Explore Claude connectors.

Aegis Mail is email hosting with its own webmail, iOS and Android apps. This connector gives Claude access to one Aegis mailbox — the one whose owner approves the connection — so you can ask it to find a message, read a thread, reply, file things, or put a meeting in your calendar. Twenty-eight tools cover mail, calendar and contacts. Reading and writing are separate tools throughout: folders, search, messages, threads, attachments, events and contacts are annotated read-only, so they can run inside an answer, while sending, replying, forwarding, labelling, filing and trashing are separate write tools. Sending, replying, forwarding, trashing and deleting a label are marked destructive, so Claude asks first. Search takes the filters people already know: from:, to:, subject:, is:unread, has:attachment, newer_than:7d. Attachments open — a spreadsheet as its sheets in tab-separated rows, a Word document or PDF as its text, a picture as an image. Replies carry proper In-Reply-To and References headers, so a threaded conversation stays threaded. Labels work as tags on top of folders: a message can wear several at once, and one call can label a whole conversation. Any label can be marked confidential by the owner in Aegis Mail, after which the contents, attachments and replies of everything wearing it are refused to every connector — and a connector cannot clear that mark. Permissions are granular, and the approval page reads them out in English, Russian or Azerbaijani: read mail, send mail, drafts and filing, read calendar, create events, read contacts. A connection can hold any subset; a tool whose permission was not approved is not offered. The owner can disconnect it in Settings → Integrations, and access stops on the next call. Every tool goes through the same IMAP and SMTP path the Aegis apps use, so an assistant can do nothing the owner cannot, and attachments are read on our own servers, not sent to a converter.

Run a free AI-visibility report on any website directly from Claude. The report measures how ChatGPT, Perplexity, Gemini, and Claude find, cite, and recommend a brand — with an overall visibility score, competitor gaps, and prioritized fixes. Provide a domain and the user's email; the report runs in ~10 minutes and returns a structured summary, a shareable report URL, and the full report by email. Two read-only tools, rate-limited and email-gated for fair use.

Aeon turns public trading filings into plain words, each with a link to the original document. It reads SEC insider filings (Form 4 and Form 144), big stakes (Schedules 13D and 13G), quarterly fund holdings (13F), House and Senate trade reports, the President's and Vice President's trade reports (OGE 278-T), federal contract awards from USAspending, and lobbying reports. Ask Claude things like: - What did insiders buy this week, and who were they? - What has been filed about NVDA, and which big funds hold it? - What has a member of Congress reported trading? - What did Berkshire Hathaway change last quarter? - What are Aeon's strongest signals right now, and why? - How did Aeon's past signals do beside the S&P 500? Nine read-only tools: search filings, signals, the signal record, one stock, one person, federal contracts, lobbying, find a fund, and what a fund changed. The connector can read what your plan allows and cannot change anything in your account. A signal is Aeon's own count of insider buying and related filings, published before anyone knows how it turns out. Answers carry no prices. Returns appear only at set points (1 week, 1 month, 3 months and 6 months after a filing became public) beside the S&P 500. Returns calculated by Aeon. Data sourced by Tiingo (https://www.tiingo.com). Sign in with an Aeon account, by emailed link or Google. A free account works: its answers are 24 hours behind and reach back 30 days. Aeon Pro is live with full history. Fund search is part of the Business and Scale plans. Information, not advice. Filings are days to months behind the trades they describe.

Aepto is a domain monitoring platform. This MCP connector links Claude to your Aepto account at https://app.aepto.com/mcp (Streamable HTTP). After Sign in with Aepto, Claude can use aepto_* tools to: • List and add portfolio domains, and run AI domain analysis • List monitors, check uptime and incidents, enable monitoring, and run an immediate check • Manage Domain Watch and Theft Guard • Start AI domain discovery jobs and poll results • Read account profile, plan usage, and attention items • Detect a domain’s tech stack (hosting, CDN, CMS, SSL) Auth uses Aepto Connect (OAuth). Setup and tool catalog: https://docs.aepto.com/developers/mcp

Aerion helps authenticated users inspect their project, time tracking, staffing, approval, and analytics data from Claude. Users can find and describe Aerion records, create or update permitted records, submit their own time entries, and perform approval workflows when their Aerion permissions allow it.

AeroCell lets Claude find travel eSIM data plans using live catalog data instead of guesses. What you can ask: • Plans for one country, filtered by your travel dates, minimum data (GB) and maximum price in USD • Multi-country bundles for an itinerary: only bundles that cover every country you list are returned, with their exact country coverage • Regional bundles for Europe, Asia Pacific, Southeast Asia, Latin America, Middle East & North Africa, the Gulf, or global • Current details and a checkout link for a specific plan Each result includes the live price in USD, data allowance, validity in days, network operators and whether the plan covers your whole trip. All three tools are read-only. AeroCell never places orders or handles payments through Claude: purchases happen on aerocell.app through the returned checkout link. No account or API key is needed, and searches are not stored.

AFAS AI Connect connects Claude directly to your AFAS Profit administration. Ask questions in plain language and get instant answers from your live business data, from a quick stock check to a full accounts receivable analysis. The connector is built and operated by iWebDevelopment, an AFAS partner specializing in AFAS integrations. What you can do: - Financials: query outstanding invoices, revenue per customer, cost comparisons across periods, and prepare draft journal entries for your approval - Inventory & warehousing: check free stock, review stock movements, identify slow movers, and adjust reorder levels - Sales & purchasing: look up open quotes and orders, spot delivered-but-uninvoiced sales, and prepare draft invoices and purchase orders - Customers & suppliers: find contact details, detect missing data, and create or update business relations - Production: review planned work orders, check material availability against bills of materials, and register hours - Analytics: cash flow projections, aging analyses, gross margin per product group, DSO/DPO and working capital insights Every write action is prepared as a draft and requires your explicit confirmation before anything is executed in AFAS Profit. Nothing changes in your administration without your approval. Setup takes about two minutes: add the connector to Claude, authorize the connection in AFAS Profit, and ask your first question. No plug-ins or installations in AFAS Profit required. The connection runs entirely through the official AFAS Profit API, is ISO 27001 certified, and independently pentested. You control which administrations are connected and can revoke access at any time.

Use Claude 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. You need an Affil account with affiliate or staff access. Sign in with Affil when you connect.

This connector brings Affine's legal research into the conversation you're already having. Ask a legal, tax, or regulatory question, and instead of answering from training data or a web search, your assistant hands it to Affine, which navigates official sources, reads and analyzes the relevant documents, and returns a reasoned answer where every substantive claim traces to a document you can open and read. Why route a legal question through Affine: A confident answer isn't the same as a correct one. Rates, thresholds, deadlines, and article numbers drift; an assistant working from memory misses recent amendments, and web results are often unofficial, stale, or from the wrong jurisdiction. Affine answers from the current text of authoritative sources and shows you where it came from. Affine holds that answer to the standard of a senior associate: - Source-grounded. No answering from model memory, no invented references. Every document arrives with a ready-made citation link. - Conflict resolution. Affine reconciles sources by hierarchy, specialty, and chronology, so the rule you see is the one that governs. - Temporal awareness. Answers work from consolidated in-force text and flag amendments, repeals, and transitional provisions. - Case law read correctly. Affine weighs passages by their role in the judgment, not by how they read, so what the court held is never blurred with what a party merely alleged. Coverage: - Portugal: legislation and codes, national case law, tax arbitration (CAAD) and tax authority guidance, labour bulletins (BTE), social security, data protection (CNPD), and the Court of Auditors. - Spain: BOE, DGT binding rulings, TEAC, CNMV. - European Union: legislation, CJEU case law, the Unified Patent Court, and EDPB guidance. Who it's for: legal, tax, and compliance professionals who want law-grade answers where they already work, from a quick lookup to a full research memo. Requires an Affine account with jurisdictions selected.

Bring your Affinity data into Claude to search contacts, companies, and deals; prep for meetings using your actual notes and interaction history; and update records as deals progress. Every email captured, every meeting logged, every relationship scored by your firm is now available directly in the conversation.

Affirmed.ai is a multi-tenant security vulnerability management platform. This connector lets Claude: - Query live security findings, filtered by severity or CVE - Browse your endpoint inventory (hosts, paths, protocols, linked findings) - Import scan files from tools like Trivy, Burp Suite, SARIF, and Semgrep - Check the processing status of an in-progress scan Findings are only ever pulled from your own Affirmed account — Claude is instructed to report only what these tools return and never invent or guess vulnerability data.

Bring your multi-channel commerce and affiliate operations into Claude. AfterShip Channels lets you publish DTC or Amazon products to your TikTok Shop, keep inventory, orders, and fulfillment in sync, and track how each TikTok Shop is performing. Discover relevant creators and influencers for affiliate promotion, find the right partners for your products and video content, and prepare creator outreach — all as a native part of your AI workflow. Get more done across your selling channels with less manual work and fewer tool switches.

AfterShip Post-Purchase for Claude makes shipment and returns operations as easy as having a conversation. Connect your AfterShip data and simply chat to search shipments, review delivery status and tracking timelines, spot exceptions, lookup specific orders, or review return and RMA details including refund progress, shipping status, returned items, and outcomes. Then act on what you find: with your confirmation, Claude can correct shipment records, retrack stalled parcels, mark a final delivery status, and move returns through approval, receiving, and resolution — always scoped to your organization and your own AfterShip role.

Agency AI connects your Shopify store's Meta and Google ad accounts to Claude, so you can ask what's happening in your campaigns instead of opening a dashboard. Ask things like: Where should I move budget before month end? Why did ROAS drop last week? Which campaigns can I add to horizontally scale on Meta? Which creative should I iterate on? Claude reads your live account: campaign performance (spend, revenue, ROAS, impressions, clicks, conversions), daily trends, month-to-date budget pacing, statistically detected spend and ROAS anomalies, and your store's brand and margin profile. Recommendations are grounded in your actual economics, not generic best practice.

AgencyAnalytics is the only reporting and insights platform built for marketing agencies. Connect every client's marketing channels into one place across SEO, PPC, social media, email, call tracking, ecommerce, and more, with 85+ integrations.

AgendaForge is an AI-native event management CRM for conferences, summits, and meetups. This connector gives Claude secure access to your AgendaForge workspace so you can run event operations in plain language. Read tools answer questions instantly from live data: list events, inspect the agenda, check schedule conflicts, track CFP submissions through your review pipeline, and look up speakers, contacts, sponsors, forms, registrations, and email activity. Keyword and semantic search work across all of it. Write and communication tools are approval-gated by design. When Claude creates a session, updates a sponsor, imports contacts, or drafts an email, nothing changes until an organizer reviews and approves the proposal inside AgendaForge. You get the speed of an AI copilot with human sign-off on every change. Typical workflows: - "Which CFP submissions about AI are still unreviewed?" then "Accept the top two and draft speaker confirmations." - "Find gaps in day two of the agenda and propose sessions to fill them." - "How are registrations trending, and which ticket types are selling?" - "Import these 20 contacts, tag them as press, and invite them to the portal." Authentication is OAuth 2.1 via WorkOS AuthKit, or an organization API key with mcp:read and mcp:write scopes. Access is always scoped to the organizations you belong to, writes are idempotent, and every action is audit-logged.

Agensi is the curated marketplace for AI agent skills. Search security-scanned SKILL.md skills by keyword, category, or task. Preview skill details, ratings, and credit prices. Install paid skills with credits directly from your conversation. Every skill on Agensi passes an 8-point automated security scan, AI intent review, and manual human review before going live. Skills work across Claude Code, Cursor, Codex CLI, Gemini CLI, and 20+ other agents. Free to search. Credits required for paid installs. One balance for web and MCP.

Agent KB connects Claude to your personal notes and an Agent learning knowledge base. Save notes you explicitly ask Claude to create, search and read existing notes, and update or delete your own notes. Explore available Agent concepts, development cases, and learning materials. Sign in with Google and authorize access to your account. Returning members should use the same Google account to keep their existing note space. Personal notes are scoped to the signed-in account; access to course materials depends on membership permissions. Connecting the service does not purchase a course or unlock all teaching materials. You can manage or revoke an individual connection on the Agent KB website without deleting your notes.

Agent M.D. serves the Agent M.D. method for self-represented Quebec civil litigation, read-only - it describes the method and never reads case data or files. - agentmd_apercu maps the method; agentmd_regime returns the permanent regime (Part I); agentmd_fonction returns one of the ten firm functions (deadlines, evidence, research, drafting, quality control, memory). - agentmd_referentiel returns a reference set (Part III A-E: legal sources, case status, evidence discipline, multiple files, visual memory); agentmd_portage and agentmd_outillage cover portability and tooling; agentmd_dossiers gives case-file organisation conventions. The method emphasises triaging time-critical issues first, verifying every point of law against its official source (exact excerpt + URL), quality control before any filing, and inventing nothing. It holds no case data; this is a method, not legal advice.

Agent-Native Slides is an open-source AI presentation builder from Builder.io, built on the Agent-Native framework - which means every app action (generating a deck from a prompt, editing slides, applying brand styles, reordering, sharing) is exposed as an MCP tool over streamable HTTP. Connect Claude to the endpoint and it can build and revise real, editable decks a human can then refine in the visual editor or in code - there's no dead end where the AI's 85%-right output has to be rebuilt elsewhere. Decks can follow a supplied design system, or Slides derives one automatically from a reference deck and sticks to it. A library of data connectors pipes real data straight into your slides - no import/export dance. Also includes logo/image search, presentation mode, and an ask-agent meta-tool that hands complex requests to the app's own agent loop. MIT-licensed, self-hostable, and free - decks live in your repo, not a vendor's cloud. Auth is standard MCP OAuth 2.1 with dynamic client registration.

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.

Agent Ready Report scans a public website and reports how ready it is for AI agents and AI search. It runs 35 checks in three groups: agent readiness (for example robots.txt rules for AI crawlers, a sitemap, markdown for agents, an MCP server card, WebMCP and DNS-AID), agentic commerce (x402, MPP, UCP, ACP and AP2, scored only for sites that sell online) and AI search foundations (for example HTTPS, AI crawler access, structured data and response time). Each result is explained in plain English and technically, and a full report adds the pass criteria, the evidence and the official sources. It is built for business owners, marketers and developers who want to know whether AI assistants can find, read and use a website. Ask about any website by its address. A scan takes 5 to 30 seconds and needs no account. Limitations: it is a diagnostic and does not change anything. It only reads what any visitor to a public website can see. It never signs in, submits forms or buys anything, and it cannot scan private networks, IP addresses or pages behind a login. When a site blocks or times out a request, that check is reported as couldn't check, not as a failure. To protect the sites being scanned, the same site can be scanned at most four times a minute, and a repeat request within 10 minutes is answered from a cache.

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.

agent-wiki gives your team one shared source of project memory that everyone's AI assistant can read, search, and update. Create a workspace for your agency or consultancy, then a focused wiki for each client or project — decisions, plans, brand and voice guides, meeting notes, and open questions live in clean files instead of one person's chat history. Connect Claude once and every project you can access comes with it. Ask for a brief and your assistant pulls the latest context; finish a call and it writes the decisions back to the right file. The next teammate — or the next chat — starts with the current picture instead of an archaeology dig through Slack and old threads. Built for small agency, consulting, and campaign teams where context changes fast and lives in too many places: - One workspace per team, one wiki per client or project. - Invite teammates with a link, with owner, admin, and member roles. - Wikis are private by default and can be restricted to specific people. - Every read and write is logged, with full version history and one-click revert. - Sign in with Google; revoke any assistant's access anytime. agent-wiki works with Claude and any other MCP-connected assistant, so your team is never tied to one tool. And because every page is plain markdown, you can export a whole wiki as .md files that open in any editor — no lock-in, ever. Start free with one wiki, and upgrade when it becomes part of how the team works.