Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the MobileValidate 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%2Fmobilevalidate.com%2Fmobilevalidate" | 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%2Fmobilevalidate.com%2Fmobilevalidate" | 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 MobileValidate API.
Check up to 100 phone numbers and e-mail addresses per lookup for messaging-app registration, carrier, and spam reputation
Estimate the cost of a bulk validation job for free before running it
Run bulk jobs of up to 50,000 numbers and e-mails from JSON or a CSV upload
Page job results filtered by registered, status, or service, or download them as CSV or NDJSON
GET STARTED
Register signed webhook endpoints for lookup.completed, job.completed, and balance.low events
Cap spend per request with max_cost and reuse cached answers with max_age
Report usage and cost by day or by check over a date range
Patterns agents use MobileValidate API for, with concrete tasks.
★ Agent Contact Checks Through Jentic
An AI agent qualifying leads or cleaning a contact list checks each phone number and e-mail before outreach, learning whether the number is on WhatsApp or Telegram and whether the mailbox exists. Through Jentic the agent finds the lookup operation by intent, sends numbers, emails, and checks with a stored key, and branches on the registered field, where false is a conclusive negative and null means unknown.
Run a lookup for numbers ['+447700900001'] and emails ['registered@test.mobilevalidate.com'] with checks ['whatsapp', 'carrier', 'email'] and report the registered value for each
Bulk List Hygiene Before a Campaign
Marketing and CRM teams upload a CSV with a phone or email column as a bulk job, after a free estimate of the maximum cost. Inconclusive, invalid, and duplicate rows are never charged and are released from the reserved amount when the job finishes, and the results download as CSV for re-import.
Estimate a job for 5,000 numbers with checks ['whatsapp'], then create the job, poll it until it completes, and download the results in csv format
Signup Fraud and Spam Screening
Signup and onboarding flows check a new user's number for spam reputation and line type, and their e-mail for account existence, then decide whether to require extra verification. Each POST accepts an Idempotency-Key header so retries after a timeout are not billed twice.
Run a lookup for number '+447700900001' with checks ['spam', 'carrier'] and an Idempotency-Key, and return the spam and line type results
19 endpoints — the mobilevalidate api checks phone numbers and e-mail addresses in real time or in bulk, reporting messaging-app and online-account registration such as whatsapp, telegram, and viber, carrier and line type, spam reputation, and whether an e-mail account exists.
METHOD
PATH
DESCRIPTION
/lookup
Check up to 100 numbers and e-mail addresses
/jobs/estimate
Estimate a bulk job for free
/jobs
Create a bulk job
/jobs/{id}
Get a job
/jobs/{id}/results
List a job's results
/jobs/{id}/download
Download a job's results as CSV or NDJSON
/services
List checks and prices
/lookup
Check up to 100 numbers and e-mail addresses
/jobs/estimate
Estimate a bulk job for free
/jobs
Create a bulk job
/jobs/{id}
Get a job
/jobs/{id}/results
List a job's results
/jobs/{id}/download
Download a job's results as CSV or NDJSON
/services
List checks and prices
What agents get from Jentic-routed access to this vendor.
Setup
Wiring MobileValidate by hand means picking the right key prefix for live, test, or agent mode, handling 202 pending answers with polling or webhooks, and sending Idempotency-Key headers for safe retries. Through Jentic you install once, import MobileValidate from the API Directory, store the key once, and your agent calls it.
Permission scoping
MobileValidate puts the job id in the URL path (/jobs/{id}), so a rule can pin your agent to one job's status, results, and download. Phone numbers and e-mails travel in the request body, so for lookups rules bound which operations your agent may call, and costly or destructive ones like creating bulk jobs or purging results are not included unless you add them.
Credential isolation
Your MobileValidate 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 'check if a phone number is on WhatsApp' or 'validate a list of e-mails', and Jentic returns the matching MobileValidate operation with its input schema so the agent calls the right endpoint without reading the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using MobileValidate API through Jentic.
What authentication does the MobileValidate API use?
The MobileValidate API authenticates with `Authorization: Bearer <key>` per its OpenAPI spec. Keys start with `mv_live_` for billed checks, `mv_test_` for test mode, or `mv_agent_` for AI agents with a daily spend cap. The health check and personal test-key request are public and need no credential, and the services price list works with or without a key. Through Jentic your key is stored once, encrypted, by your own Jentic One instance and injected at call time.
Can I check WhatsApp registration with the MobileValidate API?
Yes. Pass whatsapp in the checks list of a lookup or bulk job, alongside other service codes such as telegram, viber, carrier, or spam; the services operation lists every code and its price. The registered field is false only for a conclusive negative and null when the answer is unknown, and inconclusive answers are never charged.
Can I limit what my agent is allowed to do with the MobileValidate API?
Yes. For example, write a rule that allows only the lookup, estimate, and services operations, so the agent can run real-time checks and price a bulk job but cannot start a 50,000-row job, purge results, or change webhook endpoints, and every call it makes is logged.
What are the rate limits for the MobileValidate API?
The OpenAPI spec states that the public sandbox key is limited per IP address to 30 requests per minute and 1,000 per day. For your own keys, call the limits operation, which returns your limits and remaining allowances, and see https://mobilevalidate.com/docs for current account limits.
How do I validate a phone number with MobileValidate through Jentic?
Search Jentic for the intent 'check if a phone number is on WhatsApp', which returns the MobileValidate lookup operation on /lookup with its input schema; the agent sends numbers in E.164 format and the checks to run, and reads registered from each result row. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Is there a MobileValidate MCP server?
You don't need an MCP server to give your agent the MobileValidate API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls the lookup, job, and webhook operations. Operations are discovered on demand, so no extra tool definitions are loaded into the agent's context.
For Agents
Check whether phone numbers and e-mail addresses are registered on messaging apps and services, look up carrier and spam reputation, and run bulk validation jobs of up to 50,000 rows with MobileValidate. Authenticated with a Bearer key.
Use for: Check whether this phone number has a WhatsApp account, I need to validate a list of 20,000 customer phone numbers, Find out the carrier and line type for a mobile number, Estimate how much a bulk check of my CSV will cost
Not supported: Does not send SMS or e-mail, verify ownership with one-time codes, or enrich contacts with names and social profiles. Use for phone and e-mail registration, carrier, and reputation checks only.
The MobileValidate API checks phone numbers and e-mail addresses in real time or in bulk, reporting messaging-app and online-account registration such as WhatsApp, Telegram, and Viber, carrier and line type, spam reputation, and whether an e-mail account exists. Real-time lookups take up to 100 identifiers per request and wait a configurable number of seconds for answers, while bulk jobs accept up to 50,000 rows as JSON or a CSV upload, with a free cost estimate first. Results page by registered, status, or service and download as CSV or NDJSON, and signed webhooks report events such as lookup.completed, job.completed, and balance.low.
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>