# Anthale

## Docs

- [Anthale API Authentication with Bearer API Keys](https://anthale.com/docs/api-reference/authentication.md): Authenticate Anthale runtime API requests with a bearer API key, keep the key server-side, and understand common authentication failures.
- [Anthale API Errors, Retries, and Failure Handling](https://anthale.com/docs/api-reference/errors.md): Handle Anthale API failures predictably with clear retry rules, status meanings, and error payload fields for production integrations.
- [Anthale Runtime API Reference and Enforcement Contract](https://anthale.com/docs/api-reference/index.md): Reference Anthale runtime API behavior, authentication, errors, usage limits, and the generated endpoint contract for enforcement requests.
- [Enforce a policy](https://anthale.com/docs/api-reference/policies/enforce-a-policy.md): Evaluates a set of messages against the specified policy and returns guardrail decisions.
- [Anthale API Rate Limits and Backoff](https://anthale.com/docs/api-reference/usage-limits.md): Plan Anthale API throughput, rate-limit handling, backoff strategy, and capacity behavior for production enforcement requests and retries.
- [Anthale Agent Skills](https://anthale.com/docs/build-with-ai/agent-skills/index.md): Install Anthale agent skills for AI coding agents and use them for security reviews, workflow hardening, and repeatable implementation guidance.
- [Prompt Injection Code Review Skill for AI Coding Agents](https://anthale.com/docs/build-with-ai/agent-skills/prompt-injection-code-review.md): Inspect source code for prompt injection risk with Anthale's code review skill covering untrusted inputs, unsafe tools, and missing boundary checks.
- [Prompt Injection Hardening Skill](https://anthale.com/docs/build-with-ai/agent-skills/prompt-injection-hardening.md): Review and harden AI agents, chatbots, RAG systems, MCP integrations, and tool workflows for prompt injection risk with Anthale's agent skill.
- [Build with Anthale in AI Clients and Agents](https://anthale.com/docs/build-with-ai/index.md): Choose between Anthale documentation MCP for live lookup and Anthale agent skills for secure coding, workflow hardening, and assistant workflows.
- [Connect Anthale Documentation MCP to AI Clients](https://anthale.com/docs/build-with-ai/mcps/documentation-mcp.md): Connect Anthale's documentation MCP server to Claude Code, Codex, Cursor, or VS Code and check the endpoint, auth model, and tools.
- [Anthale MCP Integrations for AI Clients and Agents](https://anthale.com/docs/build-with-ai/mcps/index.md): Set up the Anthale documentation MCP server so AI clients and coding agents can look up product, policy, guardrail, and API details during a session.
- [Anthale Glossary for Policies and Guardrails](https://anthale.com/docs/glossary.md): Look up the Anthale terms used across the documentation, including organizations, policies, guardrails, enforcement requests, actions, and trust boundaries.
- [How Anthale Evaluates Policies at Runtime](https://anthale.com/docs/how-anthale-works.md): Learn how Anthale receives an enforcement request, evaluates a policy, resolves guardrail results, and returns a runtime action your application enforces.
- [Anthale Runtime Guardrails and Policy Overview](https://anthale.com/docs/index.md): Understand what Anthale is, where it fits in an LLM application, and how policies and guardrails return `allow`, `detect`, `redact`, or `block`.
- [Create an Anthale API Key for Server-Side Use](https://anthale.com/docs/learn/api-keys/create-an-api-key.md): Create an Anthale API key for a server-side integration so your service can authenticate enforcement requests without exposing credentials to clients.
- [Delete an Anthale API Key from the Dashboard](https://anthale.com/docs/learn/api-keys/delete-an-api-key.md): Permanently remove an Anthale API key from the dashboard when a service credential is retired, replaced, or should no longer access the runtime API.
- [Enable or Disable an Anthale API Key](https://anthale.com/docs/learn/api-keys/enable-or-disable-an-api-key.md): Temporarily stop or resume an Anthale API key in the dashboard when you need to pause a service credential without deleting it permanently.
- [Anthale API Keys for Runtime Enforcement Requests](https://anthale.com/docs/learn/api-keys/index.md): Create, view, disable, and delete Anthale API keys for server-side enforcement requests, runtime service boundaries, and operator traceability.
- [View Anthale API Keys in an Organization](https://anthale.com/docs/learn/api-keys/view-api-keys.md): Review the Anthale API keys in your organization to confirm their status, ownership, and which service credentials are currently active.
- [Anthale Content Moderation on Input and Output Paths](https://anthale.com/docs/learn/guardrails/content-moderation/index.md): Understand Anthale content moderation, which categories it covers, and where to enforce it on input and output paths in your application.
- [Moderation Evasion Patterns in Anthale Workflows](https://anthale.com/docs/learn/guardrails/content-moderation/moderation-evasion.md): Classify the common ways abusive requests are disguised to get past moderation rules across prompts, transformations, and indirect model workflows.
- [Data Exfiltration Patterns Across Boundaries](https://anthale.com/docs/learn/guardrails/data-leakage/exfiltration-patterns.md): Classify the recurring ways sensitive data is pulled or pushed across a boundary so you can design stronger leakage controls and policy tests.
- [Anthale Data Leakage Prevention Across Boundaries](https://anthale.com/docs/learn/guardrails/data-leakage/index.md): Understand Anthale data leakage prevention, what counts as sensitive data, and where to enforce it across model, tool, and output boundaries.
- [Anthale Guardrails for Runtime Risk Control](https://anthale.com/docs/learn/guardrails/index.md): Review Anthale guardrail families and move from control selection into prompt injection, data leakage, moderation, topic control, and link guidance.
- [Anthale Link Control for Allowed and Blocked Domains](https://anthale.com/docs/learn/guardrails/link-control/index.md): Understand Anthale link control, how allowlists and blocklists work, and where domain enforcement belongs across input, retrieval, tool, and output flows.
- [Advanced Prompt Injection Paths in Agents and Retrieval](https://anthale.com/docs/learn/guardrails/prompt-injection/advanced-attack-paths.md): Classify prompt injection goals, techniques, and indirect attack paths across agents, retrieval, tools, memory, multimodal inputs, and MCP flows.
- [Map Prompt Injection Attack Surfaces and Boundaries](https://anthale.com/docs/learn/guardrails/prompt-injection/attack-surfaces.md): Find the trust boundaries where Anthale should evaluate prompt injection risk across user input, retrieval, tools, files, and model output.
- [Prompt Injection Impact Paths in Agent Workflows](https://anthale.com/docs/learn/guardrails/prompt-injection/impact-paths.md): Classify the downstream consequences prompt injection can create in agent, retrieval, and tool-using systems after the initial control takeover.
- [Anthale Prompt Injection Protection at Trust Boundaries](https://anthale.com/docs/learn/guardrails/prompt-injection/index.md): Understand Anthale prompt injection protection, where injection enters a system, and which trust boundaries you should evaluate at runtime.
- [Prompt Injection Obfuscation and Evasion Reference](https://anthale.com/docs/learn/guardrails/prompt-injection/obfuscation-evasion.md): Understand the disguises attackers use to hide prompt injection attempts so you can evaluate indirect, encoded, or reformatted attack content.
- [Anthale Topic Control for Product Scope Enforcement](https://anthale.com/docs/learn/guardrails/topic-control/index.md): Understand Anthale topic control, how allowed and blocked topic lists work, and where product-scope enforcement belongs in your runtime flow.
- [Scope Escape Patterns in Topic-Controlled Assistants](https://anthale.com/docs/learn/guardrails/topic-control/scope-escape.md): Classify the common ways users and attackers try to move an assistant out of its allowed scope so you can tune product boundaries more clearly.
- [Learn Anthale Guides for Policies and Guardrails](https://anthale.com/docs/learn/index.md): Browse Anthale guides for organizations, API keys, policies, metadata, guardrails, and trust-boundary implementation tasks across your application.
- [Anthale Metadata and Logs for Runtime Operations](https://anthale.com/docs/learn/metadata-and-logs/index.md): Attach metadata and use Anthale logs to trace runtime enforcement decisions, investigate policy hits, and tune guardrail policies in production.
- [Investigate Anthale Policy Hits in Production](https://anthale.com/docs/learn/metadata-and-logs/investigate-a-policy-hit.md): Investigate Anthale detect, redact, and block events using boundary metadata and guardrail evidence to separate attacks, bugs, and tuning issues.
- [What Metadata to Send with Anthale Enforcement Requests](https://anthale.com/docs/learn/metadata-and-logs/what-metadata-to-send-with-enforcement-requests.md): Send stable metadata with Anthale enforcement requests to trace policy hits, compare behavior by feature and boundary, and investigate faster.
- [Anthale Organization Settings and Dashboard Context](https://anthale.com/docs/learn/organization/index.md): View and manage the Anthale organization that owns your policies, API keys, and dashboard context for runtime operations and service boundaries.
- [Rename an Anthale Organization in the Dashboard](https://anthale.com/docs/learn/organization/update-an-organization.md): Change the name of an Anthale organization in the dashboard when the current label no longer matches the account, environment, or operating boundary.
- [View Anthale Organizations and Switch Context](https://anthale.com/docs/learn/organization/view-organizations.md): Review available Anthale organizations and switch the current organization in the dashboard when you need to work in a different account boundary.
- [Anthale Actions and Guardrail Evaluation Flow](https://anthale.com/docs/learn/policies/actions-and-evaluation-flow.md): Understand how Anthale resolves guardrail hits into one runtime action so your application can enforce `allow`, `detect`, `redact`, or `block`.
- [Create an Anthale Policy for a Trust Boundary](https://anthale.com/docs/learn/policies/create-a-policy.md): Set up an Anthale policy with guardrails, enforcement actions, and rollout intent for a specific trust boundary in your LLM application.
- [Delete an Anthale Policy from Runtime Use](https://anthale.com/docs/learn/policies/delete-a-policy.md): Delete an Anthale policy that should no longer be available for runtime use after you confirm no active workflow still depends on it.
- [Anthale Policies for Guardrail Evaluation and Actions](https://anthale.com/docs/learn/policies/index.md): Create, review, update, and delete Anthale policies that decide which guardrails run, where they run, and how runtime actions are enforced.
- [Update an Anthale Policy Without Breaking Rollout](https://anthale.com/docs/learn/policies/update-a-policy.md): Update an Anthale policy without losing control of rollout, guardrail coverage, or runtime enforcement behavior in existing workflows.
- [View Anthale Policies in an Organization](https://anthale.com/docs/learn/policies/view-policies.md): Review the Anthale policies available in an organization so you can confirm status, scope, and which policy a workflow should evaluate.
- [Tool Call Validation and Approval Guide](https://anthale.com/docs/learn/secure-ai-systems/gate-tool-actions.md): Validate model-proposed tool calls with least privilege, deterministic checks, and approval gates before execution in agent and MCP workflows.
- [Secure AI Systems Guides for Agent, RAG, and MCP Security](https://anthale.com/docs/learn/secure-ai-systems/index.md): Choose the Anthale guide for AI agent security, RAG pipeline security, MCP integration security, tool call validation, or LLM output validation.
- [AI Security Logging Guide](https://anthale.com/docs/learn/secure-ai-systems/log-security-events.md): Capture Anthale enforcement decisions, trust-boundary context, and tool activity so AI security incidents can be tuned, investigated, and audited.
- [AI Agent Red Teaming Guide](https://anthale.com/docs/learn/secure-ai-systems/red-team-agent-workflows.md): Red-team AI agent workflows by testing for prompt injection, retrieval poisoning, tool abuse, memory compromise, and unsafe output paths.
- [AI Security Code Review Guide](https://anthale.com/docs/learn/secure-ai-systems/review-ai-security-in-code.md): Review AI agent, retrieval, tool, memory, and output code paths for trust-boundary mistakes, missing guardrails, and unsafe patterns before they ship.
- [AI Agent Security Guide](https://anthale.com/docs/learn/secure-ai-systems/secure-agent-workflows.md): Secure AI agent workflows by placing Anthale, approvals, and validation at user input, retrieval, tool, memory, and output boundaries.
- [Browser Agent Security Guide](https://anthale.com/docs/learn/secure-ai-systems/secure-browser-agents.md): Secure browser agents by controlling page content, DOM reads, navigation, and browser actions at each trust boundary in your AI workflow.
- [MCP Security Guide for AI Clients and Agents](https://anthale.com/docs/learn/secure-ai-systems/secure-mcp-integrations.md): Secure Model Context Protocol integrations with server scoping, tool review, approval paths, and boundary-aware runtime controls in AI workflows.
- [AI Memory Security Guide](https://anthale.com/docs/learn/secure-ai-systems/secure-memory-and-state.md): Prevent saved summaries, conversation state, and long-term memory from becoming a persistent prompt injection or data leakage path.
- [RAG Security Guide for Retrieval Pipelines](https://anthale.com/docs/learn/secure-ai-systems/secure-retrieval-pipelines.md): Secure RAG and retrieval pipelines so untrusted documents, search results, and chunks do not become over-trusted prompt content in your LLM application.
- [LLM Output Validation Guide](https://anthale.com/docs/learn/secure-ai-systems/validate-model-output.md): Validate LLM output before it reaches users, tools, or storage so generated content stays within your Anthale policy and application rules.
- [Create Your First Anthale Policy](https://anthale.com/docs/quickstart/first-policy.md): Create your first Anthale policy with a focused scope you can tune, test, and enforce safely before expanding to broader trust boundaries.
- [Anthale Quickstart for Your First Guarded Integration](https://anthale.com/docs/quickstart/index.md): Create an API key, create a first policy, and connect Anthale through an OpenAI, LangChain, or direct SDK path in Python or TypeScript.
- [Anthale Python Direct SDK Quickstart](https://anthale.com/docs/quickstart/python/index.md): Call the Anthale Python SDK directly, send enforcement requests, and handle allow, detect, redact, and block actions in a custom Python integration.
- [LangChain Agent Middleware for Python](https://anthale.com/docs/quickstart/python/langchain-agent-middleware.md): Add Anthale middleware to a Python LangChain agent, pass request metadata, and verify blocked or redacted runs before unsafe agent execution continues.
- [LangChain Chat Model Guard for Python](https://anthale.com/docs/quickstart/python/langchain-chat-model.md): Wrap a standalone LangChain chat model with Anthale, attach metadata, and verify blocked or redacted model calls before unsafe output continues.
- [OpenAI Python Integration with Anthale Guardrails](https://anthale.com/docs/quickstart/python/openai.md): Wrap the OpenAI Python client with Anthale guardrails, add request metadata, and handle blocked or redacted calls before model execution.
- [Anthale TypeScript Direct SDK Quickstart](https://anthale.com/docs/quickstart/typescript/index.md): Call the Anthale TypeScript SDK directly from Node, send enforcement requests, and handle allow, detect, redact, and block actions in custom code.
- [OpenAI TypeScript Integration with Anthale](https://anthale.com/docs/quickstart/typescript/openai.md): Wrap the OpenAI Node client with Anthale, attach metadata, and handle blocked or redacted calls before model execution reaches downstream systems.
- [Secure AI Systems with Runtime Trust Boundaries](https://anthale.com/docs/secure-ai-systems.md): Understand the trust boundaries, control layers, and runtime patterns that protect LLM applications from prompt injection, data leakage, and unsafe output.

## OpenAPI Specs

- [openapi.documented](https://app.stainless.com/api/spec/documented/anthale/openapi.documented.yml)
- [openapi](https://anthale.com/docs/api-documentation/openapi.json)