execute_code(code: string) -> { ok, result, stdout, state, durationMs } state: current globalThis stash (auto-populated, summary-form — read this to see what data from prior calls is available without re-fetching)

Sandbox globals: klaviyo, shopify, console, pick, topN, summarize, globalThis (persists across calls)

Discovery: search_docs / read_doc surface SDK paths, parameter shapes, and recipes. The SDK uses JSON:API conventions (sort keys, sparse fieldsets) that differ from typical JS SDKs — search_docs FIRST for unfamiliar methods.

Reference example (real API surface — note JSON:API request shape): const metricId = await klaviyo.getConversionMetricId(); const report = await klaviyo.reporting.campaignValues({ data: { type: 'campaign-values-report', attributes: { timeframe: { key: 'last_30_days' }, conversion_metric_id: metricId, statistics: ['recipients', 'open_rate', 'conversion_value'], }} }); globalThis.report = report; return topN(report.data.attributes.results, 5, r => r.statistics.conversion_value);

Search the bundled SDK reference docs for Klaviyo and Shopify methods exposed inside the execute_code sandbox. Returns ranked markdown chunks: method signatures, parameter descriptions, and runnable code examples.

Use this BEFORE writing code in execute_code — the SDK surface is constrained to registered methods (escape hatches are 'klaviyo.get/post/paginate' and 'shopify.gql/ql').

The docs index is refreshed daily from a CDN-backed source repo, so new Klaviyo/Shopify API revisions land without requiring a new MCP release.

Fetch a specific SDK docs chunk by exact path, or list all available paths when called with no args.

Use this instead of search_docs when you already know the chunk ID — it's cheaper and more deterministic. Common patterns: • read_doc({}) → list every chunk ID with one-line summaries (use this once at the start of a session to map the SDK surface) • read_doc({ path: "klaviyo.reporting.campaignValues" }) → fetch one method's full doc (signature + JSDoc + example) verbatim • read_doc({ platform: "shopify" }) → list only Shopify chunk IDs

This adopts the "filesystem-as-API" pattern from Anthropic's Code Execution with MCP research: LLMs are faster and more accurate when they can read a typed-source-of-truth doc page directly, rather than re-searching for it on every code generation.