Top Hyperliquid trader positions — long/short, size, PnL, leverage, sentiment. x402.
MCP servers
Compare source listings, connection options and authentication requirements.
Showing 27,961–27,984 of 165,917 resultsPage 1166 of 6,914
Candidate groups, not verified unique MCPs. How grouping works
Local-first long-term memory for AI coding agents. Stored on your own machine.
Liquidation radar, execution context and Li.Fi swaps for AI agents. 6 MCP tools; x402 payments.
Liquidation radar, execution context and Li.Fi swaps for AI agents. 6 MCP tools; x402 payments.
Create and edit AI videos from chat: plan shots, generate scenes, and export stories and ads.
Live prices, perps, prediction markets and a paper trading desk over one MCP.
Start cited deep-research runs, read reports, search your source vault, and verify citations.
Every web search provider has gaps. Each one indexes different pages, misses different sources, and none of them reach the structured data behind most real questions. Hyperresearch Answers layers four web search engines with about 45 structured sources, including company filings, government statistics, public registers, scholarly indexes and books. Your agent gets one search tool with the gaps filled in. It searches wide, and goes deep when a question needs it. Every answer is checked word for word against quotes from the pages it cites. If the sources don't back it up, it says "not found" instead of guessing. Your agent gets the answer and its proof, not whole web pages, so its context stays free for the actual work. Three tools: - ask: one question, one verified answer with its quotes and links. Most answers arrive within a minute; a hard question returns an id instead. - get_answer: collects an answer that is still being worked on, by its id. - search: ranked sources with only the relevant passages, for when your agent should read the evidence itself. Use it when a question needs better data than a web search, when a hallucinated number would cost you, and when you don't want search results eating your agent's context. Each call is paid from the prepaid credit in your Hyperresearch account, and every result shows what it cost and the balance left. Sign in with your Hyperresearch account when you connect. Setup guide: https://hyperresearch.ai/answers
Hyperscale Product reads and contract operations over MCP.
HyperSkill MCP enables you to create, edit, and manage HyperSkill simulations. Use it to build new simulations, modify existing ones, and iterate on simulation content and configuration directly through MCP.
Hypersonix ProfitGPT Retail Analytics connects Claude to your company's retail data in Hypersonix. You can ask business questions in plain English, such as "How did we do last week?", "Which categories lost margin this month?" or "What will run out of stock next week?". Claude works out the answer from your own sales, cost, price, inventory, order and forecast data. What you can do: - Review weekly performance. See revenue, profit, margin, units, transactions and average order value for the latest complete week, compared with the week before and the same week last year. - Act on pricing alerts. See the alerts from the Hypersonix price optimisation, such as competitor price gaps, weak margins, cost changes, MAP compliance and demand drops, with the revenue and items at stake. - Ask your own questions. Get top sellers, sales by store or category, price history, margin by brand, cancelled orders, slow movers, stock cover and forecasts. Accurate by design: retail data has traps that produce numbers that look right but are wrong. Examples are counting cancelled orders as revenue, adding up stock across snapshot dates, or joins that multiply sales by the number of stores. The connector gives Claude documented business rules that were measured against real data. It checks every query against those rules and flags likely mistakes before a number reaches you. Claude also tells you what the data cannot support, such as an empty field or a breakdown that is not available. Secure: you sign in with your existing Hypersonix account, and you only ever see your own company's data. The connector reads your data and never changes it. Requires a Hypersonix account with access to ProfitGPT.
Search and inspect 6,500+ curated AI apps from the HyperStore directory.
Search and inspect 6,500+ curated AI apps from the HyperStore directory.
Search and inspect 6,500+ curated AI apps from the HyperStore directory.
Search and inspect 6,500+ curated AI apps from the HyperStore directory.
Publish complete HTML artifacts and return a public share URL.
Evaluate and inspect your Hypertune feature flags from your AI assistant.
X feedback discovery, noise-reduced query planning, signal filtering, and AI handoffs.
Personalized hypnosis sessions and multi-day journeys, a free session library, and audio rendering.
Pharmacovigilance hypothesis generation from 15 public drug safety databases
Hypothèques en ligne aide particuliers et professionnels à obtenir les documents fonciers officiels d'un bien immobilier en France: état hypothécaire, copie d'acte notarié, règlement de copropriété, état descriptif de division, pré-état daté, situation de patrimoine immobilier et packs. Ce connecteur répond, depuis Claude, aux questions de prix et d'orientation: - combien coûte un document, au tarif public et pour chaque niveau d'abonnement; - le devis d'un état hypothécaire selon le type de recherche (par parcelles, par lots de copropriété, par personnes) et le nombre d'éléments; - le prix d'une situation de patrimoine immobilier selon la zone couverte (département, région ou France entière); - la grille des abonnements professionnels; - la page de service adaptée à une profession (avocat, syndic, banque, agence immobilière, commissaire de justice, géomètre-expert, assureur…) et le lien du formulaire de commande. Le connecteur est en lecture seule: il ne passe aucune commande, n'effectue aucun paiement et ne demande aucune donnée personnelle. Aucun compte n'est nécessaire. La commande et le paiement se font sur le site hypotheques-en-ligne.fr. Hypothèques en ligne est une marque d'Encelade Conseil (SIREN 532 957 461, Montpellier), en activité depuis 2018.
Hypotize is the agent-native Growth OS for growth, product and marketing teams. It holds the whole growth loop in one place: the idea backlog, prioritization, the experiment pipeline, results and the library of learnings. Your team works in the web app. Claude works on the same record through this connector. With Hypotize connected, Claude reads what the team already tested before proposing anything new. It turns raw ideas into hypothesis-first experiments, scores them with ICE, PIE, RICE or your own framework, writes the action plan and moves each experiment through its stages: Idea, Approved, Ready, Running, Analyzing, then a measured outcome. When a test ends, Claude records the result and the learning, so the next conversation starts from what you already know. Built for teams. Teammates vote on ideas and comment on experiments, and Claude can do both for you. Each product or market lives in its own project. The server enforces the method. An experiment cannot skip a stage or close without a result and a learning, whether a person or Claude is writing. Claude acts with your role in each project. Delete access stays off unless you grant it when connecting, and Claude never touches billing or members. Things to ask Claude: - "What have we already tried on checkout?" - "Turn this spreadsheet backlog into scored experiments." - "Run the weekly review: which tests are waiting for a verdict or overdue?" - "Close the pricing page test with the result and what we learned." Getting started: sign in with Google or email when you connect. The Free plan includes one project and needs no card. Hypotize does not assign traffic or run A/B tests. Keep your analytics and experimentation tools. Hypotize keeps the record before and after.
Hyprland/Wayland computer-use MCP: grim screenshots + uinput click/type + hyprctl targeting
Computer use for Hyprland: semantic desktop state over IPC, plus vision and native input
What this catalog covers
- Source listings
- 167,897
- Candidate groups
- 168,273
- Setup-eligible endpoints
- 30,743
Sources observed 2026-10-24–2026-11-12. Listings can overlap across sources. Groups are identity candidates; setup eligibility is not a successful connection test.
SourcesMCP data from Glama connectorsMCP data from Glama source codeOfficial MCP RegistryClaude connector directoryAPI Tracker · publisher documentationSlack MCP directory
Default browsing excludes 2,356 specialized utility groups across the catalog. They remain available through keyword search and direct links. This editorial filter does not change the indexed totals or establish publisher quality.
Categories currently cover records matched to our reviewed catalog; other listings remain Uncategorized. Source-only projects have no generated connection option. Browse reviewed official MCPs →
- Glama connectors
API result set; pagination may cap at approximately 1,000 connectors. Not exhaustive.
- Glama source code
Complete chronological source-code catalog response; includes source-reported author classifications, not publisher attestations or ready-to-use endpoints.
- Official MCP Registry
Complete paginated registry response; registry membership is not publisher verification.
- Claude connector directory
Complete public Claude directory MCP components. Source tiers, tools, icons and sign-in hints are declarations, not publisher or runtime verification.
- API Tracker · publisher documentation
Reviewed publisher and third-party remote, local and setup-only MCP listings. Publisher status is retained per exact connection. Discoverability does not establish connection readiness.
- Slack MCP directory
Reviewed additions discovered through the public Slack Marketplace MCP category. Complete discovery inventory is retained separately; membership does not prove external-client compatibility.
Listings are grouped by exact public endpoints, exact package sets, or explicit reviewed identity bindings. Shared names or repositories alone do not merge implementations. Official includes publisher evidence and accepted source author classifications. It does not mean independently verified, runtime-tested or security-certified.