# Claude.ai Documentation

## Docs

- [Admin controls](https://claude.com/docs/claude-science/admin-controls.md): Members sign in to Claude Science with their Claude account, so your identity and billing controls apply automatically.
- [Annotations](https://claude.com/docs/claude-science/annotations.md): Annotations let you attach comments to specific parts of an artifact instead of describing a location in prose.
- [Artifacts](https://claude.com/docs/claude-science/artifacts.md): An artifact is a file Claude saves into the project: a figure, processed dataset, report, notebook, or other output.
- [Claude Science changelog](https://claude.com/docs/claude-science/changelog.md): Release notes for Claude Science, including new features, improvements, and bug fixes by version.
- [Cloud storage](https://claude.com/docs/claude-science/cloud-storage.md): Connect Amazon S3, Google Cloud Storage, or Azure Blob Storage so Claude can read data and write results in place, with your permission.
- [Command line settings](https://claude.com/docs/claude-science/command-line-settings.md): Reference for the claude-science command: every subcommand, the serve flags, the single-use login link, and the two environment variables Claude Science reads.
- [Compute providers](https://claude.com/docs/claude-science/compute-providers.md): Claude Science can run jobs on an external cloud provider you control, and connect to model servers that serve scientific models over HTTP.
- [Connectors and skills](https://claude.com/docs/claude-science/connectors-and-skills.md): Connectors give Claude access to external data sources during an analysis.
- [Core concepts](https://claude.com/docs/claude-science/core-concepts.md): A project groups related sessions and the artifacts they produce.
- [Custom connectors](https://claude.com/docs/claude-science/custom-connectors.md): Add any Model Context Protocol (MCP) server as a Remote (HTTPS web server) or Local command (program on your computer).
- [Enable Claude Science](https://claude.com/docs/claude-science/enable-claude-science.md): Claude Science is a desktop app for scientific research.
- [Get started](https://claude.com/docs/claude-science/get-started.md): macOS: Download the installer from claude.com/product/claude-science and double-click to install.
- [Glossary](https://claude.com/docs/claude-science/glossary.md): One-sentence definitions for the terms you meet in Claude Science, from annotation to workspace.
- [How Claude Science works with your data](https://claude.com/docs/claude-science/how-claude-science-works-with-your-data.md): Claude Science is a local-first application.
- [Legal and compliance](https://claude.com/docs/claude-science/legal-and-compliance.md): Legal agreements, compliance certifications, and security information for Claude Science.
- [Literature access](https://claude.com/docs/claude-science/literature-access.md): Claude retrieves open-access full text without credentials.
- [Manage Claude Science on devices](https://claude.com/docs/claude-science/manage-on-devices.md): Claude Science is a desktop application that stores all member content locally.
- [Monitor Claude Science usage](https://claude.com/docs/claude-science/monitor-usage.md): Claude Science usage counts against each member's standard weekly quota and uses the same seat as the rest of claude.ai.
- [Claude Science](https://claude.com/docs/claude-science/overview.md): Anthropic's AI workbench for rigorous science.
- [Remote compute clusters](https://claude.com/docs/claude-science/remote-compute-clusters.md): Connect a machine you can reach over SSH (a lab workstation or an HPC login node) so Claude can run jobs on it.
- [Run on Windows with WSL](https://claude.com/docs/claude-science/run-on-windows-wsl.md): Claude Science doesn't ship a native Windows build yet, but the Linux binary runs well under Windows Subsystem for Linux (WSL 2).
- [The reviewer](https://claude.com/docs/claude-science/the-reviewer.md): A built-in verification step that independently re-reads Claude's recent responses, the approved plan, saved artifacts, and the execution record, then checks whether its claims match what ran.
- [Tools and environments](https://claude.com/docs/claude-science/tools-and-environments.md): Claude writes and runs Python, R, and shell commands.
- [What's not available yet](https://claude.com/docs/claude-science/whats-not-available-yet.md): Claude Science is in beta, and some admin controls you use with other Claude products don't govern it yet.
- [Give Claude access to your tools](https://claude.com/docs/claude-tag/admins/add-connections.md): An Access bundle bundles the credentials Claude Tag acts with. See how to create the dedicated service accounts, what to connect first, and how allowed websites limit reach.
- [Configure per-channel access](https://claude.com/docs/claude-tag/admins/attach-to-scope.md): Choose which Slack channels and workspaces a set of Claude Tag credentials applies to. Covers inheritance, overlap rules, and adding channels after setup.
- [Review what Claude Tag has done](https://claude.com/docs/claude-tag/admins/audit.md): Claude Tag actions appear under its own service accounts in each connected tool's audit log. See what the Audit page covers, how to trace an action to its source, and where each connected tool keeps logs.
- [Configure GitHub access](https://claude.com/docs/claude-tag/admins/configure-github.md): Claude Tag gives Claude its own GitHub identity, so it opens pull requests as Claude. See how to link your GitHub organization, grant repositories to a bundle, what loads when a repository is cloned into a session, how to get project dependencies installed, and what Claude can do with GitHub Actions…
- [Connect Asana](https://claude.com/docs/claude-tag/admins/connections/asana.md): Connect Asana to Claude Tag so it can file tasks and read project status. Covers the dedicated account to create, the token fields, and the URL to allow.
- [Connect Jira and Confluence](https://claude.com/docs/claude-tag/admins/connections/atlassian.md): Connect Atlassian Cloud to Claude Tag so it can read and update Jira issues and search Confluence pages. Covers creating an API token, which credential type to pick, and the host to allow.
- [Connect BigQuery](https://claude.com/docs/claude-tag/admins/connections/bigquery.md): Connect BigQuery to Claude Tag so it can run read-only queries on your datasets. BigQuery has no preset, so it is added as a custom credential with a GCP service-account key.
- [Connect a service that isn't in the list](https://claude.com/docs/claude-tag/admins/connections/custom.md): Connect a tool that has no built-in preset to Claude Tag. Covers credential types, what each form field means, and how to add a custom MCP server.
- [Connect Datadog](https://claude.com/docs/claude-tag/admins/connections/datadog.md): Connect Datadog to Claude Tag so it can query metrics, logs, and monitors. Covers the dedicated account to create, the API key fields, and the URL to allow.
- [Connect GitLab](https://claude.com/docs/claude-tag/admins/connections/gitlab.md): Connect GitLab to Claude Tag for repo access and merge-request comments. Covers token permissions, self-managed hostnames, and how it differs from GitHub.
- [Connect Gong](https://claude.com/docs/claude-tag/admins/connections/gong.md): Connect Gong to Claude Tag so it can pull call summaries and deal context. Covers the dedicated account to create, the token fields, and the URL to allow.
- [Connect Google Drive, Calendar, and Gmail](https://claude.com/docs/claude-tag/admins/connections/google.md): Connect Google Drive, Calendar, and Gmail to Claude Tag so it can read docs, sheets, events, and email. Covers OAuth setup, the service-account option, and what each grants.
- [Connect HubSpot](https://claude.com/docs/claude-tag/admins/connections/hubspot.md): Connect HubSpot to Claude Tag so it can read pipeline, deal, and contact data. Covers the dedicated account to create, the token fields, and the URL to allow.
- [Connect Linear](https://claude.com/docs/claude-tag/admins/connections/linear.md): Connect Linear to Claude Tag so it can file tickets and post status updates. Covers the dedicated account to create, the token fields, and the URL to allow.
- [Connect Notion](https://claude.com/docs/claude-tag/admins/connections/notion.md): Connect Notion to Claude Tag so it can read and search your Notion workspace. Covers the dedicated account to create, the token fields, and the URL to allow.
- [Per-service connection guides](https://claude.com/docs/claude-tag/admins/connections/overview.md): Step-by-step setup for each tool Claude Tag can connect to. Each guide covers the dedicated account to create, the credential to enter, and the URL to allow.
- [Connect PagerDuty](https://claude.com/docs/claude-tag/admins/connections/pagerduty.md): Connect PagerDuty to Claude Tag so it can read incidents and on-call schedules. Covers the dedicated account to create, the token fields, and the URL to allow.
- [Connect Salesforce](https://claude.com/docs/claude-tag/admins/connections/salesforce.md): Connect Salesforce to Claude Tag so it can read and update CRM records. Covers External Client App setup and the OAuth JWT bearer flow Salesforce requires.
- [Connect Sentry](https://claude.com/docs/claude-tag/admins/connections/sentry.md): Connect Sentry to Claude Tag so it can pull errors and stack traces into threads. Covers the dedicated account to create, the token fields, and the URL to allow.
- [Connect Snowflake](https://claude.com/docs/claude-tag/admins/connections/snowflake.md): Connect Snowflake to Claude Tag so it can run read-only queries on your warehouse. Snowflake has no preset, so it is added as a custom credential.
- [Connect Stripe](https://claude.com/docs/claude-tag/admins/connections/stripe.md): Connect Stripe to Claude Tag so it can answer billing and subscription questions. Covers the dedicated account to create, the key fields, and the URL to allow.
- [Connect Vercel](https://claude.com/docs/claude-tag/admins/connections/vercel.md): Connect Vercel to Claude Tag so it can check deployment status and logs. Covers the dedicated account to create, the token fields, and the URL to allow.
- [Customize Claude Tag](https://claude.com/docs/claude-tag/admins/customize.md): Claude Tag is customized per channel and workspace (a scope), not per user. See what admins set in claude.ai, what anyone can change from the channel, and what stays fixed.
- [What the Claude Slack app can access](https://claude.com/docs/claude-tag/admins/for-slack-admins.md): What the Claude app reads and posts in Slack, the OAuth scopes it requests, and what installing it does not grant. Written for the Slack admin approving the install.
- [Migrate from the earlier Claude in Slack](https://claude.com/docs/claude-tag/admins/migrate-from-earlier.md): Claude Tag replaces the earlier per-user Claude in Slack app in place. See what changes, what stays, how the version is chosen per channel, and what existing users notice.
- [Network requirements](https://claude.com/docs/claude-tag/admins/network-requirements.md): Claude Tag reaches your services from a published egress range, over HTTP and HTTPS only. See the IP block to allowlist and how the allowlist relates to the allowed-websites setting on a connection.
- [Pair your Slack workspace](https://claude.com/docs/claude-tag/admins/pair-workspace.md): Connect your Slack workspace to your Claude organization. See what to send your Slack admin, where to paste the pairing code, and whether to enable the whole workspace or specific channels first.
- [Restrict where Claude Tag operates](https://claude.com/docs/claude-tag/admins/restrict-access.md): Claude Tag responds only where it has been added and addressed. See who can invoke it, guest and externally shared channel limits, the per-scope version setting, and how to quiet or remove it.
- [Set a spend limit](https://claude.com/docs/claude-tag/admins/set-spend-limit.md): Claude Tag draws from your organization's usage balance, not individual seats. See whether you need to fund usage, how to set the spend limit, and what happens when it's reached.
- [Set up Claude Tag](https://claude.com/docs/claude-tag/admins/setup-overview.md): Set up Claude Tag for your organization: pair your Slack workspace, give Claude access to your tools, set a spending limit, and launch. See prerequisites and each step in detail.
- [Set up a skills repository Claude can update](https://claude.com/docs/claude-tag/admins/skills-repo.md): Put your org's Claude Tag skills in a git repository with auto-sync, grant Claude write access, and Claude can open pull requests to improve its own skills from what it learns in channels.
- [See Claude Tag work](https://claude.com/docs/claude-tag/admins/test-it.md): Run Claude Tag's first tasks in a pilot channel before any connection exists. See copy-paste prompts that run on Slack content alone, per-connection checks, and what to do if a step fails.
- [Troubleshoot Claude Tag setup](https://claude.com/docs/claude-tag/admins/troubleshooting.md): Error messages from Claude Tag setup and what fixes each. Covers permission mismatches, GitHub access gaps, session start failures, and account errors.
- [Manage workspaces and versions](https://claude.com/docs/claude-tag/admins/workspaces.md): Connect more Slack workspaces or an Enterprise Grid to Claude Tag, choose which Claude version each channel uses, and disconnect a workspace.
- [How agent identity works](https://claude.com/docs/claude-tag/concepts/agent-identity.md): Claude Tag acts under its own service accounts in Slack channels, not as you. See how channel access is bounded, how credentials reach it, and why DMs differ.
- [Glossary](https://claude.com/docs/claude-tag/concepts/glossary.md): Claude Tag terms defined in one place. See agent identity, Access bundle, connection, scope, Agent Proxy, routine, channel memory, environment, and session.
- [How Claude Tag works](https://claude.com/docs/claude-tag/concepts/how-it-works.md): Each Claude Tag thread in Slack runs a working session in a sandbox. See how progress shows in the thread, how to steer mid-task, what survives between turns, and how memory is scoped.
- [Security and data handling](https://claude.com/docs/claude-tag/concepts/security-and-data.md): Claude Tag runs in an isolated sandbox where outbound traffic is default-deny and reaches only allowed hosts. Covers sandbox isolation, credential storage, network egress, service accounts, and which members can invoke Claude.
- [Work with Claude Tag](https://claude.com/docs/claude-tag/overview.md): Claude Tag puts Claude in your Slack channels with admin-governed access. See what to hand it, how setup works, and where to start as an admin or end user.
- [Get started](https://claude.com/docs/claude-tag/users/getting-started.md): Claude Tag works in your Slack channels. See how to check it's on, send your first message, what it can read, and why DMs work differently.
- [Good habits for working with Claude Tag](https://claude.com/docs/claude-tag/users/good-habits.md): Name the outcome, give every task a definition of done, and pick the right channel. See how to write tasks Claude can finish and how to keep many threads reviewable.
- [What Claude Tag remembers](https://claude.com/docs/claude-tag/users/memory.md): Claude Tag memory belongs to the channel, not to you. See how public channels share workspace memory, why private channels stay isolated, and how to check or correct it.
- [Choose the model Claude Tag uses](https://claude.com/docs/claude-tag/users/models.md): Ask Claude to switch models in a Slack thread, set a channel's default model, or pick the model for your direct messages. See which models you can use and how to confirm which one replied.
- [Set up routines](https://claude.com/docs/claude-tag/users/proactivity.md): Claude Tag runs routines you set up from the channel. See scheduled jobs, channel watching, pull request subscriptions, paste-ready routine recipes, and how to list or pause standing work.
- [Prompt library](https://claude.com/docs/claude-tag/users/prompt-library.md): Copy-paste prompts for Claude Tag in Slack, each with why it works. See first messages, channel-behavior asks, memory checks, routine setup, and mid-thread steering.
- [Troubleshoot Claude Tag in channels and DMs](https://claude.com/docs/claude-tag/users/troubleshooting.md): Fixes for common Claude Tag problems in Slack. See no reply after a reaction, queued or failed sessions, lost work, missing connections, blocked links and websites, and DM or account errors.
- [Use case library](https://claude.com/docs/claude-tag/users/use-cases.md): Shapes of work teams hand Claude Tag in Slack, each with prompts to paste. See triage, catch-up, docs and tickets, project tracking, data, deals, monitoring, and bug fixes.
- [Answer data questions](https://claude.com/docs/claude-tag/users/use-cases/answer-data-questions.md): Claude Tag answers data questions in the Slack thread. See warehouse queries with charts, scheduled metric reports, and charts built from channel history alone.
- [Catch up](https://claude.com/docs/claude-tag/users/use-cases/catch-up.md): Claude Tag summarizes Slack threads and channels on demand. See one-off recaps, a scheduled morning rollup of open threads, and what's waiting on you.
- [Turn threads into docs and tickets](https://claude.com/docs/claude-tag/users/use-cases/create-artifacts.md): Claude Tag turns a Slack discussion into the artifact you name. See replies you can send, decision docs, status memos, filed tickets, and a capture-channel pattern.
- [Find answers in your docs](https://claude.com/docs/claude-tag/users/use-cases/find-answers.md): Claude Tag finds answers in connected docs and replies in the thread. See policy lookups, runbook checks, prior decisions, and answers from the Slack channel alone.
- [Fix bugs](https://claude.com/docs/claude-tag/users/use-cases/fix-bugs.md): Claude Tag takes a bug report from Slack to a draft pull request. See reproducing the issue, watching a bug channel, root-cause digs, and following CI to green.
- [Claude Tag for marketing teams](https://claude.com/docs/claude-tag/users/use-cases/marketing-team.md): Claude Tag recipes for marketing teams in Slack. See policy answers in an intake channel, campaign channel recaps and send-ready drafts, lead and campaign state from the CRM, a weekly metrics digest, and brand voice rules saved to channel memory.
- [Pull deal and account state](https://claude.com/docs/claude-tag/users/use-cases/pull-deal-state.md): Claude Tag pulls account and deal state into the Slack channel. See in-thread account answers, pre-call briefs, and a scheduled weekly pipeline digest.
- [Review documents against a checklist](https://claude.com/docs/claude-tag/users/use-cases/review-documents.md): Claude Tag reviews documents in a connected tool against a checklist or policy and posts findings in the thread. See single-document checks, batch reviews, filing lists, comparisons with past reviews, and a scheduled weekly sweep.
- [Track projects and chase approvals](https://claude.com/docs/claude-tag/users/use-cases/track-projects.md): Claude Tag posts project digests no one has to compile. See standing status updates and follow-ups on contracts, design reviews, and pull requests until they close.
- [Triage requests](https://claude.com/docs/claude-tag/users/use-cases/triage-requests.md): Claude Tag triages a Slack request channel with two setup messages. See in-thread answers, duplicate flags, owner routing, weekly theme rollups, and optional ticket filing.
- [Watch monitors and alerts](https://claude.com/docs/claude-tag/users/use-cases/watch-monitors.md): Claude Tag watches dashboards and alert channels so you see one line per issue. See scheduled checks, alert investigation before anyone asks, and the prompts to set both up.
- [Work with your GitHub repositories](https://claude.com/docs/claude-tag/users/use-cases/work-with-github.md): Claude Tag works with your GitHub repositories from Slack. See repository questions answered in-thread, pull request subscriptions, chores handed back as draft pull requests, bug triage, and CLAUDE.md repository instructions.
- [Work from your own channel](https://claude.com/docs/claude-tag/users/use-cases/your-own-channel.md): Create a Slack channel for you and Claude Tag alone and run your work from it. See scratch questions, digests of channels you don't follow, a weekly status digest, follow-ups chased until they close, and a handoff that covers your time away.
- [Control when Claude Tag responds](https://claude.com/docs/claude-tag/users/when-claude-responds.md): Claude Tag replies to DMs, threads it's already in, and channel messages it judges warrant a reply, all without an @-mention. See what triggers a response, how to tell an unprompted reply from a task reply, how to quiet a thread or channel, when Claude quiets itself, how to remove Claude from a chan…
- [Manage your listing after publishing](https://claude.com/docs/connectors/building/after-publishing.md): Update your MCP server, plugin, and directory listing after publication
- [Authentication for connectors](https://claude.com/docs/connectors/building/authentication.md): OAuth and authentication options for MCP servers in Claude
- [Directory connectors vs custom connectors](https://claude.com/docs/connectors/building/directory-vs-custom.md): Understand the difference between directory-listed and custom connectors
- [Enterprise Managed Auth for connectors](https://claude.com/docs/connectors/building/enterprise-managed-auth.md): Accept identity assertions from enterprise SSO so users connect to your MCP server without a separate OAuth consent step.
- [Building custom connectors](https://claude.com/docs/connectors/building/index.md): Build your own MCP servers to connect Claude to your tools and data
- [Lazy authentication for MCP servers](https://claude.com/docs/connectors/building/lazy-authentication.md): Let users call public tools immediately and defer OAuth until a protected tool is actually invoked.
- [Managing your directory listing](https://claude.com/docs/connectors/building/managing-your-listing.md): Track submissions, monitor server health and usage metrics, and edit your Connectors Directory listing
- [Model Context Protocol (MCP)](https://claude.com/docs/connectors/building/mcp.md): Understanding the open standard powering Claude's connectors
- [Building cross-platform MCP Apps](https://claude.com/docs/connectors/building/mcp-apps/cross-compatibility.md): Build MCP Apps that work with both Claude and ChatGPT using a single codebase
- [Design guidelines](https://claude.com/docs/connectors/building/mcp-apps/design-guidelines.md): Visual and interaction design guidelines for MCP Apps in Claude
- [Opening external links from MCP Apps](https://claude.com/docs/connectors/building/mcp-apps/external-links.md): How Claude handles ui/open-link requests, and how directory connectors can allowlist destinations to skip the confirmation modal
- [Get started with MCP Apps](https://claude.com/docs/connectors/building/mcp-apps/getting-started.md): Learn how to test MCP Apps in Claude
- [Supersede older widget instances](https://claude.com/docs/connectors/building/mcp-apps/instance-supersession.md): Keep only the newest copy of a widget active when its tool is called more than once in a conversation
- [Blend your MCP App with Claude's theme](https://claude.com/docs/connectors/building/mcp-apps/transparent-theming.md): Make your widget background transparent and style it with Claude's style variables
- [Troubleshooting MCP Apps](https://claude.com/docs/connectors/building/mcp-apps/troubleshooting.md): Debug and resolve common issues with MCP Apps
- [Build a desktop extension with MCPB](https://claude.com/docs/connectors/building/mcpb.md): Package a local MCP server as a single-click .mcpb install for Claude Desktop
- [Pre-submission checklist](https://claude.com/docs/connectors/building/review-criteria.md): What Anthropic reviewers test, so you can pass on the first try
- [Submitting to the Connectors Directory](https://claude.com/docs/connectors/building/submission.md): Submit your MCP connector to the Connectors Directory
- [Testing your connector](https://claude.com/docs/connectors/building/testing.md): Test your MCP server against Claude before submitting to the directory
- [Troubleshooting connectors](https://claude.com/docs/connectors/building/troubleshooting.md): Diagnose and resolve common connection failures for custom and directory MCP connectors
- [What should I build: MCP, plugin, or both?](https://claude.com/docs/connectors/building/what-to-build.md): Decide between an MCP server, a plugin, or both for your Claude integration
- [Desktop extensions](https://claude.com/docs/connectors/custom/desktop-extensions.md): Deploy enterprise-grade MCP servers with MCPB
- [Third party connectors with remote MCP](https://claude.com/docs/connectors/custom/remote-mcp.md): Connect Claude to your tools using the Model Context Protocol
- [Connectors directory](https://claude.com/docs/connectors/directory.md): Browse verified and community MCP integrations for Claude
- [Get started with connectors](https://claude.com/docs/connectors/getting-started.md): Learn to connect Claude to your tools and data
- [GitHub integration](https://claude.com/docs/connectors/github/index.md): Connect your code repositories to Claude
- [Google Calendar integration](https://claude.com/docs/connectors/google/calendar.md): Access your calendar and meeting information with Claude
- [Google Drive integration](https://claude.com/docs/connectors/google/drive.md): Connect Google Docs directly to Claude
- [Gmail integration](https://claude.com/docs/connectors/google/gmail.md): Search and analyze emails with Claude
- [Microsoft 365 connector](https://claude.com/docs/connectors/microsoft/365.md): Connect SharePoint, OneDrive, Outlook, and Teams to Claude
- [Connectors overview](https://claude.com/docs/connectors/overview.md): Connect Claude to external tools, data, and UI through MCP
- [Slack integration](https://claude.com/docs/connectors/slack/index.md): Use Claude directly in Slack and connect your workspace
- [Connector verification](https://claude.com/docs/connectors/verification.md): How Anthropic reviews connectors, and what Verified, Community, and Custom mean
- [Changelog](https://claude.com/docs/cowork/changelog.md): Release notes for Claude Desktop
- [Run tasks in the background with Dispatch](https://claude.com/docs/cowork/guide/dispatch.md): Assign work to a Dispatch agent that plans, runs, and reports on tasks while you do something else, on this computer or from your phone.
- [Install plugins](https://claude.com/docs/cowork/guide/plugins.md): Add packaged skills, connectors, and agents to Cowork from the plugin marketplace or a file.
- [Organize work with projects](https://claude.com/docs/cowork/guide/projects.md): Group folders, instructions, and context into a Cowork project so Claude starts each session with the right setup.
- [Monitoring](https://claude.com/docs/cowork/monitoring.md): Track Cowork usage and activity across your organization with OpenTelemetry
- [Overview](https://claude.com/docs/cowork/overview.md): Learn about Cowork, Anthropic's agentic workspace
- [Your account](https://claude.com/docs/government/account/overview.md): Check your own account details, usage limits, and active sessions.
- [Account](https://claude.com/docs/government/account/profile.md): Use this page to confirm that you are signed in as the right person and to see what access you have been given.
- [Sessions](https://claude.com/docs/government/account/sessions.md): Use this page to see every place you are currently signed in to Claude for Government and to sign out of any of them remotely.
- [Usage](https://claude.com/docs/government/account/usage.md): Use this page to see how much of your Claude allowance you have used and when it refreshes.
- [Analytics](https://claude.com/docs/government/org-admin/analytics.md): Use this page to review requests, tokens, spend, top users, and credit balance over time across your organization.
- [Billing](https://claude.com/docs/government/org-admin/billing.md): Use this page to check your account's credit balance and seat pool, distribute credits to your organization, and adjust how many seats your organization holds.
- [Config](https://claude.com/docs/government/org-admin/configuration.md): Use this page to view and change the product settings that apply to everyone in your organization, and to see where each effective value comes from.
- [Organization administration](https://claude.com/docs/government/org-admin/overview.md): Manage the people, seats, and settings for a single organization within your agency.
- [Group mappings](https://claude.com/docs/government/org-admin/provisioning.md): Use this page to map the groups pushed from your identity provider to seat tiers and roles in this organization.
- [Readiness](https://claude.com/docs/government/org-admin/readiness.md): Use this page to see everything that is stopping people in your organization from using Claude, and where each blocker is resolved.
- [Seat tiers](https://claude.com/docs/government/org-admin/seat-tiers.md): Use this page to see the models and spend limits attached to each tier and, when permitted, to create and edit self-managed tiers.
- [Seats](https://claude.com/docs/government/org-admin/seats.md): Use this page to check your organization's seat counts at a glance before assigning or reclaiming seats on the Users page.
- [Setup wizard](https://claude.com/docs/government/org-admin/setup-wizard.md): Walk through the steps that get your organization ready for users after a tenant administrator creates it.
- [Users](https://claude.com/docs/government/org-admin/users.md): Use this page to find a user, change their role or seat tier, check how close they are to their usage limits, and reset those limits when needed.
- [Claude for Government administrator guide](https://claude.com/docs/government/overview.md): Set up and manage Claude for Government for your agency: how tenants, organizations, users, seats, and credits fit together.
- [Admins](https://claude.com/docs/government/tenant-admin/admins.md): Use this page to view, add, and remove the people who can use the tenant admin portal.
- [Config](https://claude.com/docs/government/tenant-admin/configuration.md): Set tenant-wide defaults for product behavior, lock settings so organizations can't override them, and preview how a change affects each organization.
- [Billing](https://claude.com/docs/government/tenant-admin/credits.md): Use this page to move credit from your billing accounts onto the balances of the organizations they fund.
- [Identity and access](https://claude.com/docs/government/tenant-admin/identity-and-access.md): Connect single sign-on, manage SCIM provisioning, and write the routing rules that place users into organizations.
- [Organizations](https://claude.com/docs/government/tenant-admin/organizations.md): Use this page to see every organization in your tenant, open any organization's admin view, and create new organizations.
- [Tenant administration](https://claude.com/docs/government/tenant-admin/overview.md): Manage the settings that apply across your whole agency: organizations, identity and sign-in, and how seats and credits are distributed.
- [Readiness](https://claude.com/docs/government/tenant-admin/readiness.md): Use this page to see everything that is blocking your organizations from using Claude, and to find the one place where each blocker is resolved.
- [Seats](https://claude.com/docs/government/tenant-admin/seats.md): Use this page to divide each billing account's seat pool among the organizations that account funds.
- [Tenant setup wizard](https://claude.com/docs/government/tenant-admin/setup-wizard.md): Walk through the guided setup that takes a brand new tenant from first sign-in to ready for users.
- [Get started building with Claude.ai](https://claude.com/docs/index.md): Get started building with Connectors, Plugins, and other Claude.ai features.
- [Connectors and Skills](https://claude.com/docs/office-agents/connectors-and-skills.md): Extend Claude for Excel, PowerPoint, Word, and Outlook with external context and reusable task recipes.
- [Use dictation in Claude for M365](https://claude.com/docs/office-agents/dictation.md): Speak your prompts instead of typing them in Claude for Excel, PowerPoint, Word, and Outlook.
- [Security, admin auditability, and analytics](https://claude.com/docs/office-agents/enterprise-readiness.md): Security architecture diagrams, OpenTelemetry audit, usage analytics, and spend tracking for enterprise admins deploying Claude for M365.
- [Use Claude for Excel](https://claude.com/docs/office-agents/excel.md): An Excel add-in that integrates Claude into your spreadsheet workflow, for Pro, Max, Team, and Enterprise plans.
- [Install financial services plugins for Cowork](https://claude.com/docs/office-agents/fsi-plugins.md): Add the open-source financial services plugin set to Cowork for financial modeling, equity research, investment banking, private equity, and wealth management workflows.
- [Use Claude for Outlook](https://claude.com/docs/office-agents/outlook.md): An Outlook add-in that integrates Claude into your inbox and calendar, for Pro, Max, Team, and Enterprise plans.
- [Claude for M365 overview](https://claude.com/docs/office-agents/overview.md): Claude for Excel, PowerPoint, Word, and Outlook.
- [Use Claude for PowerPoint](https://claude.com/docs/office-agents/powerpoint.md): A PowerPoint add-in that integrates Claude into your presentation workflow, for Pro, Max, Team, and Enterprise plans.
- [Use Claude for M365 with third-party platforms](https://claude.com/docs/office-agents/third-party-platforms.md): Deploy the Office add-ins through Amazon Bedrock, Google Cloud Vertex AI, Azure AI Foundry, or an LLM gateway, without individual Claude accounts.
- [Use Claude for Word](https://claude.com/docs/office-agents/word.md): A Word add-in that integrates Claude into your document workflow, for Pro, Max, Team, and Enterprise plans.
- [Work across M365 apps](https://claude.com/docs/office-agents/work-across-apps.md): Let Claude read from one Microsoft 365 app and make changes in another in a single conversation.
- [Plugins overview](https://claude.com/docs/plugins/overview.md): Extend Claude with reusable capability packages that bundle MCP connectors, skills, slash commands, and sub-agents
- [Submitting your plugin](https://claude.com/docs/plugins/submit.md): Submit your plugin to the plugin directory for Cowork
- [Creating custom skills](https://claude.com/docs/skills/how-to.md): Learn how to create, structure, and test your own custom skills
- [Skills overview](https://claude.com/docs/skills/overview.md): Extend Claude's capabilities with specialized instructions and workflows
- [Deploy Claude Desktop on 3P with Amazon Bedrock](https://claude.com/docs/third-party/claude-desktop/bedrock.md): Set up AWS, choose an authentication path for your organization, and configure Claude Desktop on 3P to use Claude models on Amazon Bedrock
- [Deploy with a bootstrap server](https://claude.com/docs/third-party/claude-desktop/bootstrap.md): Host an HTTPS endpoint that returns each user's configuration, for organizations without MDM or with role-based configuration too complex for per-group profiles
- [Using Claude Desktop on 3P with the Claude API](https://claude.com/docs/third-party/claude-desktop/claude-api.md): Configure Claude Desktop on 3P to send inference directly to Anthropic's Claude API instead of a cloud-provider-hosted Claude deployment
- [Code tab](https://claude.com/docs/third-party/claude-desktop/code.md): How Claude Desktop on 3P configuration applies to the embedded Claude Code engine
- [Configuration reference](https://claude.com/docs/third-party/claude-desktop/configuration.md): Every managed-configuration key Claude Desktop on 3P supports, what it controls, and recommended security profiles
- [Configuration changelog](https://claude.com/docs/third-party/claude-desktop/configuration-changelog.md): Managed configuration keys by the Claude Desktop release they first shipped in
- [Connect to Microsoft 365](https://claude.com/docs/third-party/claude-desktop/connectors-m365.md): Give Claude access to your organization's Outlook, OneDrive, SharePoint, and Teams data through a connector you register in your own Microsoft Entra tenant.
- [Write a credential helper](https://claude.com/docs/third-party/claude-desktop/credential-helper.md): Supply Claude Desktop on 3P with a short-lived inference token by running an executable you provide
- [User identity and local data](https://claude.com/docs/third-party/claude-desktop/data-storage.md): How Claude Desktop on 3P identifies users and where it stores conversations, settings, and credentials on disk
- [MCP, plugins, skills, and hooks](https://claude.com/docs/third-party/claude-desktop/extensions.md): Extend Claude Desktop on 3P with connectors, plugin marketplaces, organization plugins, skills, and hooks for administrators and end users
- [Features](https://claude.com/docs/third-party/claude-desktop/feature-matrix.md): Feature comparison between Claude Enterprise and Claude Desktop on third-party (3P)
- [Deploy Claude Desktop on 3P with Microsoft Foundry](https://claude.com/docs/third-party/claude-desktop/foundry.md): Set up Microsoft Foundry, choose an authentication path for your organization, and configure Claude Desktop on 3P to use Claude models on Microsoft Foundry
- [Using Claude Desktop on 3P with an LLM Gateway](https://claude.com/docs/third-party/claude-desktop/gateway.md): Configure Claude Desktop on 3P to use Claude models on a self-hosted gateway that implements the Anthropic Messages API
- [In-app configuration](https://claude.com/docs/third-party/claude-desktop/in-app-configuration.md): Build, test, and export a Claude Desktop on 3P configuration from inside the app, with validation and per-provider guidance
- [Installation and setup](https://claude.com/docs/third-party/claude-desktop/installation.md): Install Claude Desktop on 3P, check device readiness, and choose how configuration reaches your devices: an MDM profile or a bootstrap server
- [Legal and compliance](https://claude.com/docs/third-party/claude-desktop/legal.md): Legal agreements, compliance, and security information for Claude Desktop on 3P
- [Desktop and filesystem access](https://claude.com/docs/third-party/claude-desktop/local-access.md): How Claude Desktop on 3P reads and writes files on the user's machine, and how to constrain it
- [Deploy Claude Desktop on 3P with Amazon Bedrock Mantle](https://claude.com/docs/third-party/claude-desktop/mantle.md): Configure Claude Desktop on 3P to use Claude models through Amazon Bedrock Mantle's Anthropic-native API surface
- [Deploy with MDM](https://claude.com/docs/third-party/claude-desktop/mdm.md): Author a full configuration in the app, export it as a profile, and deploy it fleet-wide with Jamf, Intune, Group Policy, or any MDM
- [Overview](https://claude.com/docs/third-party/claude-desktop/overview.md): Run Claude Desktop against your own cloud inference provider
- [Telemetry and egress](https://claude.com/docs/third-party/claude-desktop/telemetry.md): What Claude Desktop on 3P sends to Anthropic, how to disable it, and the network paths your firewall needs to allow
- [Deploy Claude Desktop on 3P with Google Cloud's Agent Platform](https://claude.com/docs/third-party/claude-desktop/vertex.md): Set up Google Cloud, choose an authentication path for your organization, and configure Claude Desktop on 3P to use Claude models on Google Cloud's Agent Platform
- [Web search and web fetch](https://claude.com/docs/third-party/claude-desktop/web-tools.md): How Claude Desktop on 3P reaches the internet, which providers support search, and how to control or disable web access