, and Markdown to JSON or HTML) and JSON Schema Checker (validates payloads against
Integrate your AI assistants with Todoist for seamless task management. Manage tasks, projects, comments, and labels using natural language commands. Enhance your productivity by interacting with Todoist through conversational AI.
Stand up an operation from your coding agent: a fleet of agents, each on its own model and connected account, running on a schedule after your session ends. https://sprawl.to
# Dial — Phone numbers for AI agents Dial gives your agent a real phone number. Over a single OAuth-authenticated connection it can **send and receive SMS**, **place AI-handled voice calls**, **provision numbers**, and **wait for inbound events** like one-time codes — no Twilio account, API keys, or telephony glue required. Connect once via OAuth (browser sign-in, no API key to paste), and the agent gets an account scoped to you. Outbound calls run asynchronously: place the
Search the world's wire-harness and cable-assembly manufacturers, and cross-reference component part numbers — built for sourcing, procurement and engineering agents. **Two tools** - `find_manufacturer` — filter **513 manufacturers** across **715 plants** in **65 countries** by country, industry served, process capability (crimping, ultrasonic welding, overmolding, HV, IPC/WHMA-A-620) or name. - `find_alternative` — cross-reference a connector, terminal, seal or cable-p
**MCP server for 16 crypto exchanges + MetaTrader 5.** Crypto and MT5 in one MCP connection: read balances, open and close positions, move stop-loss / take-profit, and audit every action — from Claude, ChatGPT, Cursor, Claude Code, Gemini CLI or any MCP-capable client. **Safety is enforced on the server, outside the model's reach:** - **Paper by default.** Every new key starts on a $5,000 paper balance. Live trading requires a separate, 2FA-protected approval. - **Risk rule
Let AI agents place real phone calls from your SMS-verified number, with transcripts, recordings, and structured outcomes. US & Canada. Free during pilot.
Shared workspace your AI agents write to. CMMN case management with 184 MCP tools: create cases, drive event-driven workflows with sentries, persistent memory with semantic search, billing and invoicing. Connect via OAuth (no token needed) or API token.
DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
Trade It is an MCP server for brokerage-aware investing workflows. It lets AI assistants search stocks and crypto, list and link supported brokerage accounts, inspect holdings and recent trades, create draft stock, ETF, crypto, and options orders, and execute live trades only after explicit user approval. Trade It supports Robinhood, ETrade, Charles Schwab, Webull, Public, Tastytrade, Coinbase, and Kraken, and authenticates with OAuth or user-created API keys.
One-call sold-price statistics (median, quartiles, bid stats) from Yahoo! Auctions Japan closed listings. Runs on Apify, pay-per-event from $0.02/call — connect with your own Apify API token.
Let AI agents ship parcels in India — create Shiprocket orders, check courier serviceability across 17+ couriers, track shipments. Stateless remote MCP server: bring your own Shiprocket credentials, it never holds funds or stores data.
Kilotest leverages 10 rule engines to test web pages for front-end quality (accessibility, usability, and standards conformity) and report results with specifiable granularity.
Manage test suites, run tests, view results, and automate QA workflows via AI with testRigor.
Great Question is the Agentic UX research platform for product builders. Run interviews, surveys, and prototype tests — and keep every insight in a single, AI-powered repository. Once connected, Claude, ChatGPT, Cursor, Windsurf, Gemini CLI, or any other MCP client can: - Create studies — interview studies, surveys, and prototype tests directly from a prompt - Schedule and incentivize — set up screeners, scheduling, and incentives without leaving the conversation - Find the
Verify whether a public source supports a specific factual claim before an agent relies on it.
Enforce disciplined AI-assisted programming workflows by requiring systematic auditing, analysis, and verified outputs at each development phase. Guide AI through structured phases like refactoring, feature development, and testing to ensure thorough understanding and quality results. Prevent skipping steps and maintain session state to uphold workflow integrity. ## Manual Installation ### Clone the repository - git clone https://github.com/kingdomseed/structured-workflow-mc
Check whether a real-world fact can be verified before an agent acts on it. **What it does:** business-exists claims are answered on the spot with a dated evidence bundle from public registries (GLEIF LEI records, SEC EDGAR filings, Wikidata, website liveness). Results report observed evidence with sources and an honest confidence — never a bare verdict. - **Free, no auth, no account.** All tools are read-only with no side effects — safe to call speculatively during plannin
Ask real humans what they think. User Intuition runs AI-moderated voice, chat and video interviews with a 4M+ opt-in panel across 58 countries, then returns analyzed findings — not raw transcripts. This hosted endpoint exposes the Human Signal flow: launch a study, check on it, and pull results. Study design, participant management and reporting live in the full research surface, available over stdio via `npx -y @userintuition-ai/mcp`. Docs: https://docs.userintuition.ai/mc
Let AI agents ship parcels in Italy — buy Poste Italiane Delivery Business Express labels via Shippo's master account (no carrier contract needed), track and refund unused labels. Stateless remote MCP server: bring your own Shippo token, it never holds funds or stores data.
Portfolio & trading-strategy stress diagnostics for AI agents — multi-asset stress with hedge-break detection (the 2022 stock-bond case), a daily-refreshed preregistered regime outlook, deflated-Sharpe backtest-integrity checks and IPS gating. Free tier, no key required. Descriptive, never advisory. Docs: https://crashtestyourstrategy.com/interop
Empower your LLMs with time awareness capabilities. Access current time, convert between timezones, and get timestamps effortlessly. Enhance your applications with precise time-related functionalities. usage: `npx time-mcp`
LoopGolf's free public MCP server gives AI assistants live, bookable golf tee times across US courses. Two read-only tools: search_tee_times (availability near a city or zip, filterable by date, players, time of day, price, and holes) and get_course_tee_times (every open time at a specific course with availability by date). No API key required.