662 pages for credential.
Titles and paths first, then pages whose text carries it. Each row opens that page as this site last read it.
Plugin pre-submission checklist
Claude Documentation · in the page
plugins/pre-submission-checklist
…may use a custom registry or package source** when held | | Keep real credentials out of every file, documentation and examples included. Ask for each value through a `userConfig` entry in `plugin.jso…
Create custom skills
Claude Documentation · in the page
skills/how-to
…pprove more than you intend. Don't put API keys, passwords, or other credentials in a script or anywhere else in the skill: everyone you share the skill with receives its files. When a script needs t…
Deploy with Enterprise Admin Console
Claude Documentation · in the page
third-party/claude-desktop/admin-console
…session counts from your users' apps. Anthropic never holds provider credentials such as API keys or your users' tokens. For the full list of what Anthropic stores, see [Where your data goes](#where-…
Deploy Claude Desktop on 3P with Amazon Bedrock
Claude Documentation · in the page
third-party/claude-desktop/bedrock
…ur identity provider; the proxy calls Amazon Bedrock with its own AWS credentials. Requires app version 2.7032.0 or later. | | You already operate an LLM gateway (Anthropic Messages API) | [Gateway pr…
Deploy with a bootstrap server
Claude Documentation · in the page
third-party/claude-desktop/bootstrap
…figuration varies too widely for per-group profiles: per-user gateway credentials, per-team model allowlists, or per-user OpenTelemetry attribution. When one configuration or a few group-scoped profil…
Built-in connectors
Claude Documentation · in the page
third-party/claude-desktop/built-in-connectors
…e data path. * **Sign-in on the device.** Where the server needs user credentials (Microsoft 365 and GitHub), the user signs in from the app, and tokens are stored encrypted on the device. **Disconnec…
Deploy Claude Desktop on 3P with the Claude API
Claude Documentation · in the page
third-party/claude-desktop/claude-api
…on approach There are three options. With neither a static key nor a credential helper configured, each user sees **Sign in with Claude Console** on first launch: the app opens the browser, the user…
Code in Claude Desktop on 3P
Claude Documentation · in the page
third-party/claude-desktop/code
…t in Code sessions | | - | - | | `inferenceProvider` and all provider credential keys (`inferenceGateway*`, `inferenceAnthropicApiKey`, `inferenceVertex*`, `inferenceBedrock*`, `inferenceFoundry*`, `i…
Configuration reference
Claude Documentation · in the page
third-party/claude-desktop/configuration
…der) | Inference provider | Connection | Admin Console | | [`inferenceCredentialKind`](#inferencecredentialkind) | Credential kind | Connection | Self-hosted Admin Console | | [`inferenceSessionLifeti…
Configuration changelog
Claude Documentation · in the page
third-party/claude-desktop/configuration-changelog
…inal spelling): * `inferenceGatewayAuthScheme: "sso"`: use `inferenceCredentialKind: "interactive"` instead. If `inferenceCredentialKind` is not set, this release and later keep reading the original…
Configuration implementation
Claude Documentation · in the page
third-party/claude-desktop/configuration-format
…**Sign-in to the session host**: on a self-hosted install [`inferenceCredentialKind`](/docs/third-party/claude-desktop/configuration#inferencecredentialkind) names the device's sign-in to the host, n…
Connect to Box
Claude Documentation · in the page
third-party/claude-desktop/connectors-box
…ate the client in Box** In the Box Admin Console, create integration credentials for the Box MCP server as described in Box's [remote MCP server guide](https://developer.box.com/guides/box-mcp/remote…
Connect to GitHub
Claude Documentation · in the page
third-party/claude-desktop/connectors-github
…distribute | OAuth device flow; no tokens to issue or distribute | | Credential handling | Token delivered through the entry's `headers` or a headers helper script | User signs in; the token is acqui…
Connect to Google Cloud
Claude Documentation · in the page
third-party/claude-desktop/connectors-google-cloud
…sting, or Google blocks their sign-in. Then open **APIs & Services → Credentials**, choose **Create credentials → OAuth client ID**, and select **Desktop app** as the application type. When Google sh…
User identity and local data
Claude Documentation · in the page
third-party/claude-desktop/data-storage
…3P identifies users and where it stores conversations, settings, and credentials on disk Claude Desktop on third-party (3P) keeps conversations, settings, and credentials on the device. For [SSH rem…
Sign in through the OS identity broker
Claude Documentation · in the page
third-party/claude-desktop/entra-broker
…and Entra. ## Token storage The operating system's broker holds the credential and renews it silently from the device's primary refresh token. The app stores only a reference to the signed-in accoun…
MCP, plugins, skills, and hooks
Claude Documentation · in the page
third-party/claude-desktop/extensions
…tool list, or the error returned. Use it to validate reachability and credentials before exporting the configuration. Give each remote server's final address in `url`. Claude Desktop doesn't follow H…
Deploy Claude Desktop on 3P with Microsoft Foundry
Claude Documentation · in the page
third-party/claude-desktop/foundry
…our organization already has tooling that obtains a Microsoft Foundry credential | [Credential helper](/docs/third-party/claude-desktop/configuration.md#inferencecredentialhelper) (`inferenceCredentia…
Deploy Claude Desktop on 3P with an LLM gateway
Claude Documentation · in the page
third-party/claude-desktop/gateway
…der, set `inferenceProvider` to `gateway` and supply the base URL and credentials described below. The gateway must implement the Anthropic [Messages API](https://docs.claude.com/en/api/messages): *…
Installation and setup
Claude Documentation · in the page
third-party/claude-desktop/installation
…strap server when your organization doesn't use MDM, or when per-user credentials or frequently changing settings would make per-group profiles unwieldy. The tradeoff is that you operate the endpoint.…
Deploy Claude Desktop on 3P with Amazon Bedrock Mantle
Claude Documentation · in the page
third-party/claude-desktop/mantle
…ectly and authenticates with a bearer token rather than the AWS SigV4 credential chain, so no AWS CLI, named profile, or IAM Identity Center setup is needed on the device. In practice, Mantle is the A…
Deploy with MDM
Claude Documentation · in the page
third-party/claude-desktop/mdm
…Cloud's Agent Platform, Bedrock, Bedrock Mantle, or Foundry) and its credentials Model list Organization UUID Optional credential-helper script | | **Capabilities** | Which of Cowork, Code, and Chat…
Network proxy
Claude Documentation · in the page
third-party/claude-desktop/network-proxy
…fault behavior](#default-behavior). SOCKS URLs and URLs with embedded credentials (`user:password@`) are rejected. If you point the key at a local forwarding proxy on the device, give it as `http://1…
Overview
Claude Documentation · in the page
third-party/claude-desktop/overview
…aunch from the configured inference provider. When a provider and its credentials are present, the sign-in screen offers the option to skip Anthropic authentication and start the app using your infere…
SSH remote sessions in Claude Desktop on 3P
Claude Documentation · in the page
third-party/claude-desktop/ssh-remote-sessions
…op on 3P, the sshHostAllowlist key that enables them, which inference credentials work on a remote host, and what to check before turning them on An SSH remote session is a [Code](/docs/third-party/c…
Telemetry and egress
Claude Documentation · in the page
third-party/claude-desktop/telemetry
…ctor's own request logs to confirm data is arriving. For a collector credential that cannot be a static header, [`otlpHeadersHelper`](/docs/third-party/claude-desktop/configuration#otlpheadershelper)…
Deploy Claude Desktop on 3P with Google Cloud's Agent Platform
Claude Documentation · in the page
third-party/claude-desktop/vertex
…'s Agent Platform authenticates with Google Cloud Application Default Credentials, which can be supplied several ways. The right one depends on whether your users have Google identities and whether yo…
Web search and web fetch
Claude Documentation · in the page
third-party/claude-desktop/web-tools
…N object to stdout; it follows the same execution model as [`inferenceCredentialHelper`](/docs/third-party/claude-desktop/credential-helper) (exit 0, stdout read as JSON) but always runs with no argum…
Authorization Charter
Model Context Protocol · in the page
community/interest-groups/auth
…ch Authorization Requests, structured denials, remediation hints) * **Credentials for non-HTTP transports**: patterns for stdio, WebSocket, and future transports where the HTTP authorization spec does…
Enterprise Interest Group Charter
Model Context Protocol · in the page
community/interest-groups/enterprise
…IG** — Overlapping interest in runtime security, tool poisoning, and credential management. The Enterprise IG focuses on the organizational and governance dimensions; the Security IG focuses on threa…
Enterprise-Managed Authorization Charter
Model Context Protocol · in the page
community/interest-groups/enterprise-managed-authorization
…or PRs ### Out of Scope * **Other authorization profiles**: Client Credentials, DPoP, Workload Identity Federation, and the core OAuth 2.1 flow belong to the [Authorization IG](/community/interest-…
Infrastructure Charter
Model Context Protocol · in the page
community/working-groups/infrastructure
…DNS, and certificates. * **Supporting resources:** Compute, storage, credentials, and other infrastructure MCP needs now or adopts later. * **Maintenance:** Monitoring, upgrades, recovery, ownership…
Transports Charter
Model Context Protocol · in the page
community/working-groups/transports
…, mTLS, and certificate handling, coordinated with the Security IG. Credential carriage is coordinated with the Auth IG. * **Validation and Guidance**: Reference implementations, experiments, implem…
Client Best Practices
Model Context Protocol · in the page
docs/2024-11-05/develop/clients/client-best-practices
…call, and returns the result to the sandbox. Authorization tokens and credentials are held by the host and never exposed to the generated code. **The model** sees only what the sandbox returns, typic…
Debugging
Model Context Protocol · in the page
docs/2024-11-05/tools/debugging
…hen debugging: 1. **Sensitive Data** * Sanitize logs * Protect credentials * Mask personal information 2. **Access Control** * Verify permissions * Check authentication * Monitor a…
Understanding Authorization in MCP
Model Context Protocol · in the page
docs/2024-11-05/tutorials/security/authorization
…/2024-11-05/basic/transports.md#stdio), you can use environment-based credentials or credentials provided by third-party libraries embedded directly in the MCP server instead. Because a STDIO-built MC…
Security Best Practices
Model Context Protocol · in the page
docs/2024-11-05/tutorials/security/security_best_practices
…or traffic monitoring, that depend on the token audience or other credential constraints. If clients can obtain and use tokens directly with the downstream APIs without the MCP server vali…
Client Best Practices
Model Context Protocol · in the page
docs/2025-03-26/develop/clients/client-best-practices
…call, and returns the result to the sandbox. Authorization tokens and credentials are held by the host and never exposed to the generated code. **The model** sees only what the sandbox returns, typic…
Debugging
Model Context Protocol · in the page
docs/2025-03-26/tools/debugging
…hen debugging: 1. **Sensitive Data** * Sanitize logs * Protect credentials * Mask personal information 2. **Access Control** * Verify permissions * Check authentication * Monitor a…
Understanding Authorization in MCP
Model Context Protocol · in the page
docs/2025-03-26/tutorials/security/authorization
…/2025-03-26/basic/transports.md#stdio), you can use environment-based credentials or credentials provided by third-party libraries embedded directly in the MCP server instead. Because a STDIO-built MC…
Security Best Practices
Model Context Protocol · in the page
docs/2025-03-26/tutorials/security/security_best_practices
…or traffic monitoring, that depend on the token audience or other credential constraints. If clients can obtain and use tokens directly with the downstream APIs without the MCP server vali…
Client Best Practices
Model Context Protocol · in the page
docs/2025-06-18/develop/clients/client-best-practices
…call, and returns the result to the sandbox. Authorization tokens and credentials are held by the host and never exposed to the generated code. **The model** sees only what the sandbox returns, typic…
Debugging
Model Context Protocol · in the page
docs/2025-06-18/tools/debugging
…hen debugging: 1. **Sensitive Data** * Sanitize logs * Protect credentials * Mask personal information 2. **Access Control** * Verify permissions * Check authentication * Monitor a…
Understanding Authorization in MCP
Model Context Protocol · in the page
docs/2025-06-18/tutorials/security/authorization
…/2025-06-18/basic/transports.md#stdio), you can use environment-based credentials or credentials provided by third-party libraries embedded directly in the MCP server instead. Because a STDIO-built MC…
Security Best Practices
Model Context Protocol · in the page
docs/2025-06-18/tutorials/security/security_best_practices
…or traffic monitoring, that depend on the token audience or other credential constraints. If clients can obtain and use tokens directly with the downstream APIs without the MCP server vali…
Client Best Practices
Model Context Protocol · in the page
docs/2025-11-25/develop/clients/client-best-practices
…call, and returns the result to the sandbox. Authorization tokens and credentials are held by the host and never exposed to the generated code. **The model** sees only what the sandbox returns, typic…
Debugging
Model Context Protocol · in the page
docs/2025-11-25/tools/debugging
…hen debugging: 1. **Sensitive Data** * Sanitize logs * Protect credentials * Mask personal information 2. **Access Control** * Verify permissions * Check authentication * Monitor a…
Understanding Authorization in MCP
Model Context Protocol · in the page
docs/2025-11-25/tutorials/security/authorization
…/2025-11-25/basic/transports.md#stdio), you can use environment-based credentials or credentials provided by third-party libraries embedded directly in the MCP server instead. Because a STDIO-built MC…
Security Best Practices
Model Context Protocol · in the page
docs/2025-11-25/tutorials/security/security_best_practices
…or traffic monitoring, that depend on the token audience or other credential constraints. If clients can obtain and use tokens directly with the downstream APIs without the MCP server vali…
Client Best Practices
Model Context Protocol · in the page
docs/2026-07-28/develop/clients/client-best-practices
…call, and returns the result to the sandbox. Authorization tokens and credentials are held by the host and never exposed to the generated code. **The model** sees only what the sandbox returns, typic…