Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the FastAF API, 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%2Ffastaf.co%2Ffastaf" | 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%2Ffastaf.co%2Ffastaf" | 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 FastAF API.
Pull search engine results for a query with the SERP endpoint
Scrape a web page and capture a screenshot of it
Search Google Maps for places and place details
Fetch Amazon and Walmart product and search results
Retrieve news, shopping, scholarly, and job search results
GET STARTED
Read account usage, recent requests, and the credit balance
Patterns agents use FastAF API for, with concrete tasks.
★ Search and SERP Data Collection
A research workflow needs fresh search data across sources. The FastAF API returns search engine results for a query and has focused endpoints for news, shopping, scholarly results, and jobs, so an agent can gather and compare results from several verticals without maintaining its own scrapers.
Pull SERP results for a query, then fetch news results for the same topic and return the combined findings
Web Scraping and Screenshots
A monitoring agent captures how a page looks and reads its content. The FastAF API scrapes a target URL into structured content and captures a screenshot of the same page, and can pull Google Maps or Amazon data for a specific place or product, so an agent can both read and image a page in one pass.
Scrape a target URL for its content, then capture a screenshot of the same page
AI Agent Web Data via Jentic
An AI agent collects live web data through Jentic without holding the FastAF key itself. It searches by intent, receives the matching operation and its input schema, and runs SERP, scrape, or screenshot calls with the credential injected at run time, so a research or monitoring step fits into a larger workflow while credits are tracked.
Search Jentic for 'get search results for a query', load the SERP operation schema, and run it with Jentic-managed credentials
37 endpoints — the fastaf api turns the live web into structured data, billed in fastaf credits.
METHOD
PATH
DESCRIPTION
/v1/serp
Pull search engine results
/v1/scrape
Scrape a web page
/v1/screenshot
Capture a web page screenshot
/v1/maps
Search Google Maps or place details
/v1/news
Pull news search results
/v1/shopping
Pull shopping search results
/v1/usage
Read current usage and credit balance
/v1/serp
Pull search engine results
/v1/scrape
Scrape a web page
/v1/screenshot
Capture a web page screenshot
/v1/maps
Search Google Maps or place details
/v1/news
Pull news search results
/v1/shopping
Pull shopping search results
/v1/usage
Read current usage and credit balance
What agents get from Jentic-routed access to this vendor.
Setup
Wiring FastAF by hand means carrying its bearer key, choosing between the GET and POST form of each data endpoint, and watching your credit balance across calls yourself. Through Jentic you install once, import FastAF from the API Directory, store the key once, and your agent calls it.
Permission scoping
FastAF carries the query and target URL in the request, so rules bound which operations your agent may call, not which site. Limit the agent to the search and scrape operations it needs, so API-key management and the billing-portal operation are not included unless you add them.
Credential isolation
Your FastAF key 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 'get search results for a query' or 'scrape a web page', and Jentic returns the matching FastAF 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 FastAF API through Jentic.
What authentication does the FastAF API use?
The FastAF API authenticates with a bearer API key in the Authorization header on every data and account operation per its OpenAPI spec. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at execution time, so it never reaches the agent.
Can I scrape a page and capture a screenshot with the FastAF API?
Yes. The scrape operation returns a target page's content and the screenshot operation captures an image of the same URL, each available as a GET or a POST. Dedicated endpoints also return structured data from Google Maps, Amazon, Walmart, news, shopping, and more.
What are the rate limits for the FastAF API?
The OpenAPI spec does not specify numeric rate limits for the FastAF API; usage is billed in FastAF credits instead. The usage and daily-usage operations report consumption and the credit balance, so an agent can check its remaining credits before running more calls.
How do I get search results with the FastAF API through Jentic?
Search Jentic for 'get search results for a query' and it returns the FastAF SERP operation with its input schema. Load the schema, pass the query, and the key is injected at run time. 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 FastAF API?
Yes. FastAF carries the query and target URL in the request, so a rule bounds which operations your agent may call. Limit it to the search and scrape operations it needs, and leave API-key management and the billing portal out unless you add them. Every call runs through your own instance where it is logged.
Is there a FastAF API MCP server?
You don't need an MCP server to give your agent the FastAF API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls the SERP, scrape, and screenshot operations it needs without a separate server to install.
For Agents
Pull SERP results, scrape pages and capture screenshots, and fetch structured results from Google Maps, Amazon, news, shopping, and more. Track credit usage. Authenticated with a bearer API key.
Use for: Get Google search results for a query, Scrape the content of a web page, Capture a screenshot of a web page, Search Google Maps for a place
Not supported: Does not handle data storage, proxy management, or CAPTCHA solving. Use for scraping web pages and pulling search results only.
The FastAF API turns the live web into structured data, billed in FastAF credits. It pulls search engine results, scrapes web pages, and captures page screenshots, and it has dedicated endpoints for Google Maps places, Amazon and Walmart products, news, shopping, trends, scholarly results, jobs, YouTube, LinkedIn, and X profiles. Account endpoints report usage, recent requests, and the credit balance, and manage API keys. Each data endpoint accepts a GET or a POST request.
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>