Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Cooper Email 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%2Fcooperemail.com%2Fcooperemail" | 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%2Fcooperemail.com%2Fcooperemail" | 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 Cooper Email API.
Create permanent or temporary email inboxes, one at a time or in batches
Send mail with text, HTML, and attachments from an inbox
List and full-text search the messages in an inbox
Reply, reply-all, and forward on an existing thread
Hold with a wait operation until unread mail arrives
GET STARTED
Register a message.received webhook for new inbound mail
Patterns agents use Cooper Email API for, with concrete tasks.
★ Agent-owned mailbox
An AI agent connected through Jentic creates its own inbox, sends mail, and reads replies entirely over HTTP, with no SMTP or IMAP client. It can make each send idempotent with a client_id or an Idempotency-Key header so a retry does not send twice.
Create an inbox, send a message with a subject and body, and list the inbox messages to confirm it was sent
Signup and verification capture
A test or onboarding flow spins up a temporary inbox, triggers a signup, and uses the wait operation to hold until the verification email arrives, then full-text searches the inbox for the confirmation link. Temporary inboxes can be given a ttl so they clean themselves up.
Create a temporary inbox, wait for unread mail, then search the inbox for the verification message and return its body
Thread-aware mail handling
A support or assistant workflow lists new messages, replies on the same thread with replyToMessage, and forwards items that need another recipient. Allow and block lists are checked before sending, so a blocked recipient returns an error instead of delivering.
List the newest messages in an inbox and reply on the thread of the most recent one
135 endpoints — the cooper email api creates email inboxes and sends and receives mail over http, so an agent can own a working mailbox without an smtp or imap setup.
METHOD
PATH
DESCRIPTION
/api/v1/inboxes
Create an inbox
/api/v1/inboxes
List inboxes
/api/v1/inboxes/{id}/messages
List messages in an inbox
/api/v1/inboxes/{id}/messages
Send a message from an inbox
/api/v1/inboxes/{id}/messages/search
Full-text search messages in an inbox
/api/v1/inboxes/{id}/messages/{msgId}/reply
Reply on the same thread
/api/v1/inboxes/{id}/wait
Wait until unread mail arrives
/api/v1/inboxes
Create an inbox
/api/v1/inboxes
List inboxes
/api/v1/inboxes/{id}/messages
List messages in an inbox
/api/v1/inboxes/{id}/messages
Send a message from an inbox
/api/v1/inboxes/{id}/messages/search
Full-text search messages in an inbox
/api/v1/inboxes/{id}/messages/{msgId}/reply
Reply on the same thread
/api/v1/inboxes/{id}/wait
Wait until unread mail arrives
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Cooper Email API by hand means issuing a bearer key, learning the inbox-scoped path layout, and wiring idempotency and the message.received webhook yourself. Through Jentic you install once, import Cooper Email from the API Directory, store the key once, and your agent calls it.
Permission scoping
Cooper Email puts the inbox id in the URL path (/api/v1/inboxes/{id}/...), so a rule can pin your agent to one inbox. You choose the operations it may call, so destructive ones like deleting an inbox are not included unless you add them.
Credential isolation
Your Cooper Email 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 an email' or 'wait for a verification message', and Jentic returns the matching Cooper Email operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Cooper Email API through Jentic.
What authentication does the Cooper Email API use?
The Cooper Email API authenticates with a bearer API key in the Authorization header, per its OpenAPI spec, and a few endpoints such as the public username check are open. Through Jentic the key is stored once by your own self-hosted instance and injected when a call runs, so it never appears in the agent's prompt or logs.
Can I receive inbound email with the Cooper Email API?
Yes. Read inbound mail by listing or searching the messages in an inbox, use the wait operation to hold until unread mail arrives, or register a message.received webhook so new mail is pushed to your URL. You can then reply or forward on the same thread.
Can I limit what my agent is allowed to do with the Cooper Email API?
Yes. Cooper Email puts the inbox id in the URL path, so a rule can pin your agent to one inbox and the send and read operations you choose, so it cannot delete inboxes or touch other mailboxes on the account, and every call it makes is logged.
What are the rate limits for the Cooper Email API?
The spec notes specific limits on some operations, such as the wait operation allowing at most five concurrent waits per key before returning a rate-limited response. Check the Cooper Email documentation for the current per-plan sending and request limits before high-volume use.
Is there a Cooper Email MCP server?
You don't need an MCP server to give your agent the Cooper Email API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls the inbox and message operations on demand without loading another server's tool definitions into its context.
How do I send an email with the Cooper Email API through Jentic?
Search Jentic by intent such as 'send an email from an inbox', and Jentic returns the sendMessage operation with its input schema so your agent fills in the inbox, recipient, and body. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Create email inboxes and send, receive, search, reply to, and forward mail over HTTP. Supports scheduled drafts, a wait-for-mail operation, and message.received webhooks.
Use for: Create a temporary inbox for this signup flow, Send an email with an attachment from my inbox, Search this inbox for a confirmation message, Reply to the latest message on the same thread
Not supported: Does not handle SMS, push notifications, or marketing campaign management. Use for programmatic email inboxes, sending, and receiving only.
The Cooper Email API creates email inboxes and sends and receives mail over HTTP, so an agent can own a working mailbox without an SMTP or IMAP setup. It lists and full-text searches the messages in an inbox, replies, replies-all, and forwards on a thread, and manages drafts including scheduled sends. A wait operation holds until unread mail arrives, and a webhook can push message.received events to a URL. Inboxes can be permanent or temporary, created one at a time or in batches, and each send can be made idempotent with a client_id or an Idempotency-Key header.
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>