1,063 pages for prompt.

Security, admin auditability, and analytics Claude Documentation · in the page office-agents/enterprise-readiness …The Trust Center publishes architecture diagrams that show how user prompts, document content, and responses flow between the Office add-ins, Claude, and your infrastructure. Review the diagram that… Use Claude for Excel Claude Documentation · in the page office-agents/excel …citations you can click to navigate to the referenced cell. Example prompts: * "Walk me through how the revenue number in cell C42 is calculated." * "What assumptions drive the gross margin forecas… Configure a custom OpenTelemetry collector Claude Documentation · in the page office-agents/opentelemetry …ry collector > Route the full Claude for M365 audit trail, including prompts, tool inputs and outputs, and document references, to an OpenTelemetry collector you operate. Route complete audit teleme… Use Claude for Outlook Claude Documentation · in the page office-agents/outlook …consent](#grant-microsoft-graph-consent) step below so users are not prompted individually. > [!NOTE] > > If your organization uses Microsoft Entra Privileged Identity > Management (PIM) for admin r… Claude for M365 overview Claude Documentation · in the page office-agents/overview …Dictation](https://claude.com/docs/office-agents/dictation.md): speak prompts instead of typing them. ## Deployment These pages cover enterprise admin setup and observability. * [Use Claude for M… Use Claude for PowerPoint Claude Documentation · in the page office-agents/powerpoint …eads your deck's template and respects its formatting rules. Example prompts: * "Create a market sizing section, 3 slides covering TAM, SAM, SOM with supporting visuals." * "Add an executive summa… Use Claude for M365 with third-party platforms Claude Documentation · in the page office-agents/third-party-platforms …The add-in connects through your organization's infrastructure, sends prompts to the provider your organization chooses, and receives Claude's responses from it. See [What Anthropic collects](#what-an… Use Claude for Word Claude Documentation · in the page office-agents/word …specific requirements and > your firm's standard positions. Example prompts: * "What's the liability cap and is it mutual?" * "Summarize the key commercial terms in this agreement." * "What assumpt… Plugin structure and testing Claude Documentation · in the page plugins/build …ch as language servers, executables in `bin/`, per-user configuration prompts, output styles, and dependencies between plugins. A plugin that includes them still installs on claude.ai and in Cowork, e… Plugin feature support across platforms Claude Documentation · in the page plugins/platform-support …nce | Ignored when a referenced option has no default; Cowork doesn't prompt for values | Loads; prompts you for the values | [User configuration](https://code.claude.com/docs/en/plugins/components#us… Plugin pre-submission checklist Claude Documentation · in the page plugins/pre-submission-checklist …output with and without the plugin** Run the plugin's skills on real prompts and compare the output with what Claude produces without the plugin. [`claude plugin eval`](https://code.claude.com/docs/e… Create custom skills Claude Documentation · in the page skills/how-to …lls) in claude.ai or the desktop app and turn the skill on. **2. Try prompts that should trigger it** Send prompts that should trigger the skill, and review Claude's thinking to confirm it's loading… Deploy with Enterprise Admin Console Claude Documentation · in the page third-party/claude-desktop/admin-console …s that apply to them and sends every model request to your provider. Prompts, responses, and files go to your inference provider, as they do with MDM or a bootstrap server. Anthropic holds your user… Deploy Claude Desktop on 3P with Amazon Bedrock Claude Documentation · in the page third-party/claude-desktop/bedrock …ys a short verification code so the user can confirm that the browser prompt matches the app that requested it. Identity Center redirects the user to whichever identity provider you have configured (E… Deploy with a bootstrap server Claude Documentation · in the page third-party/claude-desktop/bootstrap …starts in a degraded state with no inference provider configured and prompts the user to sign in. ### Availability The full response is held **in memory only**. If your bootstrap server is unreacha… Built-in browser and Claude in Chrome Claude Documentation · in the page third-party/claude-desktop/browser …mp of the request, and their OS/Chrome version. No URL, page content, prompt content, or anything else about the request is stored. For the built-in browser, the account ID is empty unless your organi… Chat in Claude Desktop on 3P Claude Documentation · in the page third-party/claude-desktop/chat …NING] > > By default, commands in the sandbox run without an approval prompt. A command can upload anything the sandbox can read to a listed host, and can run what it downloads from one. [Web fetch](h… Code in Claude Desktop on 3P Claude Documentation · in the page third-party/claude-desktop/code …| `organizationInstructions` | Appended to the Code session's system prompt after Claude Code's own. `CLAUDE.md` instructions still apply. | | `otlpEndpoint`, `otlpProtocol`, `otlpHeaders`, `otlpReso… Configuration reference Claude Documentation · in the page third-party/claude-desktop/configuration …0`. Its standard output must hold only one of these, with no banners, prompts or log lines: > > * the token by itself > * `{"token": "...", "headers": {"Name": "Value"}}`, to also send headers with ea… Configuration changelog Claude Documentation · in the page third-party/claude-desktop/configuration-changelog …l whatever `toolPolicy` says, and is refused where Claude can show no prompt. `toolPolicy` can still block it. The connector is updated to github-mcp-server v2.0.2, whose new tools that make changes a… Configuration implementation Claude Documentation · in the page third-party/claude-desktop/configuration-format …checkintervalminutes), 10 minutes by default) and, for most settings, prompts the user to restart and requires the restart after [`relaunchEnforcementHours`](https://claude.com/docs/third-party/claude… Connect to Microsoft 365 Claude Documentation · in the page third-party/claude-desktop/connectors-m365 …`offline_access` | Allow the desktop to refresh its token without re-prompting | The screen also lists the write permissions, such as `Mail.Send` and `Files.ReadWrite.All`. Accepting approves the wh… Write a credential helper Claude Documentation · in the page third-party/claude-desktop/credential-helper …. Stdout must contain exactly one of the following, with no banners, prompts, or log lines mixed in: * **A single bare token.** The whole trimmed stdout becomes the bearer token. * **A JSON object**… User identity and local data Claude Documentation · in the page third-party/claude-desktop/data-storage …of one Cowork session or Chat conversation. It holds the full text of prompts, Claude's responses, and tool inputs and results. See [Session audit log](#session-audit-log). | | `claude-code-sessions/`… Sign in through the OS identity broker Claude Documentation · in the page third-party/claude-desktop/entra-broker …t of compliance or the user's sessions are revoked in Entra), the app prompts the user to sign in again. ## Troubleshoot If sign-in fails with error code `AADSTS7000218`, **Allow public client flows… MCP, plugins, skills, and hooks Claude Documentation · in the page third-party/claude-desktop/extensions …fferences: a 30-second time limit, no `CLAUDE_HELPER_CONTEXT`, and no prompting for input. The helper applies only to servers provisioned through managed configuration and never replaces the `Authoriz… Features Claude Documentation · in the page third-party/claude-desktop/feature-matrix …metry-categories) to Anthropic by default. This telemetry contains no prompt or response content, and you can fully disable it via managed configuration. | > | Data handling | [Data handling](https://… Deploy Claude Desktop on 3P with Microsoft Foundry Claude Documentation · in the page third-party/claude-desktop/foundry …erated service on Azure infrastructure, not in your Azure tenant, and prompts and completions remain within Azure. The only data the service sends out of Azure to Anthropic is usage metadata and any c… Deploy Claude Desktop on 3P with an LLM gateway Claude Documentation · in the page third-party/claude-desktop/gateway …set `inferenceModels` explicitly. The gateway should also preserve [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching). Cowork and Code sessions send `cache_contro… Import history from claude.ai Claude Documentation · in the page third-party/claude-desktop/import …*Sign in to claude.ai…**. Your browser opens to claude.ai; sign in if prompted, choose your organization if you belong to more than one, and click **Authorize**. > > ), and prompts in the app if the host asks for a password or a one-time code. 2. **Deploy.** Claude Desktop places a remote server and th… Show a status line Claude Documentation · in the page third-party/claude-desktop/status-line …it in a dialog, unless the device [trusts the server's values without prompting](https://claude.com/docs/third-party/claude-desktop/bootstrap.md#keys-that-require-user-consent) If one configuration s… Telemetry and egress Claude Documentation · in the page third-party/claude-desktop/telemetry …data (app version, OS, error type, redacted stack frames) but **never prompt or response content**. Attributed to your organization via `deploymentOrganizationUuid` so Anthropic support can find issue… Deploy Claude Desktop on 3P with Google Cloud's Agent Platform Claude Documentation · in the page third-party/claude-desktop/vertex …res a refresh token that is subject to that policy, and users will be prompted to sign in again each time it expires. For short session policies, either mark your OAuth client as a [trusted app exempt… Web search and web fetch Claude Documentation · in the page third-party/claude-desktop/web-tools …] } ``` Set the per-entry `toolPolicy` to `"allow"` so users aren't prompted to approve each search in Cowork sessions and Chat conversations. For Code sessions, see [Tool permissions for managed MC… Contributing to MCP Model Context Protocol · in the page community/contributing …ge type, request/response structure, and primitive (tools, resources, prompts) that clients and servers exchange. SDK implementers across all languages rely on this schema to build conformant implemen… Design Principles Model Context Protocol · in the page community/design-principles …cificity MCP provides foundational primitives: resources, tools, and prompts. We don't add protocol features for use cases that can be constructed from these existing building blocks. This keeps the… SDK Tiering System Model Context Protocol · in the page community/sdk-tiers …ent, message exchange, or use of core primitives (tools, resources, prompts) Interceptors Charter Model Context Protocol · in the page community/working-groups/interceptors …ers MCP-defined operations such as tool invocations, resource access, prompt handling, sampling, and elicitation, as well as any other operation that shapes agent context — including LLM completions a… Progressive Disclosure Charter Model Context Protocol · in the page community/working-groups/progressive-disclosure …sclosure Working Group explores how MCP Primitives (Tools, Resources, Prompts, Tasks) might be organized, beyond the flat lists maintained by the protocol, and how such organization might benefit both… Transports Charter Model Context Protocol · in the page community/working-groups/transports …plication-layer behavior for MCP primitives such as tools, resources, prompts, tasks, agents, or events, including application state, application-session meaning, task lifecycle, and event or subs… Build an MCP client Model Context Protocol · in the page docs/2024-11-05/develop/build-client …Console.WriteLine("MCP Client Started!"); > Console.ResetColor(); > > PromptForInput(); > while(Console.ReadLine() is string query && !"exit".Equals(query, StringComparison.OrdinalIgnoreCase)) > { >… Build an MCP server Model Context Protocol · in the page docs/2024-11-05/develop/build-server …*: Functions that can be called by the LLM (with user approval) 3. **[Prompts](https://modelcontextprotocol.io/docs/2024-11-05/learn/server-concepts.md#prompts)**: Pre-written templates that help user… Build with Agent Skills Model Context Protocol · in the page docs/2024-11-05/develop/build-with-agent-skills …1-05/tools/inspector.md) > > Test your server's tools, resources, and prompts interactively > [card] [Connect to a client](https://modelcontextprotocol.io/docs/2024-11-05/develop/connect-local-server…