What's shipped.

The Anakin MCP connector (mcp.anakin.io) and the @anakin-io/mcp npm package (v0.2.0) now expose every Anakin product: Website Monitoring, AI Visibility, saved Browser Sessions, and AI Browser Automation join scraping, search, crawling, mapping, deep research, and Wire — 21 tools in total. Wire execution is now split into read and write tools, each carrying MCP safety annotations, so your client asks before anything state-changing runs; payment execution remains refused by policy. Non-Claude MCP clients (Cursor, VS Code) connect over the same OAuth flow, each with its own revocable API key.

See what the major AI engines say when asked the same thing. POST /v1/ai-visibility/search fans one prompt out to ChatGPT, Gemini, and Google AI Overview and returns every answer side by side — full response, extracted summary, per-source latency, and credit cost. Pick the search geography with country, poll as each engine streams in, and re-run a single failed source without repeating the whole run. Available in the dashboard and the API.

Stop polling. Subscribe an HTTPS endpoint once and get signed deliveries for scrape, crawl, map, and agentic-search job completions, Wire task results, monitor alerts, and AI Visibility runs. Payloads are signed with your endpoint's secret so you can verify authenticity, failed deliveries retry automatically with backoff, and a per-delivery log in the dashboard shows exactly what was sent and when. One-off jobs can also pass a webhookUrl directly — no endpoint setup needed.

Monitors can now carry an end date and expire themselves when a watch is only relevant for a while. Wire monitor diffs are schema-aware, so changes are reported field by field against the action's actual output shape, with the full raw JSON one click away. And the country selector is searchable instead of a long scroll.

Monitors gain a third scope: wire. Run any catalog action on your schedule — a product search, a listing lookup, an account page — and get alerted when the JSON it returns changes. Same alerting and history as page monitors, pointed at structured API output instead of a page.

Point a monitor at a URL and Anakin checks it on your schedule (down to every 15 minutes), records a change whenever the page differs from the last check, and alerts you by webhook or email. Watch the whole page (markdown or HTML diff) or track specific fields with a JSON Schema, and optionally let AI judge whether a change matters — e.g. "only when the price drops or it goes out of stock". site scope crawls the whole site each run and reports pages added, removed, and changed.

POST /v1/url-scraper now accepts outputSchema — a JSON Schema describing exactly the fields you want. The completed job's generatedJson matches your schema instead of an AI-inferred shape, so downstream code can rely on the structure. Passing outputSchema implies generateJson: true.

Connect 1Password as an Identity Source and Wire signs into catalog websites on your behalf — no passwords pasted into Wire. Link a vault item once and authenticated actions pull the right credentials securely at run time.

Wire — turn any website into an agent-callable API — now lives natively on anakin.io. A new /products/wire landing page, a built-in Wire dashboard, the public action catalog, and Identity Sources for managing how actions authenticate, all alongside your scraping and search tools.

Bring your team onto one account. A single subscription now covers the whole team with seat limits, member invites, and owner / admin / member roles, plus a top-nav switcher to move between your personal and team workspaces. Credits and usage pool across the org, with a per-member usage view so owners can see who's running what.

Choose annual billing to save versus paying monthly, and step up to the new Scale plan built for high-volume workloads. The pricing page now shows the monthly-vs-annual savings clearly, with discounts visible without toggling.

Keep more than one identity for the same catalog — a personal account, a work account, a shared test login — and choose which one an action runs as. Manage them all from Identities in the Wire console.

For sites with SSO or MFA where a username and password aren't enough, sign in through a guided browser session and Wire captures the resulting authenticated session to reuse — so those actions can run behind login too.

Provide a site's username and password once and Wire signs in for you (Plaid-style), then runs actions on pages behind that login. Your password is never stored — Wire keeps only the session it captures.

Tougher anti-bot handling: a new browser engine gets scrapes through Datadome's protection, so more high-defense sites return data reliably instead of failing or serving challenge pages.

An interactive playground at anakin.io/demo lets developers test scrape, map, crawl, search, and AI search against any URL before creating an account. Five endpoint modes, two free anonymous calls, then a contextual signup prompt. No credit card required.

Five new official SDKs published across major registries:

• Rust — crates.io/crates/anakin-sdk cargo add anakin-sdk
• PHP — packagist.org/packages/anakin/sdk composer require anakin/sdk
• Ruby — rubygems.org/gems/anakin-sdk gem install anakin-sdk
• Elixir — hex.pm/packages/anakin {:anakin, "~> 0.1"}
• Java — Maven Central io.github.anakin-inc:anakin-sdk:0.1.0

All five mirror the same surface as the existing Python, Node.js, and Go SDKs: scrape, map, crawl, search, agentic_search, wire, browser-session CRUD, and a typed error hierarchy.

Dedicated reference pages added for Go, Rust, PHP, Ruby, Elixir, Java, and .NET (coming soon). Each covers install, quickstart, method reference, configuration options, and the full error hierarchy. The SDKs landing page now lists all nine languages with install commands.

The official Go module is now live on the Go module proxy and pkg.go.dev.

go get github.com/Anakin-Inc/anakin-go

Uses functional options (WithAPIKey, WithTimeout, etc.), zero runtime dependencies (pure stdlib HTTP), and 23 tests. Requires Go 1.21+.

Previously, npx -y @anakin-io/mcp init --all exited with an error if ANAKIN_API_KEY wasn't set — forcing a manual export step. The --all flag controls per-client confirmations, not the key prompt. Now the key is always requested interactively if the env var is absent, regardless of mode.

Four packages went live simultaneously:

• @anakin-io/sdk v0.1.0 — Node.js / TypeScript SDK on npm
• @anakin-io/mcp v0.1.0 — Model Context Protocol server on npm (auto-configures Claude Desktop, Claude Code, Cursor, Cline, Continue, Zed, Windsurf, VS Code)
• anakin-sdk v0.1.0 — Python SDK on PyPI (import name: anakin)
• anakin-cli v0.2.0 — CLI for terminal-driven scraping on PyPI

All packages are Apache 2.0 licensed and open source under github.com/Anakin-Inc.

New endpoints to discover and search the Wire (Holocron) action catalog:

• GET /v1/holocron/catalog — list available action catalogs
• GET /v1/holocron/catalog/{id} — get a specific catalog
• POST /v1/holocron/search — search actions by keyword

Enables programmatic discovery of pre-built Wire actions without needing the dashboard.

Browser Connect (/v1/browser-connect) now supports loading saved sessions via ?session_id or ?session_name. Cookies, localStorage, and proxy assignment are injected into the CDP context before the WebSocket upgrade — eliminating re-login flows for authenticated scraping targets.

anakin-cli v0.2.0 ships:

• New research command powered by agentic search — ask a question, get a synthesised answer with sources
• Markdown output now renders in-terminal with colour coding
• --format json flag on all commands for piping to jq
• --country flag on scrape and crawl for geo-targeted results

POST /v1/agentic-search now accepts an optional schema field (JSON Schema object). When provided, the answer is returned as structured JSON matching the schema rather than free-form text. Useful for extracting typed data from multi-source research tasks.

Default rate limits increased across the board:

Enterprise plans can request higher limits via the dashboard.

POST /v1/map gains two new parameters:

• include_subdomains (bool) — discover links across all subdomains of the root domain
• search (string) — filter returned links to those matching a keyword (server-side, no extra API calls)

Both are optional and backward-compatible.

Pass "screenshot": true in the scrape request body to capture a full-page PNG screenshot of the scraped page. Returned as a base64-encoded string in the screenshot field of the response. Automatically handled by the browser worker when useBrowser is also true.

Our browser engine now achieves materially higher success rates on heavily-protected sites:

• Stronger fingerprint masking across canvas, WebGL, audio, and fonts
• WebRTC leak prevention on by default
• Automatic handling of interactive challenges on supported targets
• Self-healing browser workers that auto-recover from crashes

POST /v1/crawl now accepts:

• max_depth (int, default 2) — how many link-hops from the start URL to follow
• max_pages (int, default 100) — hard cap on total pages crawled

Both are enforced server-side. The job completes when either limit is hit or the site is exhausted.

Previously, credits were checked and reserved upfront but deducted at the end. A race condition meant some failed jobs still consumed credits. The deduction path is now strictly gated on status = completed. Jobs that timeout, fail, or are cancelled consume zero credits.

Scrape requests are now routed to the proxies that perform best for each domain+country pair, and routing adapts continuously as performance shifts. The result: lower block rates on difficult targets without manual proxy management.

API keys are now stored AES-256-GCM encrypted at rest. The SHA-256 hash is used for fast lookup; the plaintext key is only shown once at creation time. Existing keys were migrated transparently — no action required from existing users.

POST /v1/url-scraper/batch submits up to 10 URLs in a single API call. Each URL is processed as an independent job; the batch endpoint returns a list of job IDs for polling. Useful for scraping product listings, search results, or other sets of known URLs.

The dashboard now shows a 30-day credit usage chart and a per-request breakdown table (endpoint, URL domain, credits used, timestamp). Filterable by endpoint type. Useful for understanding spend distribution before upgrading plans.