Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Piloterr API Reference, 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%2Fpiloterr.com%2Fpiloterr" | 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%2Fpiloterr.com%2Fpiloterr" | 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 Piloterr API Reference API.
Scrape Google search results, AI Mode answers, images, news, videos, shopping, maps, and job listings for a query
Extract LinkedIn profile, company, job posting, and post data, and count LinkedIn jobs by keyword, job_type, and experience_level
Retrieve Amazon, Walmart, and other retailer product details with pricing and offers
Look up company and funding data from Crunchbase, Trustpilot, G2, Similarweb, and the Piloterr company database
GET STARTED
Render pages, capture website screenshots, unlock antibot-protected pages, and detect technology stacks
Find and verify email addresses from a company_domain or company_name, and extract emails and phone numbers from websites
Search property listings on portals such as Zillow, Rightmove, Idealista, and SeLoger
Patterns agents use Piloterr API Reference API for, with concrete tasks.
★ AI Agent Data Collection Pipeline
AI agents use the Piloterr API through Jentic to run multi-source data extraction without configuring individual scrapers. Agents search for extraction operations by intent, load the endpoint schema, and execute the call, with Jentic injecting the x-api-key header from your own Jentic One instance.
Search Jentic for 'extract LinkedIn company profile', load the Piloterr LinkedIn endpoint schema, and retrieve company data for a target organization
Lead Research and Enrichment
Build comprehensive company and contact profiles by combining data from LinkedIn, Crunchbase, and business directories. Piloterr extracts company details, employee profiles, funding rounds, and contact information across multiple sources through a single API, replacing manual research with automated data collection.
Extract LinkedIn company info for 'acme-corp', retrieve their Crunchbase funding data, and find email addresses for their domain
Competitive Intelligence Monitoring
Monitor competitors across search rankings, product reviews, and web traffic. The API scrapes Google search positions, Trustpilot company pages and G2 product reviews, Amazon product listings, and Similarweb domain data, so an agent can assemble a competitive snapshot without manual browsing.
Search Google for 'project management software', extract Trustpilot ratings for the top 3 companies, and get their Similarweb traffic data
E-Commerce Product Data Extraction
Extract product listings, pricing, offers, and availability from Amazon, Walmart, Best Buy, Shopify stores, and European retailers such as Fnac, Cdiscount, and MediaMarkt. The API returns structured product data including titles, prices, ratings, and seller information for price comparison, product listing enrichment, and market analysis.
Retrieve Amazon product details for ASIN B09V3KXJPB including price, ratings, and available offers
Website Analysis and Contact Extraction
Analyze websites for technology stacks, capture screenshots, check domain reputation, and extract contact information. The API identifies frameworks, CMS platforms, and analytics tools while also finding email addresses and phone numbers published on site pages.
Detect the technology stack on example.com, capture a screenshot, and extract any email addresses found on the site
778 endpoints — the piloterr api scrapes public web sources and returns structured json: search engines such as google, bing, brave, duckduckgo, and yahoo, professional networks such as linkedin, crunchbase, and indeed, and retail, real-estate, and marketplace sites from amazon and walmart to zillow, idealista, and leboncoin.
METHOD
PATH
DESCRIPTION
/v2/google/search
Scrape Google search results for a query
/v2/linkedin/profile/info
Extract a LinkedIn profile
/v2/linkedin/company/info
Extract LinkedIn company data
/v2/amazon/product
Retrieve Amazon product details
/v2/email/finder
Find email addresses for a company
/v2/email/verify
Verify email deliverability
/v2/website/technology
Detect website technology stack
/v2/crunchbase/company/info
Look up Crunchbase company data
/v2/google/search
Scrape Google search results for a query
/v2/linkedin/profile/info
Extract a LinkedIn profile
/v2/linkedin/company/info
Extract LinkedIn company data
/v2/amazon/product
Retrieve Amazon product details
/v2/email/finder
Find email addresses for a company
/v2/email/verify
Verify email deliverability
/v2/website/technology
Detect website technology stack
/v2/crunchbase/company/info
Look up Crunchbase company data
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Piloterr API by hand means setting up its x-api-key header auth, picking the right operation among hundreds of per-source scrapers, and choosing between the GET and POST form of each. Through Jentic you install once, import Piloterr from the API Directory, store the API key once, and your agent calls it.
Permission scoping
Piloterr takes its target in the query parameter rather than a resource id in the path, so scoping is by operation: you limit the agent to the operations it needs, such as a Google search or LinkedIn profile lookup. You choose that set, so an unlisted operation like email finding stays unavailable unless you add it.
Credential isolation
Your Piloterr API 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 'scrape LinkedIn company data' or 'verify an email address', and Jentic returns the matching Piloterr operation with its input schema so the agent calls the right endpoint without browsing hundreds of scrapers.
Alternatives and complements available in the Jentic catalogue.
Specific to using Piloterr API Reference API through Jentic.
Is there a Piloterr MCP server?
You don't need an MCP server to give your agent the Piloterr API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls it. Because the API spans hundreds of operations, the agent discovers the one it needs on demand instead of loading every tool definition into its context.
What authentication does the Piloterr API use?
The Piloterr API authenticates with an API key sent in the x-api-key header, per its OpenAPI spec. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at call time, so it never enters the agent's prompt or logs.
Can I scrape LinkedIn profiles and company data with the Piloterr API?
Yes. GET /v2/linkedin/profile/info extracts an individual profile and GET /v2/linkedin/company/info retrieves a company page, with an optional domain parameter. Further operations cover job search, job count, job details, product, and post information from LinkedIn.
Can I verify email addresses with the Piloterr API?
Yes. GET /v2/email/verify checks deliverability, GET /v2/email/finder finds an address from a person's name together with company_domain or company_name, and GET /v2/email/analyzes returns a detailed analysis of an address.
What are the rate limits for the Piloterr API?
The OpenAPI spec does not specify rate limits; it lists a credit cost per operation, such as 1 credit per call for LinkedIn Company Info and Email Finder. GET /v2/usage returns real-time usage statistics and your credit balance, and https://www.piloterr.com lists current plan limits.
How do I extract company data through the Piloterr API using Jentic?
Search Jentic for 'extract LinkedIn company profile' and it returns GET /v2/linkedin/company/info with its input schema; call it with the company's LinkedIn URL or slug as query and the agent gets structured company data 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 Piloterr API?
Yes. Write a rule that allows only GET /v2/google/search and GET /v2/linkedin/company/info, so a research agent can run searches and read company pages while email finding, website rendering, and the retailer scrapers stay unavailable, and every call it makes is logged by your self-hosted instance.
For Agents
Extract structured data from search engines, LinkedIn, Crunchbase, job boards, retailers, and real-estate portals, and run website rendering, screenshots, technology detection, email finding, and domain checks.
Use for: I need to scrape Google search results for a keyword, I want to extract a LinkedIn company profile, Retrieve product details from Amazon by ASIN, Find email addresses associated with a domain
Not supported: Does not handle data storage, CRM record management, or outreach automation. Use for public web data extraction and enrichment only.
The Piloterr API scrapes public web sources and returns structured JSON: search engines such as Google, Bing, Brave, DuckDuckGo, and Yahoo, professional networks such as LinkedIn, Crunchbase, and Indeed, and retail, real-estate, and marketplace sites from Amazon and Walmart to Zillow, Idealista, and Leboncoin. Website tools render pages, take screenshots, detect technology stacks, unlock antibot-protected pages, and extract emails and phone numbers, while email and domain operations find and verify addresses and run WHOIS, malicious-domain, and DNSBL checks. Most operations are offered as both GET with query parameters and POST, under the /v2 path prefix.
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>