canonical: https://jentic.com/apis/apiacre.com/apiacre # API Acre The API Acre API exposes a catalog of machine-discoverable utilities that turn messy inputs into structured JSON: it extracts web and document content, cleans and converts datasets, repairs and validates JSON, and runs SEO, security, and accessibility audits on a page. It also covers research lookups against public registries and read-only EVM utilities on Base and Solana. Every paid operation is metered per call through x402 USDC settlement, and agents can start from a discovery endpoint that lists the available services. ## For AI agents Extract web and document content, clean and convert datasets, repair and validate JSON, and run site audits, returning structured JSON with per-call x402 settlement. ## Scope Does not host data, run scheduled jobs, or store state between calls. Use for per-call web, document, and data transformation and audits only. ## Capabilities - Extract readable content and metadata from a web page or document - Clean, convert, and deduplicate a dataset into structured JSON - Repair and validate JSON against a generated schema - Run SEO, security, accessibility, and performance audits on a page - Look up entities against public research registries - Browse the service catalog to discover available operations ## Use cases ### Agent-driven content extraction An AI agent connected through Jentic turns a URL or file into clean, structured data: it extracts the readable content or tables, then cleans and converts the result into JSON it can reason over. Because the agent discovers operations from the service catalog by intent, it can go from a raw page to structured output without a developer wiring each utility endpoint. Example prompt: Extract the main content from a web page, then convert and clean the result into a structured JSON record ### Data cleanup and JSON repair The data utilities take unreliable input and make it usable: they repair malformed JSON, validate it against a generated schema, deduplicate records, and convert between formats. An agent that receives broken or inconsistent data can run it through these endpoints before continuing, so downstream steps work with well-formed, validated structures. Example prompt: Repair a malformed JSON payload, generate a schema from it, and validate the repaired document against that schema ### Website auditing The web audit endpoints inspect a site for SEO, security, accessibility, and performance issues and return structured findings. An agent can run a full or targeted audit and summarize what to fix, turning a manual review checklist into a single structured report grounded in the site's actual responses. Example prompt: Run an SEO audit on a given URL and return the structured list of issues found ## Key endpoints | Method | Path | Description | | --- | --- | --- | | POST | `/v1/web/extract` | Extract web page content | | POST | `/v1/document/extract` | Extract document content | | POST | `/v1/data/clean` | Clean a dataset | | POST | `/v1/data/convert` | Convert data between formats | | POST | `/v1/data/json-repair` | Repair malformed JSON | | POST | `/v1/web/seo-audit` | Run a technical SEO audit | | GET | `/catalog` | List available services | ## Key resources - **Web** — Extract content and metadata and run SEO, security, accessibility, and performance audits - **Document** — Extract text and tables, diff documents, and redact personal data - **Data** — Clean, convert, deduplicate, repair, and validate datasets and JSON - **Research** — Search public registries for entities, filings, and scholarly works - **Crypto** — Read-only EVM utilities for Base accounts, contracts, and transactions - **Catalog** — Discover available services and their purchase handoff ## AI readiness This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use. - **Score:** 52 / 100 - **Maturity:** Foundational - **Dimensions:** - Foundational Compliance: 48 / 100 - Developer Experience & Jentic Compatibility: 63 / 100 - AI-Readiness & Agent Experience: 29 / 100 - Agent Usability: 88 / 100 - Security: 100 / 100 - AI Discoverability: 72 / 100 - **View full report:** https://jentic.com/apis/apiacre.com/apiacre/scorecard - **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/ - **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview ### Score it yourself Every API in the directory is allowlisted, so you can re-score it with no key required. - **Score your own API:** https://jentic.com/scorecard.md - **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md ```sh npx @jentic/api-scorecard-cli score ``` ## Why Jentic - **Setup:** Wiring API Acre by hand means learning its per-call x402 USDC settlement on Base and Solana and the input shape of each utility endpoint. Through Jentic you install once, import the API from the Directory, and your agent calls it. - **Permission scoping:** API Acre carries its inputs in the request body, so rules bound which operations your agent may call: you can allow only the web-extraction and data-cleaning operations while leaving the crypto and audit operations out unless you add them. You choose the operations it may use. - **Credential handling:** API Acre needs no API key: its endpoints are open and metered per call through x402 settlement. Jentic One still runs each call from your own self-hosted instance, so request contents stay out of the agent's prompt, logs, and context. - **Discovery method:** Agents search Jentic by intent such as 'extract web content' or 'repair JSON', and Jentic returns the matching API Acre operation with its input schema so the agent calls the right endpoint without browsing the reference docs. ## Related APIs - **Firecrawl** — Firecrawl crawls and extracts web pages into clean markdown or structured data - **Apify** — Apify runs scraping and automation actors for extracting structured web data - **Diffbot** — Diffbot turns web pages into structured entities and can enrich the data API Acre extracts ## FAQ ### What authentication does API Acre use? API Acre's endpoints require no API key per its OpenAPI spec; paid operations settle per call through x402 USDC on Base and Solana. Through Jentic each call runs from your own self-hosted instance, so request contents stay out of the agent's prompt and logs. ### Can I extract and clean data with API Acre? Yes. You can extract content from a web page or document, then clean, convert, deduplicate, repair, and validate the result into structured JSON. The service catalog lists every available utility so an agent can pick the right one for a task. ### Is there an API Acre MCP server? You do not need an MCP server to give your agent API Acre. Jentic connects it directly from the API Directory: import the API and your agent calls its utilities on demand, discovering operations by intent without loading another server's tool definitions into its context. ### Can I limit what my agent is allowed to do with API Acre? Yes. Write a rule that allows only the web-extraction and data-cleaning operations, so the agent can turn pages and datasets into JSON but cannot call the crypto or audit operations unless you add them, and every call it makes is logged for review. API Acre carries its inputs in the request body, so rules bound which operations the agent may call. ### What are the rate limits for API Acre? The OpenAPI spec does not state numeric rate limits for API Acre; paid operations are metered per call through x402 settlement instead. Check the vendor documentation at https://apiacre.com for current limits before running large batches. ### How do I extract web content with API Acre through Jentic? Search Jentic for an intent such as 'extract content from a web page', and it returns the matching operation with its input schema so your agent passes the URL and options correctly. To run it on your own infrastructure, install Jentic One from its GitHub repo.