Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the MailGlyph 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%2Fmailglyph.com%2Fmailglyph" | 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%2Fmailglyph.com%2Fmailglyph" | 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 MailGlyph API.
Send a transactional email to a single recipient with a stored template or inline content
Create and schedule marketing campaigns, then read their delivery and open statistics
Validate a single email address in real time and run bulk verification jobs against uploaded lists
Group contacts into segments and add or remove members for targeted sends
GET STARTED
Verify sending domains and build reusable templates for repeated messages
Inspect automation workflows and their execution history
Patterns agents use MailGlyph API for, with concrete tasks.
★ AI Agent Email Automation
Connect an AI agent to MailGlyph so it can send transactional messages, launch campaigns, and validate addresses on demand. The agent discovers the send and campaign operations through Jentic, stores the MailGlyph key once, and triggers email without hand-written SDK wiring. Delivery events flow back so the agent can confirm each message landed.
Send a transactional welcome email to a new contact using a stored template and confirm the delivery event was recorded
Transactional Email Delivery
Send password resets, receipts, and notifications straight from your application. MailGlyph accepts a template id or inline HTML, records each delivery event, and exposes event names for filtering. Public tracking keys let client-side code report engagement without exposing the secret key.
Send a receipt email to a customer address and poll the events list until the delivery event appears
Email List Verification
Clean large mailing lists before a campaign to cut bounces. MailGlyph validates single addresses in real time and runs bulk verification jobs that consume prepaid credits, with a downloadable results file and a credit ledger for tracking usage. A paused job can be continued to finish an oversized list.
Create a bulk email validation job for an uploaded address list and download the results when the job completes
Campaign Management
Build, test, and schedule marketing campaigns to targeted segments. MailGlyph sends test copies before launch, schedules or cancels a send, and reports per-campaign statistics so you can measure open and delivery performance across segments.
Create a campaign targeting a contact segment, send a test email, then schedule the campaign and retrieve its stats
48 endpoints — the mailglyph api sends transactional and marketing email, runs multi-step campaigns, and validates recipient addresses before delivery.
METHOD
PATH
DESCRIPTION
/v1/send
Send a transactional email
/campaigns
Create a campaign
/campaigns/{id}/send
Send or schedule a campaign
/v1/verify
Validate a single email address
/v1/verify/files
Create a bulk email validation job
/contacts
List contacts
/segments/{id}/members
Add members to a segment
/v1/send
Send a transactional email
/campaigns
Create a campaign
/campaigns/{id}/send
Send or schedule a campaign
/v1/verify
Validate a single email address
/v1/verify/files
Create a bulk email validation job
/contacts
List contacts
/segments/{id}/members
Add members to a segment
What agents get from Jentic-routed access to this vendor.
Setup
Wiring MailGlyph by hand means learning its bearer-token auth, separating secret from public keys, and polling delivery events yourself. Through Jentic you install once, import MailGlyph from the API Directory, store the key, and your agent calls the operation it needs.
Permission scoping
You decide which MailGlyph operations your agent may call. A rule can grant the transactional send and address-validation operations while withholding domain deletion and contact removal, and because the recipient travels in the request body, the rule bounds operations rather than a single address.
Credential isolation
Your MailGlyph 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 'send a transactional email' or 'validate an email address', and Jentic returns the matching MailGlyph 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 MailGlyph API through Jentic.
What authentication does the MailGlyph API use?
The MailGlyph API authenticates with a bearer token in the Authorization header, per its OpenAPI spec. Secret keys authenticate server-side requests, while public keys are limited to the client-side event tracking endpoint. Through Jentic your MailGlyph key is stored encrypted by your own Jentic One instance and injected when a call runs, so it never enters the agent's prompt or logs.
Can I validate email addresses with the MailGlyph API?
Yes. The API validates a single address in real time and also runs bulk validation jobs that check an uploaded list against your prepaid verification credits. You can download the results file and review a credit ledger to track usage.
What are the rate limits for the MailGlyph API?
The OpenAPI spec does not publish specific rate limits. Check the MailGlyph documentation at https://docs.mailglyph.com for current limits, and design your agent to handle throttling responses gracefully.
How do I send email with the MailGlyph API through Jentic?
Search Jentic for an intent like 'send a transactional email', and it returns the MailGlyph send operation with its input schema. Import the connector once, store your key, and your agent posts to the send operation without hand-written HTTP code. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Is there a MailGlyph MCP server?
You don't need an MCP server to give your agent MailGlyph. Jentic connects it directly from the Jentic API Directory: import the API, store your key once, and your agent calls the send, campaign, and validation operations. Operations are discovered on demand, so no extra tool definitions are loaded into the agent's context.
Can I limit what my agent is allowed to do with the MailGlyph API?
Yes. You choose the operations the agent may call, so a rule can allow just the send and validation operations while leaving campaign deletion or contact removal out unless you add them. MailGlyph carries the recipient inside the request body, so a rule bounds which operations run rather than which individual contact is emailed, and every call is logged.
Know of an official OpenAPI document? Contribute it →
For Agents
Send transactional and marketing email, run campaigns, validate addresses, and organize contacts, segments, and templates through the MailGlyph API.
Use for: I want to send a transactional email with a template, Send a marketing campaign to a contact segment, Validate a batch of email addresses before a send, Check the delivery stats for a campaign
Not supported: Does not handle SMS, push notifications, or voice messaging. Use it for email sending, campaigns, and address validation only.
The MailGlyph API sends transactional and marketing email, runs multi-step campaigns, and validates recipient addresses before delivery. It stores contacts, segments, and reusable templates, drives automation workflows, and reports delivery events and per-campaign statistics for every send. Bulk verification jobs check large address lists against prepaid verification credits so lists stay clean before a launch.
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>