Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the agentic-endpoints, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fagentic-endpoints.com%2Fagentic-endpoints" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fagentic-endpoints.com%2Fagentic-endpoints" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with agentic-endpoints API.
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
GET STARTED
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
Patterns agents use agentic-endpoints API for, with concrete tasks.
★ 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.
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.
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.
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.
Run reach against a target URL and report which of the nine clients are refused and the likely cause of each refusal
26 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.
METHOD
PATH
DESCRIPTION
/scrape
Scrape a page and extract its text
/pdf-parse
Extract text from a PDF
/compress
Compress a prompt's tokens
/vault/store
Store an encrypted item in the vault
/meetings/import
Import a meeting transcript
/meetings/search
Full-text search across queryable meetings
/reach
Check whether common clients can reach a URL
/scrape
Scrape a page and extract its text
/pdf-parse
Extract text from a PDF
/compress
Compress a prompt's tokens
/vault/store
Store an encrypted item in the vault
/meetings/import
Import a meeting transcript
/meetings/search
Full-text search across queryable meetings
/reach
Check whether common clients can reach a URL
What agents get from Jentic-routed access to this vendor.
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 isolation
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.
Intent-based discovery
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.
Alternatives and complements available in the Jentic catalogue.
Specific to using agentic-endpoints API through Jentic.
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.
For Agents
Scrape web pages, extract PDF text, compress prompt tokens, store items in an encrypted vault, and search meeting transcripts, all billed per call.
Use for: Scrape the text from a web page, Extract the text from a PDF document, Compress a long prompt before sending it to a model, Store a secret in an encrypted vault
Not supported: 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.
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.
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.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>