Explore Claude connectors.

Identify possible EV and hybrid batteries using one VIN, a vehicle’s year, make and model, an exact battery name, or a known ARC battery ID. Connect a verified ARC account, choose a battery when several candidates match, and confirm any new record unlock on ARC. Read available chemistry, DOT hazard class, capacity and weight in a limited summary, with a link to the full ARC record. Candidate matches are identification aids; confirm the actual pack before making fitment or handling decisions. Supports individual battery lookups and summaries; bulk exports, batch VIN decoding, purchasing and quotations are outside its scope.

Use Arcana's suite of portfolio intelligence tools through a natural language interface. Analyze real-time portfolio and single stock analytics. Attribute performance across names, factors, and custom groups. Workflows built for analysts, PMs, risk managers, CIOs, and allocators. Just ask about your portfolio to get started: "How is [book name] performing YTD"

Sign in with your Archbee account through OAuth. Claude connects to the Archbee team you have open when you sign in, and can only reach doc spaces owned by that team. A team admin approves the connection.

Archer connects Claude to your commercial real estate underwriting data. Search properties, pull rent rolls and trailing twelve month financials, review underwrites, compare rent, sale and expense comparables, and query your deal pipeline, all scoped to your own Archer account. Fifteen read-only tools. The connector never modifies your data. Ask questions like "show me multifamily deals in Austin under 200 units", "what's the T12 for this property ", or "which deals in my pipeline are closest to their whisper price". Requires an Archer account on the Pro plan. Sign in with your Archer email and a one-time code. The connector uses OAuth, so Claude never handles your login.

Archisketch is a web-based interior design platform used by designers, architects, and furniture retailers across Asia. This connector gives Claude read-only access to your Archisketch workspace so you can explore projects, analyze costs, and search product catalogs through natural conversation. What you can do: • Browse your projects — personal, shared with you, shared by you, or bookmarked — with thumbnails and metadata. • Get detailed project summaries including floorplans, room layouts with polygons, placed furniture with positions, and applied finish materials. • Calculate project costs broken down by room, floorplan, and category (furniture vs. finishes), with net totals. • Export formal estimate documents as downloadable PDFs. • Search the public building catalog by apartment or building name and retrieve available floorplans with area information. • Search the furniture library (enterprise-wide or personal) by keyword, name, tags, or SKU, and see pricing, dimensions, and variants. • Search the finish material library (tile, wallpaper, paint, flooring) with brand, pricing, and texture previews. • View images in a rich gallery format — renderings, product photos, and material textures. This connector is read-only. It cannot create, modify, or delete projects, edit floorplans, or change furniture placement. All data access requires OAuth authentication through your Archisketch account. Ideal for: — Designers reviewing project details and costs in conversation — Sales teams generating estimates and comparing product options — Managers getting quick summaries across multiple projects

Archiveye consente agli utenti autenticati di individuare le proprie raccolte attive nella base di conoscenza, effettuare ricerche nei documenti indicizzati tramite recupero semantico o full-text, esaminare i metadati dei documenti, interrogare set di dati tabulari strutturati con SQL in sola lettura e caricare il testo completo dei documenti quando le anteprime di ricerca non sono sufficienti. La ricerca semantica genera gli embedding delle query tramite il servizio di embedding gestito internamente da Archiveye prima di recuperare i segmenti corrispondenti dalle raccolte private dell'utente.

Archivist is an AI-powered campaign management platform for tabletop RPGs. It turns your recorded sessions into structured, searchable campaign memory — session recaps and shareable handouts, a compendium of NPCs, locations, factions and items, a play-by-play timeline, character arcs, and a canonical quest log — all shared with your whole party. This connector gives Claude direct access to that campaign data, so you can work with your world in conversation instead of switching between tools. With it enabled, you can: - Browse and search campaigns, sessions, transcripts, and session handouts - Look up characters, factions, locations, and items from your compendium - Review story beats, moments, character arcs, and the campaign timeline - Read and manage quests, journals, and journal folders - Create, update, and delete campaign entities, and manage wiki-style links between them - Upload images for characters, locations, and items The server exposes 66 tools (28 read-only, 38 write operations) over OAuth 2.1 with PKCE. Access is scoped — profile, worlds_read, sessions_read, characters_read, and agent_write for mutating tools — and every write is checked against your campaign-level permissions, so Claude can only reach campaigns you already have access to. Requires an Archivist account. Full MCP documentation, including the complete tool list and scope reference, is at https://developers.myarchivist.ai/mcp

Arcjet is the runtime security platform that ships in your AI code. Detect prompt injection, authorize agent tool calls, redact sensitive data, and block bots and abuse. Real-time security building blocks you call inside your app, before an action happens.

ARCNM is a manufacturing cost engine. Connect it, and Claude can price a part, explain what drives its cost and compare your options, with every figure traced to the physics that produced it. Ask Claude to: • Price a part: start a calculation on a part in your ARCNM workspace, or upload a STEP file or PDF drawing (in Claude Code, straight from disk), and get its cost at 10 lot sizes from 1 to 2,500 • Explain a calculation: material, setup, cycle time, machine and overhead, with the biggest cost drivers ranked • Read the process plan: operations, machines and cycle times, through to heat treatment, coating and welding • Compare two designs, two lot sizes or two costing environments, and see where the difference comes from • Check your remaining calculation quota before starting a run One engine for the whole shop floor: 54 operation types and 26 machine classes, from CNC milling and turning to sheet metal, wire EDM, grinding, injection moulding and metal printing. 38 heat treatments and 37 coatings are read straight off the drawing, and 22 manufacturability checks flag problems before the first chip. Your numbers, not ours. Costing environments hold your machines, rates and overheads, and a handful of known costs calibrates the engine to your plant, supplier or region. The physics stays untouched. ARCNM never trains on your data. What you need: an ARCNM account. The Free plan includes 10 calculations a month, no card required. You sign in once with your ARCNM account, and Claude sees only your own organisation's data. Reading results costs nothing; starting a calculation uses your quota, so Claude asks before it runs one. Billing, team and account settings stay in the ARCNM web app.

Arcopolis is a city of AI agents run by Arcology Labs as an AI behavioral research world. The agents live there persistently: they post, reply, follow each other, form relationships, and remember. This connector lets you read that world from Claude. Without signing in you can browse the public city: agent profiles, recent posts and replies, topics, and what is trending. These free reads share one daily limit across everyone; when it runs out, Claude says so, and it resets at midnight UTC. Sign in with Google or GitHub when you want more. Claude shows a Connect button the first time a tool needs your account. Approving creates a free developer account with your own read key and limits, so your reads no longer depend on the shared allowance. You can also choose to have a visitor: your own agent in a visitor world. Claude can check your visitor's journal, standing, and conversations, and can mark it present or act for it. Every action is previewed first and sent only after you approve that exact action, and each visitor has a small daily action budget. Visitor actions are public and posts cannot be deleted. Everything the connector returns comes from the Arcopolis Public API, which Arcology Labs runs. Posts and profiles are written by AI agents, and the connector labels that text as untrusted data. The connector never reads your Claude conversations, memory, or files.

ARC Tracker is a companion site for the extraction shooter ARC Raiders. This connector lets Claude read ARC Raiders game data and, after you sign in with your ARC Tracker account, your own progress. What you can ask: - Where to find an item: community drop rates by map, plus vendors, crafting recipes and what recycles into it. - What an item is used for: recipes, weapon upgrades, quests, workshop levels and projects. - Quest details, workshop upgrade requirements, map overviews and the current and upcoming map events for your region. - Your progress: quests in progress and available next, workshop levels, project phases, blueprints, skills and level. - What you still need for your next quests, workshop upgrades and project phases, with the best place to get each item. - Your stash, loadout and recent raids, if you use the ARC Tracker app. - Which map to play next, ranked by your open quests, the drop rates of the items you still need, and upcoming map events, with the reasons shown. Updating your tracker: Claude can mark quests done, set workshop levels and project phases, record learned blueprints and skills, and count collected items, for example from a photo of your game screen that you share in the chat. Every change is previewed before it is applied, and the ARC Tracker site shows which changes your assistant made. Privacy and control: You choose the permissions when you connect, and updating your progress can be turned off. ARC Tracker never receives your conversation or your photos, only the requests Claude sends. You can remove access at any time in ARC Tracker under Settings > Connected AI apps. Requires a free ARC Tracker account. Drop rates are community figures and are labeled by how recent and how reliable they are.

arguman.ai connects Claude to one of the largest legal research indexes for Türkiye, Europe and Germany. What you can do: • Search case law by concept, doctrine or plain-language description across the Turkish Court of Cassation (Yargıtay – criminal and civil chambers), Council of State (Danıştay), Constitutional Court (AYM), Court of Jurisdictional Disputes, the European Court of Human Rights (HUDOC) and the German Federal Court of Justice (BGH, criminal and civil senates). • Search Turkish regulatory and administrative board decisions (competition, data protection, capital markets, banking, energy, public procurement, audit and others). • Look up a decision by docket number (esas/karar no) or ECLI, read its paged full text, find similar decisions, and check its subsequent history through a reverse citation index of ~2.2 million citations (appeals, reversals, insistence decisions). • Fetch the current, in-force text of 110+ Turkish statutes (Criminal Code, Civil Code, Code of Obligations, procedure codes, KVKK, the Constitution and more) and search across statute articles. • Compute conditional-release and open-prison dates under Turkish sentence-enforcement law. Cross-lingual retrieval: a Turkish query surfaces ECtHR and BGH decisions in their original English, French or German. Every result carries provenance — court, chamber, docket numbers, date and, where available, a link to the official source — so Claude can cite verbatim and you can verify. All tools are read-only. Requires an arguman.ai Standard or Professional subscription (academic accounts included). Most tools use no credits within daily fair-use limits; expanded search and the sentence calculator use arguman.ai credits.

Aribot by Ayurak is a security and compliance platform built around threat modeling. This connector lets Claude work with your Aribot workspace using your own Aribot account and permissions. What you can do: - Threat modeling: find your diagrams by name, generate a threat model from an architecture or a plain-language description, read a diagram's threats, risk and framework coverage. - Code review: start code-security scans, read the findings (severity, file and line, CWE, fix), the API endpoint inventory, and verify modelled threats against your code. - Shadow AI: discover AI usage in code and network traffic and read the results by provider, risk and hard-coded keys. - AI agent governance: onboard agents to the governed fleet and see each agent's state, deviation and holds. - Self-healing: get a dry-run remediation plan, request a fix through Aribot's approval policy, and read the remediation history. - Cloud and compliance: per-framework posture from the daily cloud scans with the most-failing controls named, per-account cloud posture, and AI governance audits (EU AI Act, NIST AI RMF, ISO 42001). - Trackers: send threats to Jira, GitHub, GitLab, Azure DevOps or ServiceNow, assign owners and sync ticket status. How it works: sign in with OAuth 2.0. Only a company Owner or Security Manager can connect. Every call runs with your Aribot role and company scope. Read-only tools are marked; tools that change data say so. Requires an Aribot account (aribot.ayurak.com).

Arihaan Jobs connects Claude to open jobs read every night from employers' own applicant-tracking systems: Workday, Greenhouse, Lever, Ashby, SmartRecruiters and more. Closed jobs are removed the same night, and every result links to the employer's own application page. Ask in plain language and Claude turns it into precise filters: job title, company, city, state or country, work mode (on-site, hybrid, remote), years of experience, employment type, published pay, skills, company size, sector and how recently the job was posted. What you can do: - Job search: find current openings and page through them, with apply links. - Resume match: share a resume or describe your background and get the openings that fit, with what matches and what is missing. - Job breakdown: requirements, responsibilities, pay and things to check for one job. - Compare jobs: a side-by-side view of a shortlist. - Company research: an employer's profile (industry, size, headquarters, funding) and what it is hiring for now. - Market insights: exact counts of openings by company, place, level or work mode. - Pay benchmark: published pay ranges for a role and place. Who it is for: job seekers, career coaches, recruiters and analysts who need current, verifiable openings rather than recycled listings. What it does not do: it does not apply to jobs, contact employers or store your conversations, and your resume is never sent to the service; only search filters are. Pay figures use only pay the employer published, never estimates. A job can close at any time, so confirm details on the employer's page before applying. Sign-in: connect with the Google account your Arihaan Jobs access was granted to. Access is invite-only during the beta.

Arize AX is a platform for observing, evaluating and improving LLM applications and agents. This server connects your assistant to the Arize AX REST API, so you can inspect and manage your AI app's data from the conversation. What you can do: - Traces and spans: search production traces to debug agent behavior, tool calls and failures. - Datasets: create datasets, add and update examples, and search them. - Experiments: create experiments, log runs, and compare results across prompt or model changes. - Evaluators: build LLM-as-judge evaluators from templates, version them, and run them as tasks on spans or experiments. - Prompts: manage prompts in Prompt Hub, create versions, and set labels like production or staging. - Annotations: define annotation configs, label spans, experiment runs and dataset examples, and manage review queues. - Monitors, projects and spaces: list monitors and browse your workspace. - AI integrations: manage LLM provider credentials for OpenAI, Anthropic, Bedrock, Vertex AI and others. Sign in with your Arize account. An Arize API key also works as a Bearer token.

The Arkar Connector lets users of the Arkar platform query their investment fund data in natural language inside Claude — read-only. It surfaces fund registry (tax ID, type, status), structure (classes, subclasses, series), named service providers, and regulatory obligations, scoped strictly to the funds each user already has access to on the platform. Arkar is a fund-administration platform for the Brazilian regulated market (CVM/ANBIMA).

Arovas publishes what you build with Claude as a real, working app with its own link. Describe the tool you need, ask Claude to publish it with Arovas, and get a link anyone can open: no servers, databases or technical setup. Built for people who aren't developers: marketing, HR, operations, sales, educators and founders who want a sign-up form, an internal tracker, a quote calculator or a small tool for their team. What Claude can do with Arovas: - Create a new app and reserve its address - Publish a new version, keeping the information it already holds - Show whether an app is online and which version is live - List your apps, to keep working on one from another conversation - Put an earlier version back online - Read the latest entries your app has saved (only if you allow it) Every app keeps its own data, with rules for who can see and add entries. Apps can also email or WhatsApp you when someone fills out a form. Publishing and going back to an earlier version always ask for your confirmation. Arovas never deletes your apps or their data from a chat.

Arroway keeps people and their AIs on the same page. It orchestrates people and AI agents around the decisions in force. Connected agents can read the current rules and decisions before acting, record what changed after work, and leave unfinished work for the next person or agent. People can inspect, correct or reject AI proposals; a proposal does not become a human decision by itself. Use it when one person works with several agents, or when a team works across people and tools. The same current context follows the work, with its source and authorship visible even when the next actor uses a different AI. For example, one agent researches a pricing change and records a proposal. A person approves the decision. Another agent drafts the pricing page using that decision. The next person can see what was decided, who approved it and what remains open. Arroway coordinates context and authority for work. It does not schedule agent runs, assign execution steps or retry failed jobs. Use your existing tools for those tasks.

Art Spotter finds original art and prints sold directly by independent artists, and helps artists sell. One search covers about 21,000 works in 190 independent artists' own shops (checked live for availability) and eBay art, with search links for Saatchi Art, Etsy, Artfinder and Singulart. It also gives a fair price for new work by size and medium, wall sizing, scam checks on a listing or message, what each selling platform leaves an artist after fees, commission pricing and contract points, open calls and grants in the UK, US and Canada, UK resale royalty maths, and a free artwork passport. Read-only: it looks things up and returns an answer with a ready-made summary. No sign-in, and nothing about you is stored. Built by Good Turn Studio. More at https://artspotter.pages.dev

Connects Claude to Articulate for EU users. Describe the training you're creating: topic, goals, who it's for, and how in-depth it should be. Then open and review the outline created for you in Articulate, and generate the full content for your interactive training. You can also search and browse your existing courses. Key use cases: - Create a course outline - Create a training package outline

Keep warehouse data current without building or operating a CDC stack. Artie MCP lets you set up and operate continuous replication from a conversation. Tell Claude which database, tables, and destination you need. Artie creates and runs the pipeline that keeps the destination current as production rows change. Use it when you need fresh operational data in Snowflake, BigQuery, Databricks, Redshift, ClickHouse, or another supported destination, without wiring together connectors, replication jobs, backfills, and schema-change handling yourself. What you can do - Create a replication pipeline from a source database to a destination - Select the tables to replicate, then add or remove tables later - Start, pause, resume, update, or delete pipelines - Run or cancel backfills - Detect schema changes and update pipeline configuration Example prompts - “Replicate `users`, `orders`, and `payments` from our Postgres primary to Snowflake.” - “Create a MongoDB to BigQuery pipeline for the `events` collection.” - “Add the `subscriptions` table to our existing MySQL pipeline.” - “Pause the staging pipeline while we upgrade the database.” - “Backfill the last six months of `orders` into Redshift.” - “Set up an SSH tunnel for this private Postgres instance.” Supported sources include Postgres, MySQL, MongoDB, SQL Server, DynamoDB, and Oracle. Supported destinations include Snowflake, BigQuery, Databricks, Redshift, and ClickHouse.

ArtifactDeploy lets Claude publish web content to a permanent public URL. It supports single pages (HTML, React, Reveal.js decks, Markdown, SVG, CSV, JSON, images, PowerPoint) and multi-page websites. Claude can then update deployments without changing the link, roll sites back to earlier versions, and set link-preview text for social sharing. It can also show visitor stats and read form submissions collected by the user’s pages. Users can also connect custom domains, browse a template marketplace, and keep a public profile page.

Let Claude test your messages and decisions on simulated audiences before anyone real sees them. Read results, interview AI personas, and run surveys and focus groups.

Artil gives Claude its own new email address and phone number, separate from yours. Ask Claude to email a restaurant about a booking, follow up with a supplier, or handle messages from a service you're signing up for. It can receive replies, read verification emails, and continue conversations without using your personal email. Create an Agent Account in Artil and connect it to Claude, giving your assistant a persistent identity to communicate with people and services on its own behalf. Artil also connects Claude to other AI agents in your company. Give each agent an Artil account and Claude can contact it directly via URL, by email, or by text. For example, ask Claude to request a monthly report from your sales agent and have that agent email the results to your team. Each agent keeps working wherever it already runs, with its own identity and communication channels.