> ## Documentation Index > Fetch the complete documentation index at: https://docs.anchorbrowser.io/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > Anchor Browser provides cloud browsers for AI agents and automation: stealth browsing with residential proxies, managed authentication into third-party web apps, and browser sessions that run reliably at scale. AI agents that need Anchor credentials should start with https://docs.anchorbrowser.io/quickstart/agent-access. This flow lets agents obtain an API key programmatically without creating a dashboard account. Read that page before attempting authentication or API access. # Create Agent Access project > Issue an Agent Access API key. Submit the challenge `token` and computed integer `answer` from GET /v1/agent-access/challenge. GET on this path returns a guide, not a key. Optional `identity_token` as an OIDC JWT grants more credits. `identity_provider` is optional when the JWT `iss` is Google (`https://accounts.google.com`), GitHub Actions (`https://token.actions.githubusercontent.com`), or Vercel (`https://vercel.com`). Returns `api_key` for header `anchor-api-key`. Docs: https://docs.anchorbrowser.io/quickstart/agent-access ## OpenAPI ````yaml /openapi.yaml post /v1/agent-access openapi: 3.1.0 info: title: AnchorBrowser API version: 1.0.0 description: > Anchor Browser ([anchorbrowser.io](https://anchorbrowser.io)) provides cloud browsers built for AI agents and automation. Use this API to launch and control browser sessions, run natural-language web tasks, authenticate into third-party web apps with managed identities, and capture recordings — reliably and at scale, without operating browser infrastructure yourself. ## Core resources - **Sessions** (`/v1/sessions`): launch configurable cloud browsers — residential proxies, stealth browsing, captcha solving, profiles, extensions, recording — and connect over CDP with Playwright, Puppeteer, or any CDP client. - **AI tools** (`/v1/tools/perform-web-task`): state a goal in natural language and the built-in agent completes it inside the browser. Related tools fetch webpages, take screenshots, render PDFs, and execute code in a session. - **Tasks** (`/v1/task`): create, version, deploy, and monitor repeatable browser automations built to run reliably in production. - **Applications and identities** (`/v1/applications`, `/v1/identities`): managed authentication into third-party web apps — including multi-step logins and TOTP-based 2FA — so agents can act on behalf of users. - **Profiles** (`/v1/profiles`): persist cookies and login state across sessions. - **OS-level control** (`/v1/sessions/{sessionId}/mouse`, `/keyboard`, `/clipboard`): raw input for flows that resist DOM automation. - Plus batch sessions for running browser fleets in parallel, session recordings, webhooks, events, extensions, client certificates, and billing usage. ## Authentication Pass an API key in the `anchor-api-key` header on every request. Create keys at [app.anchorbrowser.io](https://app.anchorbrowser.io) under API Access. AI agents that have no key yet can obtain one autonomously through the unauthenticated [agent-access flow](https://docs.anchorbrowser.io/quickstart/agent-access) (`POST /v1/agent-access`). ## For AI agents and LLMs - Docs: [docs.anchorbrowser.io](https://docs.anchorbrowser.io), with a machine-readable index at [/llms.txt](https://docs.anchorbrowser.io/llms.txt) and the full corpus at [/llms-full.txt](https://docs.anchorbrowser.io/llms-full.txt). - MCP server for hosted browser control: `https://api.anchorbrowser.io/mcp`. - Official SDKs: `anchorbrowser` on [npm](https://www.npmjs.com/package/anchorbrowser) and [PyPI](https://pypi.org/project/anchorbrowser/). `DELETE` operations terminate sessions or permanently remove resources (profiles, identities, extensions); `GET` operations are safe and read-only. servers: - url: https://api.anchorbrowser.io description: API server security: [] paths: /v1/agent-access: post: tags: - Agent Access summary: Create Agent Access project description: > Issue an Agent Access API key. Submit the challenge `token` and computed integer `answer` from GET /v1/agent-access/challenge. GET on this path returns a guide, not a key. Optional `identity_token` as an OIDC JWT grants more credits. `identity_provider` is optional when the JWT `iss` is Google (`https://accounts.google.com`), GitHub Actions (`https://token.actions.githubusercontent.com`), or Vercel (`https://vercel.com`). Returns `api_key` for header `anchor-api-key`. Docs: https://docs.anchorbrowser.io/quickstart/agent-access requestBody: required: true content: application/json: schema: type: object required: - token - answer properties: token: type: string minLength: 1 description: >- Token returned by GET /v1/agent-access/challenge. Not the puzzle answer. answer: type: string minLength: 1 description: Final integer from the challenge prompt, as a string. identity_provider: type: string description: >- Optional when identity_token is an OIDC JWT whose iss matches a known provider (google, github, or vercel). Required for opaque OAuth access tokens (google or github). identity_token: type: string description: >- OIDC JWT preferred (iss auto-detected). GitHub Actions — GET $ACTIONS_ID_TOKEN_REQUEST_URL with Authorization bearer $ACTIONS_ID_TOKEN_REQUEST_TOKEN. Google — ID token JWT. Vercel — Sign in with Vercel user ID token (iss https://vercel.com). Opaque OAuth access tokens also work with identity_provider set. identity_audience: type: string description: >- Optional. Pin the JWT aud claim. Omit unless you requested a specific aud. responses: '200': description: API key issued. Follow `next` to make an authenticated call. content: application/json: schema: type: object required: - api_key - project_id - credits_granted - auth - next - docs - limits properties: api_key: type: string description: >- API key for authenticated requests. Send as header anchor-api-key. project_id: type: string description: Anchor project id created or reused for this onboarding. credits_granted: type: number description: >- Credits added by this POST. 0 when the Agent Access project already existed for this owner. agent_identity_token: type: string description: >- When present, send as header anchor-identity-token on later API calls when auth.identity_token_required is true. auth: type: object required: - api_key_header - identity_token_required properties: api_key_header: type: string description: Header name for api_key (anchor-api-key). identity_token_header: type: string description: >- Header name for agent_identity_token when identity_token_required is true. identity_token_required: type: boolean description: >- When true, authenticated API calls must include anchor-identity-token in addition to anchor-api-key. upgrade: type: object required: - message properties: message: type: string description: >- How to repeat onboarding with identity_token to receive more credits. next: $ref: '#/components/schemas/AgentAccessNextStep' docs: type: string description: Human-readable guide URL for Agent Access. limits: type: object required: - session_max_duration_minutes properties: session_max_duration_minutes: type: number description: >- Maximum session duration in minutes for keys issued through Agent Access. '400': description: >- Missing token/answer, expired token, or incomplete identity fields. Follow `next`. content: application/json: schema: $ref: '#/components/schemas/AgentAccessError' '401': description: Incorrect answer or invalid identity token. Follow `next`. content: application/json: schema: $ref: '#/components/schemas/AgentAccessError' '429': description: Too many onboarding attempts from this source. content: application/json: schema: $ref: '#/components/schemas/AgentAccessError' '500': description: Failed to create project. content: application/json: schema: $ref: '#/components/schemas/AgentAccessError' security: [] components: schemas: AgentAccessNextStep: type: object required: - method - path - description properties: method: type: string enum: - GET - POST description: HTTP method for the next call in the Agent Access onboarding flow. path: type: string description: >- Path on https://api.anchorbrowser.io for the next call. Prepend the method to execute it. description: type: string description: >- Plain-language instruction for what to do on the next call and what you receive afterward. AgentAccessError: type: object required: - error - next - docs properties: error: type: string description: Why the request failed. next: $ref: '#/components/schemas/AgentAccessNextStep' docs: type: string description: Human-readable guide URL for Agent Access. example: https://docs.anchorbrowser.io/quickstart/agent-access ````