Install Jentic One Beta

Connect the LayerCall API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the LayerCall 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%2Flayercall.com%2Flayercall" | sh

Step 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%2Flayercall.com%2Flayercall" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic 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.

Capabilities

What an agent can do with LayerCall API.

Detect VPNs, proxies, Tor exit nodes, and datacenter IPs and return country, city, ASN, and ISP for an address

Score an entire signup in one call from its ip, email, phone, domain, and device_id

Verify and score an email address, and validate a phone number with an optional country

Score up to 500 IPs, emails, domains, or phones of one type in a single batch request

GET STARTED

Start building with LayerCall API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use LayerCall API for, with concrete tasks.

★ Agent-run signup screening through Jentic

An AI agent triaging new signups can send the applicant's IP, email, and phone to LayerCall's user-scoring operation and act on the verdict: approve on allow, queue for a human on review, reject on block. Through Jentic the agent finds the operation by intent and the API key is injected at call time, and a rule can keep the agent to scoring operations so it cannot rewrite your allow and block rules.

Call POST /v1/score/user with ip '185.220.101.5', email 'new.user@example.com', and phone '+14155550123', then approve the account only if verdict is 'allow'

Signup and checkout fraud scoring

Fake accounts and fraudulent checkouts often share tells: a datacenter IP, a throwaway email, a VoIP phone number. LayerCall scores each signal separately or combines them in one user-scoring call, and the strictness parameter shifts the allow, review, and block thresholds without changing the underlying risk_score, so each flow can be tuned on its own.

Call GET /v1/score/ip with ip '203.0.113.42' and strictness 'strict', and flag the order for review if signals.is_vpn or signals.is_proxy is true

Bulk list cleanup

Marketing lists and user exports accumulate bad addresses and numbers over time. The LayerCall batch operation takes a type of ip, email, domain, or phone and up to 500 items per request, so an existing list can be scored in a few calls and the high-risk entries removed.

Call POST /v1/batch with type 'email' and items set to the 250 addresses from the export, then return the ones whose verdict is 'block'

Verifying AI agent traffic

Sites that accept agent traffic need to know which agent is calling rather than trusting a User-Agent string. LayerCall verifies HTTP Message Signatures (RFC 9421, Web Bot Auth) from a request's url and headers, and the authorize operation checks the request against the agent policy you set with the policy operations.

Call POST /v1/agent/authorize with the incoming request's url, method 'GET', and its signature headers, and serve the page only if the decision allows it

Key Endpoints

19 endpoints — the layercall api scores ip addresses, email addresses, phone numbers, domains, and device fingerprints for fraud risk, returning a risk_score from 0 to 100 and an allow, review, or block verdict.

METHOD

PATH

DESCRIPTION

POST

/v1/score/user

Score a whole signup

GET

/v1/score/ip

Score an IP address

GET

/v1/verify/email

Verify and score an email

GET

/v1/lookup/phone

Validate and score a phone number

POST

/v1/batch

Score up to 500 values at once

POST

/v1/outcome

Label a past score

POST

/v1/verify/agent

Verify an agent's message signature

POST

/v1/score/user

Score a whole signup

GET

/v1/score/ip

Score an IP address

GET

/v1/verify/email

Verify and score an email

GET

/v1/lookup/phone

Validate and score a phone number

POST

/v1/batch

Score up to 500 values at once

POST

/v1/outcome

Label a past score

POST

/v1/verify/agent

Verify an agent's message signature

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring LayerCall by hand means choosing between the x-api-key header and a bearer token, handling 429 responses when the rate limit is hit, and shaping separate calls for each signal type. Through Jentic you install once, import LayerCall from the API Directory, store the key once, and your agent calls it.

Permission scoping

LayerCall carries the values being scored in query strings and request bodies, so rules bound which operations your agent may call, not which IPs or emails it checks. You choose the operations it may call, so destructive ones like deleting every rule or replacing the agent policy are not included unless you add them.

Credential isolation

Your LayerCall 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 'score a signup for fraud' or 'check if an IP is a VPN', and Jentic returns the matching LayerCall operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

FAQs

Specific to using LayerCall API through Jentic.

Is there a LayerCall MCP server?

You don't need an MCP server to give your agent the LayerCall API. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent calls it. Operations are discovered on demand, so your agent's context carries no tool definitions it will not use.

What authentication does the LayerCall API use?

Per its OpenAPI spec, LayerCall accepts your API key in the x-api-key header, or the same key as a bearer token in `Authorization: Bearer <key>`. Through Jentic, the key is stored encrypted by your own Jentic One instance and injected at execution time, so it never enters the agent's context.

Can I score a whole signup in one call with the LayerCall API?

Yes. POST /v1/score/user accepts ip, email, phone, phone_country, domain, device_id, device_signals, and device_automation, and returns one risk_score with an allow, review, or block verdict. GET /v1/score/user takes the same core fields as query parameters.

What are the rate limits for the LayerCall API?

The OpenAPI spec documents an x-ratelimit-limit response header of 600 requests per minute, with x-ratelimit-remaining showing what is left in the current minute, and a 429 response when you exceed it. The spec description also states a free tier of 1,000 lookups per month.

How do I check an IP address with LayerCall through Jentic?

Install Jentic One with `curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh`, import the LayerCall API from the directory, and store your API key. Your agent then searches for 'score an IP address' and Jentic returns GET /v1/score/ip, which takes the address in the ip parameter. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Can I tell LayerCall when a score was wrong?

Yes. POST /v1/outcome takes the request_id of a past score and an outcome of fraud or legit. To flag a value directly, POST /v1/report takes a kind of ip, email, domain, or phone with a value or list of values.

Can I limit what my agent is allowed to do with the LayerCall API?

Yes. For a screening assistant, write a rule that allows only POST /v1/score/user, GET /v1/score/ip, and GET /v1/verify/email: the agent can score signups and check IPs and emails, but cannot change your agent policy or touch your rules, and every call it makes is logged.

LayerCall API

AI ReadinessFoundational (C-)53/100

See full scorecard

Official vendor OpenAPI document · agent-readySecurityThreat DetectionapiKey (x-api-key header), bearer19 EndpointsREST

For Agents

Score signups, IPs, emails, phones, domains, and devices for fraud risk with an allow, review, or block verdict, label outcomes, and manage allow and block rules.

Use for: I need to check whether this signup looks fraudulent before approving it, Check whether IP 185.220.101.5 is a Tor exit node or VPN, Verify that a customer's email address is deliverable and not disposable, Score a list of 300 email addresses from yesterday's signups

Not supported: Does not handle payment processing, chargeback disputes, user login, or KYC document checks. Use for risk scoring of IPs, emails, phones, domains, devices, and signups only.

The LayerCall API scores IP addresses, email addresses, phone numbers, domains, and device fingerprints for fraud risk, returning a risk_score from 0 to 100 and an allow, review, or block verdict. An IP check flags VPNs, proxies, Tor exit nodes, and datacenter ranges with geo and ASN context, and a single user-scoring call combines IP, email, phone, domain, and device signals for a whole signup. It also scores up to 500 values of one type in a batch, takes fraud reports and outcome labels as feedback, verifies AI agent HTTP Message Signatures, and maintains your own allow and block rules.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: CSignals: 4

84%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

Specification Validity

Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).

35%

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: B+Signals: 4

29%

Example Density

How richly the API is illustrated with examples.

98%

Example Validity

Percentage of examples that conform to their schemas.

43%

Response Coverage

Percentage of operations with complete response definitions (success, client error, server error).

100%

Tooling Readiness

Health of API ingestion, bundling, and resolution within Jentic pipelines.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: FSignals: 4

32%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

37%

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

57%

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A+Signals: 1

94%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: CSignals: 1

55%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: A-Signals: 1

73%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the LayerCall API to your agent

Capabilities

Start building with LayerCall API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

LayerCall API

Jentic AI Readiness Score

LayerCall API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness