Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the EmailKind 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%2Femailkind.com%2Femailkind" | 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%2Femailkind.com%2Femailkind" | 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 EmailKind API.
Classify a single email address or domain by provider and type
Label an address as business, personal, disposable, education, or role
Classify up to 100 emails or domains in one batch call
Identify a disposable or role-based address before accepting a signup
Issue a free API key programmatically through the signup endpoints
GET STARTED
Patterns agents use EmailKind API for, with concrete tasks.
★ Agent signup screening
An AI agent decides what to do with a new signup. Through Jentic the agent classifies the email at registration and reads back its provider and type, so it can wave through a business or personal address and hold a disposable or role account for review. No message is sent to the address during the check.
Classify a new signup's email and flag it when the type is disposable or role
Batch list classification
A workflow cleans an existing list. The batch operation classifies up to 100 emails or domains in one call and returns each one's provider and type, so an agent can segment a list into business, personal, education, and role buckets, or drop disposable addresses, in a few requests. The analysis is passive DNS, so nothing is emailed.
Classify a batch of up to 100 addresses and group them by the returned type
Role and disposable filtering
A signup flow keeps role and throwaway accounts out. The classify call identifies disposable providers and role addresses such as info or support, so an agent can apply a different rule to them, like requiring extra verification. Business and education addresses are labeled distinctly for onboarding logic.
Classify an address and require extra verification when it is labeled disposable or role
4 endpoints — the emailkind api classifies an email address or domain by its provider and type, labeling it as business, personal, disposable, education, or role, using passive dns analysis rather than sending any message.
METHOD
PATH
DESCRIPTION
/classify
Classify one email address or domain
/classify/batch
Classify up to 100 emails or domains
/signup
Start a programmatic signup for a free key
/signup/confirm
Exchange the confirmation code for a key
/classify
Classify one email address or domain
/classify/batch
Classify up to 100 emails or domains
/signup
Start a programmatic signup for a free key
/signup/confirm
Exchange the confirmation code for a key
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the EmailKind API by hand means handling its bearer key, minting one through the public signup endpoints first, and mapping its provider and type labels into your own signup logic. Through Jentic you install once, import EmailKind from the API Directory, store the key once, and your agent calls it.
Permission scoping
EmailKind is a small API, so a rule bounds your agent to the classify operations it needs: classifying one address or a batch. The public signup operations that mint a key are not something the agent needs to call at run time.
Credential isolation
Your EmailKind 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 'classify an email address' or 'detect a disposable domain', and Jentic returns the matching EmailKind 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 EmailKind API through Jentic.
What authentication does the EmailKind API use?
The EmailKind API authenticates the classify operations with a bearer API key per its OpenAPI spec, sent as `Authorization: Bearer sk_live_...`. The two signup endpoints are public so you can mint a free key programmatically. 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 context.
Is there an EmailKind MCP server?
You don't need an MCP server to give your agent the EmailKind API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls the classify and batch operations on demand without loading another server's tool definitions into its context.
Can I detect disposable email addresses with the EmailKind API?
Yes. The classify operation labels an address or domain as business, personal, disposable, education, or role based on passive DNS analysis, and the batch operation applies the same labels to up to 100 inputs at once. No email is ever sent during the check.
What are the rate limits for the EmailKind API?
The OpenAPI spec does not state specific rate limits. Check the provider's documentation at https://emailkind.com for the limits that apply to your key before classifying large lists.
Can I limit what my agent is allowed to do with the EmailKind API?
Yes. Write a rule that allows your agent only the classify and batch operations, so it can label addresses but the key-minting signup operations stay out of its reach. Every call it makes is logged.
How do I classify an email address with the EmailKind API through Jentic?
Search Jentic for 'classify an email address' and it returns the classify operation with its input schema; your agent passes an address or domain and reads back its provider and type. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Classify an email address or domain by provider and type, business, personal, disposable, education, or role, via passive DNS, one at a time or in batches of up to 100.
Use for: Classify this email address by provider and type, Check whether a domain is a disposable email provider, Find out if an address is a role account like info or support, Classify a batch of signup emails in one call
Not supported: Does not send email, verify mailbox deliverability, or find addresses for a domain. Use for classifying email addresses and domains by provider and type only.
The EmailKind API classifies an email address or domain by its provider and type, labeling it as business, personal, disposable, education, or role, using passive DNS analysis rather than sending any message. A single classify call handles one address or domain, and a batch call classifies up to 100 at once. Two public signup endpoints issue a free key programmatically so an agent can start without a dashboard.
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>