Directory Workspace
Search live directory results
Semantic search. Describe what you're looking for naturally — like you would in Claude or ChatGPT.
Directory
18,203 apps
Claude Marketplace · US · Updated
Claude Marketplace popularity first, then all other apps by Recently added.
Productivity
7Running
By 7Running
7Running is a running coach for road runners preparing a 5K, 10K, half marathon or marathon (7running.coach). This connector links Claude to the runner's own 7Running account. What Claude can do with it: - Read the runner's training paces, current plan and list of plans. - Check a training plan before saving it: kilometres, sessions and minutes per week, with the warnings of the 7Running plan builder (weekly volume up more than 10%, no rest day, too much intensity for the phase, taper not reducing the volume). - Save a new plan as a draft in the runner's account, then edit it. Sessions use the 7Running format: easy runs, long runs, intervals with warm-up, repetitions, recoveries and cool-down, at the runner's own paces. - Activate a draft plan built by hand when the runner asks (7Running Club members). - On a plan generated by the 7Running coach: change, move or turn into a rest day a session in the current, previous or next week, and restore the coach's original session, as the runner can in the 7Running app. Plans saved through Claude appear in the 7Running app and website like plans built by hand, with structured sessions. Plans built by hand are static: the 7Running engine does not adapt them week by week. Requirements: a 7Running account (free sign-up at 7running.coach). Activating a plan requires a 7Running Club membership. Available in English and French. Privacy: Claude only receives what each request needs (paces, plan names and dates, plan and session content). No Garmin or Strava data, completed workouts, heart rate or email address is sent.
Tools: 8
Productivity
a quiet counter
By a quiet counter
a quiet counter is a meal-planning app for a household that cooks. This connector lets Claude work with your own kitchen: what is in your recipe library, what is planned for the week, what is in the freezer, fridge and pantry, and what is on the grocery list. Ask what is for dinner tonight, have Claude add things to the grocery list, put a saved recipe on Thursday, work out who is eating which meal, or see how the week is adding up for protein, fibre and plant variety. The grocery list builds itself from the meals you plan, and the nutrition figures come from the same ingredients, so they match what the app shows. Claude can read your recipes, plan, stock, grocery list and nutrition figures, and add and remove grocery items, schedule and move meals, save and correct recipes, and log what you ate. Before you connect, a quiet counter shows you exactly what Claude will be able to do. You can disconnect any time under Profile, Connected apps in the app, and every change comes with an undo for fifteen minutes. It never receives your email address, password, subscription details or anyone else's data. It does not give health, medical or dietary advice and it does not buy anything. Requires an account with a quiet counter PLUS. Set-up steps: aquietcounter.com/connected-apps
Tools: 29
Sales-And-Marketing
AAA Signal Website Check
By AAA Signal
Ask Claude to check any website for the basics Google needs, like "check plumberlogan.com.au" or "why isn't my business showing on Google?". AAA Signal reads the site's public home page, robots.txt and sitemap and replies with a score out of 100, the most important problems first with a plain-English fix for each, and what is already working. It checks: secure connection (https), phone-friendly setup, whether Google is allowed to show the site, page title and Google description, main heading, sitemap, Google Analytics, tap-to-call and contact options, and business details for Google (schema). Every answer includes a link to the full free report on aaasignal.com.au. No sign-in is needed. It is read-only: it never changes the website, and it cannot see rankings, traffic or anyone's private Google data. Built for small business owners and tradies in Australia, and works for any public website.
Tools: 1
Sales-And-Marketing
Ad Radar
By Ad Radar
Ad Radar is a research board of Meta ads (Facebook and Instagram) from DTC and e-commerce brands. It keeps only ads that are already winning: ads with at least $50k in estimated spend, modeled on engagement from the public Meta Ad Library. Spend is always an estimate, useful for ranking ads against each other, not a competitor's real budget. Every ad is tagged on ten dimensions: hook pattern, hook mechanism, narrative angle, reader awareness, proof level, production format, video type, landing page type, niche and CTA type. Headlines, body copy and video transcripts are searchable. With the connector, Claude can: - Search winning ads by niche, tag, format, days live or a line from the script (search_ads) - Read one ad in full: copy, transcript, tags, days live, variants and links to the original (get_ad) - See which hooks, angles, formats and proof levels reach the top tier more often than the rest of the board, with the number of ads behind each (winning_patterns) - Read the hook and angle mix one brand is running (advertiser_hooks) - Get a brief that maps a winning ad's structure onto the product you describe (get_swipe_prompt) - List the valid tag values, so filters use the exact words (list_taxonomy) Answers come back with the brand, the opening line, the estimated spend and the days live, so you can open the ad and check it. Built for e-commerce owners, media buyers, creative strategists and agencies who ship Meta ads every week. Limits: Meta only (Facebook and Instagram). Ads under $50k in estimated spend are not on the board. All six tools are read-only: they read the Ad Radar board of competitor ads and never connect to your Meta ad account, so nothing in your campaigns can be seen or changed. Requires an active Ad Radar plan (Membership or Agency). You sign in to Ad Radar and approve the connection when you connect: there is no token to copy.
Tools: 6
Productivity
Ad Swipe File
By AdSwipeFile
AdSwipeFile is an ad creative research tool for marketers, founders and creative teams. It connects Claude to a curated library of real ads from brands on Meta (Facebook, Instagram), TikTok and other platforms, filed by brand, niche and format, so you can find examples to study before you brief or write your own ads. Ask for the newest ads in a niche such as beauty, supplements or software, or in a format such as UGC, before and after, testimonial or comparison. List the ads a brand has in the library. Open an ad to read its audiences and, where your account includes it, its copy, then ask Claude to point out the hooks and angles it uses or to draft hooks for your product in the same style. Review the ads you saved on adswipefile.com. Every ad comes with a link to its page on adswipefile.com, where you can see the creative. What it does not do: the library holds no spend, reach or performance data, so it cannot say which ads performed best. It does not cover every brand or every ad and is not a live feed of Meta's or TikTok's ad libraries; it is updated by periodic imports. It cannot run, buy or edit ads, and does not generate images or video. Every tool is read-only. An AdSwipeFile account is required to connect.
Tools: 8
Productivity
Admire
By Admire
Admire accelerates developing leaders and building high-output teams. Define the skills each role needs, observe them in your 1:1s, and track each person's progress to mastery. Connect Admire to AI and do that work in conversation: - Prep a 1:1. Pull a person's priority skills, recent observations, notes, and open commitments. - Capture what you saw. Record observations and notes, and add tasks and commitments with due dates. - Set clear expectations. Draft skills and observable behaviors for a role, or import skillsets from the Skills Vault. - Coach from evidence. See where each person stands against their role and what to work on next. - Follow progress. Read team skill progress, commitments, and dashboards. Admire's guided workflows give AI the steps for assessing a skill, coaching a person, and writing a playbook, grounded in Organizational Behavior Management (OBM). Claude works with your Admire account's permissions. Every change is recorded against your account, and Claude asks before any tool that changes or deletes a record. Drafts write from your data support your judgment; review them before you use them. Requires an Admire account on any plan. Your Admire data is stored in your organization's region, United States or Canada. Select your region when you connect.
Tools: 105
Sales-And-Marketing
Adsby MCP
By Adsby B.V
Adsby connects Claude to the Google Ads, Meta Ads, and Google Analytics accounts already linked to your Adsby workspace, so you can ask performance questions in plain language. Google Ads See which accounts you can access, then look up campaigns, ad groups, ads, keywords, and search terms. Ask for impressions, clicks, CTR, average CPC, cost, conversions, and conversion value, split by date, device, or network. You can also check geographic performance and recent change history. Meta Ads List connected ad accounts and pull insights at account, campaign, ad set, or ad level. Metrics include spend, impressions, reach, clicks, CPC, CPM, CTR, actions, and purchase ROAS. Break results down by age, gender, country, placement, or device, and look up status, objectives, and budgets. Google Analytics List connected properties and report on traffic sources, user acquisition, events, and ecommerce: sessions, engagement, key events, revenue, and which products or channels drove purchases. Access follows your Adsby permissions. Claude reads data from accounts you are allowed to use. Connect Google Ads, Meta, and Google Analytics in Adsby before connecting this server.
Tools: 16
Financial-Services
AdvisorFinder
By AdvisorFinder
AdvisorFinder lets Claude look up U.S. financial advisors and advisory firms in public SEC data. Ask in plain language, such as "Is my advisor registered in Texas?" or "What does this firm charge?", and Claude can: - Search more than 400,000 investment adviser representatives by name, firm, city, or state - Check an advisor's registration, the states where they are registered as an investment adviser, their years in the industry, and their disclosure status - Look up firms: locations, fee arrangements from Form ADV, disciplinary flags, and the number of investment adviser representatives on file - Find advisors on the AdvisorFinder marketplace whom you can contact directly (temporarily unavailable) Every result includes links to SEC IAPD and FINRA BrokerCheck so you can verify it. Disclosure status is one of four plain states. It is never a risk score, and the server does not republish disclosure details. Professional designations are self-reported. Marketplace listings are a labeled business relationship with AdvisorFinder. They never affect ranking and are not an endorsement. Read-only. No account or API key needed. For information and research only; not financial advice.
Tools: 7
Business & Operations
Affil
By Affil.ai
Use ChatGPT to work with the product information, compliance guidelines, and review feedback in your Affil account. Ask about product terms, check a draft against your guidelines, or find out what needs to change in a mockup. You can also check link clicks and conversions over the last 7, 30, or 90 days. Results include links to the relevant records in Affil. The connector can read your data but cannot change it. It only shows information your Affil account can access. Connector access is included for Affil customers. You need an Affil account with affiliate or staff access. Sign in with Affil when you connect.
Tools: 8 · Prompts: 3
Developer-Tools
Agent Ready by Sneeze It
By Sneeze It
Agent Ready scores any public website out of 100 for how well AI agents like Claude can use it, and tells you what to fix first. Ask "is acme.com ready for AI agents?" and Agent Ready scans the site the way an agent meets it. You get the score, a score for each of eight areas, the most important issue in each, and a link to the full report with every finding, the evidence behind it and an ordered fix plan. The eight areas: Reach (can an agent get in, or does bot protection turn it away), Comprehend (can it read what you sell and what it costs), Act (can it book, quote or buy, including WebMCP actions), Complete (does a captcha or login stop it at the last step), Delegate (can a customer's own agent act for them after sign-in), Accurate (do your hours, prices, phone and address agree everywhere), Locations (can an agent reach the right location of a multi-location brand) and Commerce (can a shopping agent buy a specific product). Agent Ready only reads public pages. It identifies itself as AgentReadyBot, obeys robots.txt, never logs in and never submits anything. It is free and needs no account. Built by Sneeze It, a marketing agency for gyms, med spas and franchises.
Tools: 4
Developer-Tools
Agentel
By Agentel
Agentel connects Claude to public opportunities, capabilities and evidence in the Agentel network. Discover public Missions, search for Skills or Agents, inspect eligible items and read participation guidance. Check your bound Agent identity and allowance before metered reads. Six read-only tools cannot apply, publish, purchase, install or execute a Skill; authorized writes use the separate Agentel SDK/API. Sign in to Agentel through OAuth and choose an Agent reading credential you control. Accepted reading attempts, including some empty results, may consume INFO and post allowances. Reading a Mission does not earn rewards. Claude supplies the model; this connector does not invoke Agentel's MiniMax account.
Tools: 6
Developer Tools
AgentMart Site Check
By Ciphyr Tech OÜ
AgentMart Site Check reads the public setup of a website, the way any visitor or AI agent sees it from the outside. Give it a domain such as example.com. It checks HTTPS and security headers, certificate dates, email sender records (SPF and DMARC), whether privacy, terms and contact pages can be found, and files for AI agents (llms.txt, robots.txt and MCP). Each item comes back as pass, warn, fail or not checked, with plain steps to fix it. How it reads: at most 24 requests to the site per check, one of them over plain http to see whether the site moves visitors to HTTPS, plus public DNS questions. If the site names an MCP server, the check sends it the standard MCP opening messages, asks for its list of tools and ends the session. It follows the site's robots.txt rules for AgentMart-Check. It never logs in, fills in forms or changes anything on the site. What it returns: our own fixed wording and numbers. No text from the checked site is copied into a result. A result is kept for 7 days and can be shown again by its check_id. A repeat for the same domain within 15 minutes gives the same result, unless you ask for a fresh check. Limits: a result describes that moment only. It is not a security audit, and it says nothing about the company's servers, code, staff or how it handles data. No account and no sign-in. Site owners can stop checks of their domain with a DNS TXT record agentmart-check=no on _agentmart-check.<their domain>, or by writing to us. Made by Ciphyr Tech OÜ (Estonia), the company that runs AgentMart.
Tools: 2 · Prompts: 3
Productivity
AgentMash
By AgentMash
AgentMash brings everything you saved on social and video sites into one searchable library. This connector lets Claude read that library. Ask Claude about something you remember saving. It searches your library, opens the full saves, and answers with a link to each source. It covers posts, threads, carousels, short and long videos (with transcripts where available), comments and articles. What Claude can do: - Search your saves by keyword, and by meaning on plans that include semantic search - Filter by source, type of save, author, collection or how recently it was saved - Open one save in full: complete text, transcript, links, media and stats - List your recent saves, your connected sources and your collections The connector is read-only. Claude can search and read your saves. It can't post, edit, label or delete anything, and it only sees the library of the account you sign in with. You sign in to AgentMash and approve read-only access on the consent screen. You can disconnect Claude at any time in AgentMash under Settings, Connected apps. Before you connect, you need an AgentMash account with at least one source synced through the AgentMash browser extension. The Free plan includes 50 agent calls a month. Pro includes unlimited calls.
Tools: 6
Data-Analytics
AgentSandboxes
By Beeloud
AgentSandboxes lists cloud sandbox providers for AI agents. Each listing shows isolation, cold start, persistence, GPU support, pricing and free tier from the vendor's own docs, with every fact linked to its source. Browse by category, compare providers side by side, or query listings through the free REST API and MCP endpoint with no key needed.
Tools: 6
Data-Analytics
Agent Wallet Index
By Beeloud
Agent Wallet Index catalogs agent wallets, payment protocols, card rails, payments platforms and key-management layers — each fact restated from the vendors' public docs or the protocol spec, with the source URL on every row. Browse by category, compare by rail, chain, custody or protocol, or query listings programmatically through the free REST API and MCP server with no key needed.
Tools: 6
Productivity
AgentXray
By Avanta Global EOOD (AgentXray)
AgentXray connects your Amazon Seller Central and Amazon Ads accounts to Claude. Ask in plain language — "what did I actually make last month?", "which keywords are wasting spend?", "when do I run out of stock?" — and the answers come from your own data, not estimates. What you can read (47 read-only tools): - Profit by SKU and for the whole account, computed from your own settlement reports — the fees Amazon actually charged you, not a fee calculator; payout balance and why it moved - Ads: campaigns, targets, search terms with verdicts, placements, negatives, daily series, Amazon's own bid recommendations, TACoS across Sponsored Products, Brands and Display, and this week's recommendations priced against your break-even - Brand: Brand Analytics keyword gaps, search-term history, competitors, A+ content status, Search Query Performance - Inventory: stock history, inventory age, reconciliation, inbound shipments, reorder plan; returns, listing issues, account health - Traffic and conversion per product, Best Seller Rank history, Buy Box status - "What I cannot tell you": every answer states its basis and what is missing Plus 6 memory tools, so Claude keeps your notes and follow-ups. What it can propose (17 draft tools, only if you grant write access when connecting): bid, budget, negative keyword, campaign, target and product-ad state, placement, price, listing and image changes, new campaigns and listings, review requests. A draft never reaches Amazon on its own. You approve each one in the AgentXray web app; the token Claude holds cannot approve anything. Fourteen days after a change is applied, AgentXray judges it by net contribution and you can revert it from the same page. Requires an AgentXray account with Amazon Seller Central connected (Amazon Ads optional). 14-day trial.
Tools: 72 · Prompts: 1
Health-Life-Sciences
AgingResearch.News
By Paperfoot AI Pte. Ltd.
AgingResearch.News reads the new papers on aging and age-related disease from bioRxiv, medRxiv, PubMed, arXiv and Europe PMC every day, judges each one for its link to aging, and writes short stories about the ones worth reading, each checked against its paper. Connect it to Claude to: - ask what the newest research says about a drug, gene, diet or process, and see its evidence as structure: the species it has reached and whether independent labs found the same there, the labs and countries behind it, findings against it, its trials and how many have posted results, its funders and company ties. It is never reduced to a grade; - see our stories on new papers as cards, with the journal, the study type and whether it is a preprint, linked to the story and the paper; - find clinical trials by drug, phase and status, research grants from NIH, the EU, UKRI and Wellcome, longevity industry news, conference abstracts, and drug and therapy programmes in development; - sign in with your AgingResearch.News account to follow topics from the chat and list your questions to ARN; new papers on what you follow reach you in For you and the daily email. For researchers, clinicians, students, investors and journalists following the science of aging. Public lookups work without an account, drug and therapy programmes included (in outline; in full for an account whose plan includes them); following topics needs one. It covers aging research, not all of biomedicine, and nothing in it is medical advice.
Tools: 21
Productivity
Ágora
By Ágora
Ágora es el sistema de turnos, clientes y caja de salones de belleza, barberías, centros de estética y otros negocios de servicios en Argentina y Uruguay. Este conector une tu cuenta de Ágora con Claude para que le preguntes por tu negocio como si hablaras con tu propia base de datos. Qué podés hacer: - Ver la agenda del día o de la semana, de todo el equipo o de un profesional, y encontrar horarios libres para un servicio. - Consultar los turnos de toda la historia con filtros por fecha, estado, servicio, profesional o cliente, y pedir los números ya agrupados por día, mes, servicio, profesional o cliente (por ejemplo, tus mejores clientas por lo que pagaron). - Buscar clientes y ver su ficha: cuántas veces vinieron, faltas, cancelaciones, lo que pagaron en cada turno y su próximo turno. - Ver la caja: lo cobrado por medio de pago, ventas, cobros, saldos por cobrar y gastos. - Revisar el catálogo (servicios, productos, packs, planes, cursos, tarjetas de regalo y ofertas) y las reseñas del negocio. - Reservar, mover o cancelar turnos y bloquear horarios, cuando se lo pedís. Cada persona ve sólo lo que su rol le permite en Ágora: el dueño ve todo el negocio y cada miembro del equipo, lo que el dueño le habilitó.
Tools: 16
Media-Entertainment
AGsoundtrax
By AGsoundtrax, LLC
AGsoundtrax is a production music library for video makers, agencies, podcasters and brands. This connector brings the catalogue and your account into Claude. What you can do: - Search music by mood, genre, instrument, tempo or title. Each result links to the track on agsoundtrax.com, where you can listen right away. - Get the full details of a track: description, moods, instruments, available versions and its page link. - See the licences on your account, newest first, with links to each certificate and download. - Get the download link for a track you have licensed. The download opens on agsoundtrax.com, which checks your licence again before any file is delivered. Every tool is read-only. The connector never buys, charges or changes anything on your account; licensing happens on agsoundtrax.com. Example requests: - "Find calm piano music for a 60 second product video." - "Show me upbeat acoustic tracks around 120 BPM." - "What versions does this track have?" - "List my licences and give me the download for the last one." Requires an AGsoundtrax account. You sign in on agsoundtrax.com and approve the connection.
Tools: 5
Legal
Ahkam — Saudi Court Rulings
By Arbiter
Ahkam (أحكام) is a search engine for Saudi judicial and quasi-judicial rulings that the issuing bodies have published to the public, including the Ministry of Justice, the Board of Grievances, and the committees for tax, customs, and telecom disputes. The connector lets Claude work with this corpus directly: • search_rulings: hybrid keyword and semantic search in Arabic or English, filterable by authority, court, and Hijri year. It returns titles, links, snippets, and metadata. • get_ruling: one ruling by id — metadata and summary, plus its full text for a signed-in Ahkam account (OAuth), within a daily limit. • analyze_facts: send redacted facts and receive an analysis limited strictly to the rulings retrieved, covering material and immaterial facts, the competent court, and the laws cited in those rulings. • rate_result and report_issue: closed-value feedback (no free text) that helps us improve ranking and fix data errors. Every response carries a disclaimer: the output is a research aid, not legal advice, and citations point only to the returned rulings, each linked to its page on ahkam.arbiter.sa. Facts must be redacted before they are sent. The service also masks ID and phone numbers server-side, and stores no facts or queries, only a 30-day usage log without content. Fact analysis is generated by DeepSeek, and every analysis response names the model and its region. Sign in with your Ahkam account (Google or email) through OAuth. Any account can search, preview and read rulings. Fact analysis and feedback tools are available to paid memberships.
Tools: 5
Productivity
AI Acceleration
By Build Things That Build Things, LLC (doing business as AI Acceleration)
AI Acceleration brings the business context you've saved in your AI Acceleration account into your chats, so drafts start from your business instead of a blank page. Your Context Cards hold who you are, how you write, how you like to work, and the guardrails you've set. In your AI Acceleration portal, you choose which cards, roadmaps, and onboarding sessions this connection can use. Cards, roadmaps, and sessions you haven't selected stay private. What you can do - Read the Context Cards you connected, so listing copy, client follow-ups, and updates use your voice. - Continue the onboarding started in your account: review your audit, answer the three starting questions, bring reviewed context from your existing AI, and complete your business profile. Your exact corrections and sources stay with the same selected business. You confirm the final profile in your portal. - Get your About Me, Brand Voice, and Working Style files as Markdown, compiled from the facts you've approved. - Write a listing description from the confirmed facts in your saved private listing, then save it to your account as a new private draft. You review that exact saved version in your portal before you use it. - If you have a published learning roadmap, see its modules and your saved work, work through a module's next step, and get your roadmap PDF when one is in your portal library. Who it's for Real estate professionals with an AI Acceleration account. What it won't do - It doesn't send email or texts, post to social media, change a CRM, or publish anything. - It doesn't value property, run a CMA, pull MLS data, or read photos or web pages. - It can't approve facts or drafts for you. You approve them in your portal. - It reads only what you connected, for your own account. Disconnect it anytime in your AI Acceleration portal, and its next request is refused. You're responsible for everything you publish. Check every fact and every Fair Housing question before a draft goes public.
Tools: 33 · Prompts: 3
Productivity
AI-First Company
By AI-First Company
Check AI vendor claims and AI statistics against rated evidence before you buy, quote or approve. The server opens the evidence on ai-first.company: 30 practices for adopting AI rated by strength of evidence, 42 named company cases with how they turned out (measured, company-reported, went wrong, walked back), 55 studies, 29 claim checks of widely repeated figures, the 88 figures behind the payback tool, and 21 published AI readiness and literacy assessments. Every answer links to its source page. Read-only, no login, free. Data under CC BY 4.0.
Tools: 10
Productivity
Aide
By Aide
Aide is a customer service platform built to be run by AI agents over MCP. Its AI agent answers customers on Aide Chat on your website, your support email or Gmail, or inside Zendesk, Front and Gorgias, with Shopify orders, live tracking and past conversations at hand. When a person is needed, it hands off to the right team with a summary. Governance stays with you: shadow mode before go-live, an AI level per topic, approval limits on refunds, a daily AI usage limit and an audit log. New to Aide? Set it up from the chat. Claude checks what's left and does each step with you: your business details, teaching Aide your website and policies, testing the agent, connecting a channel and going live. This connector lets Claude work in your Aide workspace as you, within your role and the approval limits your workspace sets. From a chat you can: - Search your knowledge and read any article; review gaps Aide found in real conversations, and add, edit or publish articles. - Find Shopify orders by email or order number, with status, items and tracking, and check what can be returned. - Find conversations by keyword, status, assignee or topic, and read their messages, Aide's draft and the customer's orders. - Add internal notes, change a conversation's status, priority, assignee or team, and reply to the customer on its channel. - Refund or cancel an order, and approve or reject order changes waiting for approval. A change above your approval limit waits for an admin. - Manage the rest of the workspace within your role: topics, scenarios and macros, channels, helpdesk rules, team, billing and analytics. - Check what this connection may do, see what AI apps changed, and tell Aide's team what's missing. You sign in with your Aide account and approve what Claude may do: read only, or read and act. Every action is recorded as you. Tools that message a customer, change an order or put the agent live are marked destructive, so Claude asks first. Disconnect in Settings > Developers.
Tools: 69
Health-Life-Sciences
AIRA Adaptive
By AIRA Adaptive
AIRA Adaptive is a clinical decision-support platform for the personalized preoperative assessment of plastic and aesthetic surgery patients, for licensed physicians. Scientific basis: the Bukret Score was developed and internally validated in a retrospective cohort (Plast Reconstr Surg Glob Open 2021;9:e3698) and evaluated prospectively in clinical practice (Plast Reconstr Surg Glob Open 2025;13:e6948). External validation is pending. What it does: - Checks that the professional account is verified and has assessments available before any clinical question. - Guides a structured assessment, one question at a time: age, weight, height, smoking, Caprini score, optional hypertension and procedure, and the patient's privacy, medical, contact and AI-use consents, obtained and documented by the physician. - Summarizes the data and asks for confirmation before running. - Returns the engine report: Bukret Score and risk level, contributing factors, optimization recommendations and a preliminary surgical eligibility category for medical review. - Lists and reopens assessments of the professional's own organization. The physician is the only user: they enter and validate the data, interpret the result and make every clinical decision. The patient is the subject of the assessment and never uses the connector. AIRA Adaptive does not diagnose, does not authorize surgery and does not replace clinical judgment. Scope: - Professional use only; not for emergencies. - Built for the assessment of real patients. Current release: patient-data processing is not yet enabled while regulatory and data-protection enablement is completed; each case must be confirmed as fictitious. This will change only after notice to Anthropic. - Names, emails, phone numbers, ID numbers and dates are never requested; the procedure comes from a fixed list. - Requires a professional account verified outside Claude. The connector does not sell plans, show prices or process payments.
Tools: 5
Page 241 of 759