890 pages for allow.

ip-allowlist Claude Developer Platform · title manage-claude/ip-allowlist glossary Claude Developer Platform · in the page about-claude/glossary …represents a “working memory” for the model. A larger context window allows the model to process and respond to more complex and lengthy prompts, whereas a smaller context window might limit the mode… model-deprecations Claude Developer Platform · in the page about-claude/model-deprecations …ny instances where your application is still using deprecated models, allowing you to prioritize updates to newer models before the retirement date. ## Best practices 1. Regularly check the document… choosing-a-model Claude Developer Platform · in the page about-claude/models/choosing-a-model …pgrade only if necessary for specific capability gaps. This approach allows for quick iteration and lower development costs, and is often sufficient for many common applications. This approach is bes… Or, for the model with the same capabilities and no access approval requirement: Claude Developer Platform · in the page about-claude/models/migration-guide …ameter](https://platform.claude.com/docs/en/build-with-claude/effort) allows you to tune Claude's intelligence versus token spend, trading off capability for faster speed and lower costs. Claude Opus… optimizing-for-cost-and-intelligence Claude Developer Platform · in the page about-claude/models/optimizing-for-cost-and-intelligence …ggers of 150,000 tokens (the default), 90,000, and 50,000 (the lowest allowed), and no compaction. Costs within a setting agreed to within 4%. With the default trigger, 15 of each session’s 45 replies… pricing Claude Developer Platform · in the page about-claude/pricing …en/build-with-claude/fast-mode). ### Batch processing The Batch API allows asynchronous processing of large volumes of requests with a 50 percent discount on both input and output tokens. | Model… content-moderation Claude Developer Platform · in the page about-claude/use-case-guides/content-moderation …fluent in each supported language. Claude’s multilingual capabilities allow it to classify content in various languages without the need for separate models or extensive translation processes, streaml… customer-support-chat Claude Developer Platform · in the page about-claude/use-case-guides/customer-support-chat …, nuanced conversation: Claude’s sophisticated language understanding allows for more natural, context-aware conversations that feel more human-like than chats with other LLMs. * You often receive com… legal-summarization Claude Developer Platform · in the page about-claude/use-case-guides/legal-summarization …nts. This capability can significantly speed up the research process, allowing legal professionals to focus on higher-level analysis and strategy development. </Accordion> </AccordionGroup> ### Det… ticket-routing Claude Developer Platform · in the page about-claude/use-case-guides/ticket-routing …tensive feature engineering. Claude’s advanced language understanding allows for accurate classification based on content and context, rather than relying on strict ontological structures. </Accordi… enterprise Claude Developer Platform · in the page agents-and-tools/agent-skills/enterprise …arning stays usable behind a caution notice. Organization owners can allow some Skills that failed the scan. So can members whose [custom role](https://platform.claude.com/docs/en/manage-claude/user-… PDF Processing Claude Developer Platform · in the page agents-and-tools/agent-skills/overview …s alone. Claude operates in a virtual machine with filesystem access, allowing Skills to exist as directories containing instructions, executable code, and reference materials, organized like an onboa… mcp-connector Claude Developer Platform · in the page agents-and-tools/mcp-connector …MCP servers directly from the Messages API without an MCP client, and allowlist, denylist, or configure individual tools. featureMetadata: status: beta betaHeader: mcp-client-2026-09-15, mcp-clien… concepts Claude Developer Platform · in the page agents-and-tools/mcp-tunnels/concepts …ent. Terminates inner TLS, validates that upstream IPs fall within an allowed range, and routes each request to an upstream MCP server based on hostname.… console Claude Developer Platform · in the page agents-and-tools/mcp-tunnels/console …esolves to** line, such as `wiki.abcd1234.tunnel.anthropic.com`, to **Allowed hosts**. Leave the **Allow MCP servers** checkbox unchecked, as the [Limit the network](https://platform.claude.com/docs/e… Edit docker-compose.yaml: increment the integer in the setup service's Claude Developer Platform · in the page agents-and-tools/mcp-tunnels/deploy-compose …ut data/tls.crt -days 90 \ -extfile data/tls.ext # Allow the non-root proxy container (UID 65532) to read the key from # the bind mount. Without the world-read bit the conta… deploy-helm Claude Developer Platform · in the page agents-and-tools/mcp-tunnels/deploy-helm …your routes target in-cluster Services, add `gateway.config.upstream.allowed_ips` here as described in [Upstream IP validation](https://platform.claude.com/docs/en/agents-and-tools/mcp-tunnels/troubl… overview Claude Developer Platform · in the page agents-and-tools/mcp-tunnels/overview …en inbound firewall ports, expose services to the public internet, or allowlist Anthropic’s IP ranges on your origin. ## How it works The [tunnel stack](https://platform.claude.com/docs/en/agents-an… reference Claude Developer Platform · in the page agents-and-tools/mcp-tunnels/reference …| Required | | `upstream.allowed_ips` | IPv4 CIDR ranges or single addresses the proxy is allowed to connect to. Mutually exclusive with `disabl… security Claude Developer Platform · in the page agents-and-tools/mcp-tunnels/security …defense in depth on top of the tunnel’s transport authentication and allows user-level authorization at the data layer. * **Enable SSO for your organization.** Tunnels, federation rules, and service… troubleshooting Claude Developer Platform · in the page agents-and-tools/mcp-tunnels/troubleshooting …hat need more than a one-line fix. ## OAuth fails behind a source-IP allowlist OAuth flows fail when your authorization server’s source-IP allowlist blocks Anthropic’s back end from reaching `/token… advisor-tool Claude Developer Platform · in the page agents-and-tools/tool-use/advisor-tool …| unlimited | Maximum number of advisor calls allowed in a single turn. Once the executor reaches this cap, further advisor calls return an `advisor_tool_result_error` with `er… bash-tool Claude Developer Platform · in the page agents-and-tools/tool-use/bash-tool …plement safety measures"> Add validation and restrictions. Use an allowlist rather than a blocklist: a blocklist misses any command it didn’t anticipate. The example also rejects shell operators t… browser-use-sdk Claude Developer Platform · in the page agents-and-tools/tool-use/browser-use-sdk …back", "forward", "reload", or a URL that your URL policy # allowed, as Claude wrote it. Like is_allowed, backend.goto adds https:// # to a URL that doesn't start with a scheme.… browser-use-tool Claude Developer Platform · in the page agents-and-tools/tool-use/browser-use-tool …e same way. 2. Restrict the hosts the browser can reach to a domain allowlist enforced at the network layer and re-checked in your `navigate` handler after redirects, and block loopback, link-local,… build-a-tool-using-agent Claude Developer Platform · in the page agents-and-tools/tool-use/build-a-tool-using-agent …t Output wrap I tried to schedule the all-hands but the calendar only allows 10 attendees per event. I can split this into two sessions, or you can let me know which 10 people to prioritize. ``` The… code-execution-tool Claude Developer Platform · in the page agents-and-tools/tool-use/code-execution-tool …d files directly within the API conversation. The code execution tool allows Claude to run Bash commands and manipulate files, including writing code, in a secure, sandboxed environment. **Code execu… computer-use-tool Claude Developer Platform · in the page agents-and-tools/tool-use/computer-use-tool …on, to prevent information theft. 3. Limiting internet access to an allowlist of domains to reduce exposure to malicious content. 4. Asking a human to confirm decisions that might result in meanin… define-tools Claude Developer Platform · in the page agents-and-tools/tool-use/define-tools …efinition, including `cache_control`, `strict`, `defer_loading`, and `allowed_callers`, see [Tool definition properties](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-reference#to… Process results programmatically Claude Developer Platform · in the page agents-and-tools/tool-use/programmatic-tool-calling …se/code-execution-tool#tool-versions). --- Programmatic tool calling allows Claude to write code that calls your tools programmatically within a [code execution](https://platform.claude.com/docs/en/a… server-tools Claude Developer Platform · in the page agents-and-tools/tool-use/server-tools …rver-side-loop-and-pause-turn), re-send it as-is instead. ## ZDR and allowed\_callers The basic versions of web search (`web_search_20250305`) and web fetch (`web_fetch_20250910`) are eligible for [… text-editor-tool Claude Developer Platform · in the page agents-and-tools/tool-use/text-editor-tool …g you debug, fix, and improve your code or other text documents. This allows Claude to directly interact with your files, providing hands-on assistance rather than just suggesting changes. For model… tool-combinations Claude Developer Platform · in the page agents-and-tools/tool-use/tool-combinations …] } ``` Pair this with a constrained working directory and a command allowlist if the agent operates on untrusted code. See [Text editor tool](https://platform.claude.com/docs/en/agents-and-tools/too… tool-reference Claude Developer Platform · in the page agents-and-tools/tool-use/tool-reference …dated `type` fixes the member names. `configs`, `cache_control`, and `allowed_callers` (which accepts only `["direct"]`) are optional. Client toolsets are Messages API tools. They aren’t currently av… web-fetch-tool Claude Developer Platform · in the page agents-and-tools/tool-use/web-fetch-tool …thout `max_uses`, `citations` or `cache_control`. The web fetch tool allows Claude to retrieve full content from specified webpages and PDF documents. The latest web fetch tool version (`web_fetch_2… web-search-tool Claude Developer Platform · in the page agents-and-tools/tool-use/web-search-tool …web search tool gives Claude direct access to real-time web content, allowing it to answer questions with up-to-date information beyond its knowledge cutoff. The response includes citations for sourc… Beta Claude Developer Platform · in the page api/beta …default: model - `id: string` Unique model identifier. - `allowed_fallback_models: array of string or null` Model IDs this model accepts as `fallbacks[i].model` on the Messages API. A… beta-headers Claude Developer Platform · in the page api/beta-headers …hropic-beta` header or the SDK's `betas` parameter. --- Beta headers allow you to access experimental features and new model capabilities before they become part of the standard API. <Info> The [c… Agents Claude Developer Platform · in the page api/beta/agents …`{"type":"agent","id","version"}` reference, or `{"type":"self"}` to allow recursive self-invocation. Entries must reference distinct agents (after resolving `self` and string forms); at most one `se… Archive Agent Claude Developer Platform · in the page api/beta/agents/archive …name: "bash"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution.… Create Agent Claude Developer Platform · in the page api/beta/agents/create …`{"type":"agent","id","version"}` reference, or `{"type":"self"}` to allow recursive self-invocation. Entries must reference distinct agents (after resolving `self` and string forms); at most one `se… List Agents Claude Developer Platform · in the page api/beta/agents/list …name: "bash"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution.… Get Agent Claude Developer Platform · in the page api/beta/agents/retrieve …name: "bash"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution.… Update Agent Claude Developer Platform · in the page api/beta/agents/update …`{"type":"agent","id","version"}` reference, or `{"type":"self"}` to allow recursive self-invocation. Entries must reference distinct agents (after resolving `self` and string forms); at most one `se… Versions Claude Developer Platform · in the page api/beta/agents/versions …name: "bash"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution.… List Agent Versions Claude Developer Platform · in the page api/beta/agents/versions/list …name: "bash"` - `permission_policy: BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy` Permission policy for tool execution.… Dreams Claude Developer Platform · in the page api/beta/dreams …mory store instead of a new memory store. The credential must be allowed to write memory stores, or the request returns a 403 error. While another `update_existing` dream on the same memory store… Archive a Dream Claude Developer Platform · in the page api/beta/dreams/archive …ry store instead of a new memory store. The credential must be allowed to write memory stores, or the request returns a 403 error. While another `update_existing` dream on the same memory store… Cancel a Dream Claude Developer Platform · in the page api/beta/dreams/cancel …ry store instead of a new memory store. The credential must be allowed to write memory stores, or the request returns a 403 error. While another `update_existing` dream on the same memory store…