High-performance M2M context middleware and x402 micropayment engine for AI Agents and MCP tools on Base. ContextSlim prunes massive JSON payloads by up to 85%, enforces strict token budgets, and handles autonomous HTTP 402 EIP-712 micropayments—keeping agent execution fast, cost-effective, and deterministically within LLM context limits.
Paid handoff desk for AI agents. File sealed research free and earn 90% USDC on Base when buyers unlock with x402. Discover existing work instead of re-burning tokens. Read /api/earnings for on-chain filer proof. MCP tools are HTTP pointers — filing and unlock need user consent and X-AGENT-ID.
Catalog of gift cards, service top-ups and travel eSIMs sold by BlinkCodes, with purchase over x402 (USDC on Base).
Official MCP server for OmniDimension. Drive voice agents, dispatch calls, and run bulk campaigns.
Tischanruf turns a natural-language request into a real phone reservation. Say "book a table for four at Luigi tomorrow at 7," and an AI voice agent calls the restaurant in German, handles counter-offers and special requests, and reports back whether the table was confirmed. Built for phone-only German restaurants - no restaurant sign-up required.
Let AI agents highlight and annotate any webpage — end-to-end encrypted, no accounts needed. **Tools:** - `annotate_page` — highlight or comment on text at any URL - `get_annotations` — retrieve all annotations on a page - `share_page` — generate a shareable link (anyone views annotations live on the original page) - `remove_annotation` — delete an annotation by ID **Privacy:** Annotations are AES-256-GCM encrypted client-side. The key lives in the URL fragment — the server
RightCard tells an AI agent which of a person's credit cards to use at any store or category, from bank-published, two-source-verified reward data. Honest caveats built in: superstores and warehouse clubs where grocery bonuses don't post, rotating 5% quarters with activation flags, points valued per program. No bank login, no account, nothing stored.
toui is the short-link service embedded in your AI workflow. Connect its remote MCP server once — OAuth, no API key — then shorten links, group them into campaigns, and pull click stats for your AI to analyze, right from your chat in Claude, ChatGPT, Cursor, Cline, or any MCP-capable agent. Links are permanent; custom branded domains and deeper analytics live in your toui.io account.
MascotLab gives an app one character and keeps it that way. Describe a mascot once and it is locked. Every pose, prop and animation you generate afterwards is rendered against that locked reference rather than from the description again, so the character on your empty state and the character on your error page are recognisably the same one. That is the difference from a general image tool, which redraws a new character every call. Ask in plain language and the agent picks t
Secure email infrastructure for AI agents. Every inbound message is verified, sanitized, and screened for prompt injection before your agent reads it — hidden HTML, zero-width characters, and decode-then-apply payloads are stripped or fail closed — then delivered as typed JSON. Outbound send is idempotent, with optional human approval on consequential replies.
# CoinEx MCP Server A Model Context Protocol (MCP) server that enables AI agents to interact seamlessly with the CoinEx cryptocurrency exchange. This server provides comprehensive access to market data, trading operations, and account management through a standardized MCP interface. ## Key Features - **Market Data Access**: Retrieve real-time tickers, order books, K-lines, and recent trades for both spot and futures markets - **Futures Analytics**: Access funding rates, pr
Elicitly puts a human in the loop of any MCP-connected agent. The free stdio server (`npx -y elicitly`) provides `elicit_confirm`, `elicit_form`, and `elicit_doctor` — native host dialogs plus a capability diagnostic. The hosted Pro Edition adds durable approvals: requests that survive disconnects, reach any device via a review page, and leave an audit trail.
Evidence-backed web research for AI agents with citations and confidence scores.
Japanese prompt injection detection and x402 pre-payment security check API. Deterministic validator included. No AI used for core validation.
Evidence-backed web research for AI agents with citations and confidence scores.
AI-native payment infrastructure that gives AI agents isolated wallets with programmable spending policies for autonomous USDC stablecoin transactions. **11 MCP tools** for Claude Desktop, Cursor, and Windsurf: - check_balance, send_payment, list_transactions, agent_info - create_invoice, pay_invoice, check_invoice_status, list_invoices - call_x402_endpoint, call_mpp_endpoint, plus more **Tri-rail support:** x402 (HTTP-native micropayments), MPP (session-based streaming), a
Create a free sandbox object storage bucket; upload, download, list, inspect, and delete objects.
Agentic escrow payments for AI agents. Create, fund, and release escrow payments across fiat (MXN/USD via SPEI/wire) and crypto (USDC/USDT/MXNB on Arbitrum, Base, Polygon, Solana). **36 tools** covering: - 🏦 **Fiat escrows** — SPEI/wire deposits, KYC-gated release, dispute resolution - ⛓️ **Web3 escrows** — on-chain ERC-20 escrows with relayer, 7 supported chains - 🔐 **Confidential escrows** — FHE-encrypted amounts (Fhenix CoFHE) - 🔁 **Recurring payments** — subscription bil
On-chain Solana token safety for AI trading agents. Screens any SPL / Token-2022 token for rugs, honeypots, active mint/freeze authority and dangerous extensions (permanent delegate, transfer hook) by reading the chain directly, then builds the buy as an unsigned, screened Jupiter swap the agent signs. 15 tools, remote — no install.
Persistent memory, teams, and projects for AI agents. Store and recall knowledge across sessionswith 4-st rategy hybrid search — alias matching, full-text BM25, tag intersection, and vector cosine similarity. Private brains per agent, read-only team sharing, and scoped project collaboration. Works with Claude, Cursor, OpenClaw, and any MCP-compatible client. Free tier available.
Connect AI agents to your ZERNO product backlog over a secure remote MCP endpoint. Read project briefs, list and open tasks, retrieve compiled project memory, patch task status, submit triage proposals, and file agent-intake tasks. OAuth 2.1 (PKCE), per-project authorization. 8 tools, no resources or prompts.
InvoiceXML brings e-invoice compliance to your AI agent. Create, validate, convert, render, and extract structured invoices across UBL (Peppol BIS Billing 3.0, used worldwide), CII, Factur-X, ZUGFeRD, and XRechnung, all checked against the EN 16931 standard and official Schematron rules. Ask your assistant to generate a compliant invoice, validate one for errors, or convert between formats, with no e-invoicing expertise required.
A library card for your agent ShelfLayer lets your AI search a public-domain book index, inspect shelves, books, and tables of contents, read sections, and return citation-ready passages from Project Gutenberg-sourced works. It is a read-only research app for finding source material across history, philosophy, economics, science, biography, religion, art, and other nonfiction topics.
Plyto is an agentic CRM for small businesses, and this server exposes the whole platform to the AI you already use. Connect Claude, Cursor, or any MCP-compatible assistant with a per-business API key and your agent can create and search contacts and companies, move deals through pipelines, draft emails and campaigns, manage tasks and notes, inspect automations, and run live reports. It all runs on your own AI subscription, with no Plyto AI credits needed. Safe by default: an
Model the realistic monthly cost of an LLM app **before you build it**. Not a token calculator: retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth are modeled in, across GPT-5.x, Claude, Gemini, DeepSeek, and more. **Works without a key.** Connect and ask — demo mode covers the six free-tier models. A Pro API key ([beforeyouship.dev](https://beforeyouship.dev)) unlocks the full 18-model catalog. ## Tools | Tool | What it does | |---|---| - **`estim
Fleet entry point for **Moltline Studio**: 19 hosted MCP servers, 132 tools, 92 of them free. Searches 138 SKILL.md agent skills and routes you to the right server. No account, no API key, no signup on the free tier. Independently audited — [MCPize Verified A](https://mcpize.com/check/results/a4a18019-d08a-446b-a816-656b9751f9fc). Direct endpoint: `https://mcp.moltlinestudio.com/catalog`
AI teammate for tasks: builds your list from meetings, email and chats, and checks off done work. Bubbl turns your meetings, email, and group chats into a task list that maintains itself, nudges the right person at the right time, and marks work done when it actually happens. You can also @mention your own AI agent in a task's thread and it works that task on your machine, on your subscription.
Generate designed, localized App Store screenshot sets from your raw app captures. Your agent runs the whole workflow: create an app, upload source screenshots, generate a set, refine headlines and order, localize into other App Store locales, and download files sized for App Store Connect. **Tools cover the full workflow** - `list_apps`, `create_app`, `request_screenshot_upload` - `generate_screenshot_set`, `get_batch_status`, `regenerate_failed` - `edit_headline`, `reorde
54+ pay-per-use AI & data tools for agents, payable in USDC via x402 on Solana — no API keys, no subscriptions. AI image, video, music and voice generation (cheaper than official APIs), web search, cited research reports, Claude Opus Q&A, crypto prices, page scraping, domain info and more. Pay only for what you call, straight from the agent wallet. Free directory tool lists all live endpoints.
Your curated sources as context for any AI agent. FeedNest is a reader with no algorithm: RSS, YouTube channels, podcasts and Google News in one chronological feed you control. This remote MCP server gives your assistant direct access to that library: ask for a morning briefing from your feeds only, compare how your sources cover a story, search everything you have ever read, or save, tag, highlight and annotate articles from the chat. 26 tools. OAuth 2.1 or API key. Works
24 keyless tools for AI agents on Vector, the Apex Fusion eUTXO L2: wallets, transactions, smart contracts, soulbound agent registry, and improvement-proposal operations. The server only builds unsigned transactions - signing stays with the caller. Hosted on mainnet and testnet, anonymous access with per-IP rate limits. Docs: https://apex-fusion.github.io/vector-ai-documentation/
WhenPeak tells your agent when its human peaks, when to protect the dip, and how ready they are today, so it can schedule work around real capacity instead of treating every hour as equal. Returns the peak window, natural dip, secondary peak, readiness score and chronotype from sleep. Also projects a 7 to 30 day outlook, finds today's best slot for analytical, creative, learning or administrative work, and reports whether right now is a peak or a dip. Built on the Two-Proce
Publish an HTML page to a private, unguessable link straight from your agent — no build step, no Git, and nothing for the person you send it to install or sign up for. Use it whenever a conversation produces something worth looking at: a report, a dashboard, a slide deck, a small interactive tool. Pass the complete self-contained HTML and get a shareable URL back in about ten seconds. Republishing keeps the SAME link, so the URL you already sent someone shows your newest ver
AI agents hallucinate package names. `need` gives them a verified index of 10,000+ CLI tools with a feedback loop that gets smarter with every install. **Three MCP tools:** - `search_tools` — semantic search in plain English ("compress png images") - `install_tool` — install via brew, apt, npm, pip, or cargo (allowlisted only) - `report_tool_usage` — success/failure signals that improve rankings for every future agent **Works with:** Claude Code, Cursor, Claude De
Outsource a task to AI agents on the Frantic bounty board. Agents claim funded work, deliver artifacts in the open, and are paid in USDC on Base only when a delivery is accepted, with every claim, judgment, and payout sealed to a public receipt ledger anyone can verify. This server exposes the board, ledger, receipts, and agent state as read tools; money writes are deliberately excluded from MCP.
CPFHub.io is a Brazilian CPF lookup and validation API built for developers. This MCP server lets AI agents query CPF data — including full name, gender, and date of birth — directly from a conversation, without writing any HTTP code. ## Available tools - **`lookup_cpf`** — Query a Brazilian CPF number. Returns full name, gender, and date of birth. - **`get_quota_info`** — Check your current credit balance and plan details. ## Key specs - ~300ms average response time · 99