canonical: https://jentic.com/apis/agentic-endpoints.com/agentic-endpoints # agentic-endpoints The agentic-endpoints API offers pay-per-call utilities that autonomous agents can use without signing up, including web scraping, PDF text extraction, and prompt token compression. It also runs an encrypted namespaced vault for storing and retrieving items, a meeting store that imports transcripts and answers questions over them with citations, and a reachability checker that reports which clients and bots a URL refuses. Paid endpoints answer HTTP 402 with a price and serve the request once payment is signed, while a prepaid credit token can stand in for a per-call signature. ## For AI agents Scrape web pages, extract PDF text, compress prompt tokens, store items in an encrypted vault, and search meeting transcripts, all billed per call. ## Scope Does not host applications, run a long-term database, or serve model inference. Use for on-demand agent utilities like scraping, PDF extraction, token compression, encrypted storage, and meeting transcript search only. ## Capabilities - Scrape a web page and return its extracted text - Extract the text from a PDF document - Compress a prompt's tokens before sending it to an LLM - Store, retrieve, and delete encrypted items in a namespaced vault - Import meeting transcripts and answer questions over them with cited excerpts - Check which common clients and bots can reach a URL and why requests are refused - Compare a stranger's x402 payment challenge against earlier observations for drift ## Use cases ### Pay-Per-Call Agent Utilities An AI agent connecting through Jentic can use the agentic-endpoints utilities on demand without holding an account: it buys a prepaid credit token once, and Jentic injects it on each paid call. The agent scrapes a page, parses a PDF, or compresses a prompt and is debited at list price, with safety blocks and provider failures costing nothing. Example prompt: Buy a prepaid credit token, then call scrape on a target URL and return the extracted text to the user ### Web and Document Text Extraction Turn web pages and PDFs into clean text for a downstream model. The agentic-endpoints API scrapes a URL and extracts its readable text, parses a PDF into text, and can compress the result so it fits a model's context budget. This pairs a crawl step and a cleanup step without standing up your own extraction stack. Example prompt: Scrape a product page, parse any linked PDF spec sheet, and compress the combined text before passing it to a model ### Private Meeting Knowledge Base Import meeting transcripts and ask questions grounded in them. The agentic-endpoints API accepts a raw WebVTT or SRT export, strips timestamps so phrases split across cues still match, and runs full-text search and a summarize step that cites the meeting each claim came from. Items stored as private are kept as ciphertext the service cannot read. Example prompt: Import a Zoom transcript as queryable, then ask summarize a plain-language question and return the answer with its meeting citation ### Agent Reachability Diagnostics Find out whether agents and crawlers can actually reach a site before relying on it. The agentic-endpoints API sends one request as each of nine common clients, reports which are refused and why, and flags robots.txt AI-crawler blocks, a missing llms.txt, and POST-dropping redirects, with a full report covering up to twenty pages and a reproducing command for each refusal. Example prompt: Run reach against a target URL and report which of the nine clients are refused and the likely cause of each refusal ## Key endpoints | Method | Path | Description | | --- | --- | --- | | POST | `/scrape` | Scrape a page and extract its text | | POST | `/pdf-parse` | Extract text from a PDF | | POST | `/compress` | Compress a prompt's tokens | | POST | `/vault/store` | Store an encrypted item in the vault | | POST | `/meetings/import` | Import a meeting transcript | | POST | `/meetings/search` | Full-text search across queryable meetings | | POST | `/reach` | Check whether common clients can reach a URL | ## Key resources - **Utilities** — Scrape pages, parse PDFs, compress prompt tokens, and run an atomic once-key idempotency witness - **Vault** — Store, retrieve, list, check, delete, and rotate tokens for encrypted items in a namespace - **Meetings** — Import transcripts and run full-text search, summarize, get, list, and delete over them - **Credits and payments** — Buy prepaid credit, check balances, claim a free trial credit, and verify x402 payment endpoints ## 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:** 61 / 100 - **Maturity:** AI-Aware - **Dimensions:** - Foundational Compliance: 49 / 100 - Developer Experience & Jentic Compatibility: 68 / 100 - AI-Readiness & Agent Experience: 52 / 100 - Agent Usability: 94 / 100 - Security: 50 / 100 - AI Discoverability: 71 / 100 - **View full report:** https://jentic.com/apis/agentic-endpoints.com/agentic-endpoints/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 the agentic-endpoints API by hand means handling its HTTP 402 pay-per-call flow, buying prepaid credit, and attaching the credit token or a signed x402 payment header on each paid call yourself. Through Jentic you install once, import agentic-endpoints from the API Directory, store the credit token once, and your agent calls it. - **Permission scoping:** You choose which agentic-endpoints operations your agent may call, so scraping and PDF extraction can be allowed while vault deletion or token rotation stay out unless you add them. These endpoints carry their inputs in the request body, so a rule bounds which operations run, not which item a single request names. - **Credential handling:** Your agentic-endpoints credit token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context. - **Discovery method:** Agents search Jentic by intent such as 'scrape a web page' or 'parse a PDF', and Jentic returns the matching agentic-endpoints operation with its input schema so the agent calls the right endpoint without browsing the reference docs. ## Related APIs - **Firecrawl** — Firecrawl crawls sites and returns clean, LLM-ready content. - **Apify** — Apify runs hosted scrapers and actors for structured web data. - **Diffbot** — Diffbot extracts structured entities from web pages and articles. ## FAQ ### What authentication does the agentic-endpoints API use? Paid endpoints accept a prepaid credit token sent in the `X-Credit-Token` header, or a signed payment sent in the `X-PAYMENT` header in response to the HTTP 402 price challenge. A few endpoints, such as a free trial credit and balance checks, need neither. Through Jentic the credit token is injected at call time rather than living in the agent's prompt. ### Can I store secrets in an encrypted vault with the agentic-endpoints API? Yes. The vault store operation claims a namespace and returns a one-time namespace token, and you then store, retrieve, list, check existence, delete, and rotate tokens for items under that namespace. Items stored as private are kept as ciphertext the service cannot read. ### What are the rate limits for the agentic-endpoints API? The OpenAPI spec does not specify rate limits; pricing is pay-per-call and each paid endpoint answers HTTP 402 with its price. Check the documentation at https://agentic-endpoints.com for current limits and prices. ### How do I scrape a web page with the agentic-endpoints API through Jentic? Search Jentic for 'scrape a web page' and it returns the scrape operation with its input schema. Your agent sends the target URL, is debited at list price from your prepaid credit, and gets the extracted text back. To run it on your own infrastructure, install Jentic One from its GitHub repo. ### Can I limit what my agent is allowed to do with the agentic-endpoints API? Yes. Write a rule that allows only the scrape and pdf-parse operations, so the agent can extract text but cannot delete vault items or rotate a namespace token, and every action it takes is logged. Because these operations carry their inputs in the request body, the rule bounds which operations run rather than which item a request names. ### Is there an agentic-endpoints MCP server? You don't need an MCP server to give your agent the agentic-endpoints API. Jentic connects it directly from the API Directory: import it, store your prepaid credit token once, and your agent calls the scrape, parse, compress, vault, and meeting operations on demand without loading another server's tool definitions into its context.