For Agents
Send and receive email, manage inboxes and sending domains, run outreach workflows with contact enrollments, and extract OTP codes or invoice fields from incoming messages. Approval policies gate what the agent can send.
Use for: Send a personalized email from an agent inbox, Search messages across my inboxes for a sender, Enroll a list of contacts into an outreach workflow, Extract the OTP code from a received email
Not supported: Does not handle SMS, voice calls, or push notifications. Use for agent email sending, inboxes, and outreach automation only.
The OutreachAgent API sends, receives, and parses email for AI agents, tracking every delivery through webhook events. It manages inboxes, sending domains, contacts, segments, and templates, and runs multi-step workflows that enroll contacts into outreach sequences. Built-in extractions pull OTP codes and basic invoice fields from incoming messages, and approval policies gate what an agent is allowed to send.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the OutreachAgent 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%2Foutreachagent.dev%2Foutreachagent" | 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%2Foutreachagent.dev%2Foutreachagent" | 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 OutreachAgent API.
Send emails and track every delivery through webhook events
Create and manage inboxes and sending domains
Run multi-step email workflows that enroll contacts into sequences
Search messages and threads across inboxes
Extract OTP codes and basic invoice fields from incoming messages
Segment contacts and preview templates before sending
Set approval policies that gate what the agent is allowed to send
Patterns agents use OutreachAgent API for, with concrete tasks.
★ Agent Email Automation
An AI agent connected to OutreachAgent through Jentic can send email from a managed inbox, watch delivery events through webhooks, and act on replies it reads back from threads. Approval policies let a human gate risky sends, so the agent runs within bounds you set.
Send an email from a managed inbox, then poll webhook deliveries to confirm it was delivered
Transactional Email Sending
Send transactional messages from a verified sending domain and track their delivery. OutreachAgent records every delivery attempt as a webhook event, so an application can confirm receipt and retry failures.
Create a sending domain, send a transactional message, and replay a failed webhook delivery
OTP and Invoice Extraction
Turn inbound email into structured data by extracting one-time passcodes and basic invoice fields. An agent can forward a received message to the extraction endpoints and get back the OTP or invoice fields without parsing raw email itself.
Extract the OTP code from a received message and use it to complete a login flow
Outreach Sequences
Build nurture sequences by enrolling segmented contacts into a workflow and letting it run step by step. OutreachAgent tracks enrollment logs and workflow analytics, and an agent can pause or resume individual nodes as conditions change.
Enroll a segment of contacts into a workflow and pause one node pending review
89 endpoints — the outreachagent api sends, receives, and parses email for ai agents, tracking every delivery through webhook events.
METHOD
PATH
DESCRIPTION
/v1/messages/send
Send an email message
/v1/search/messages
Search messages across inboxes
/v1/inboxes
Create an inbox
/v1/workflows
Create an outreach workflow
/v1/enrollments
Enroll contacts into a workflow
/v1/extractions/otp
Extract an OTP from a message
/v1/messages/send
Send an email message
/v1/search/messages
Search messages across inboxes
/v1/inboxes
Create an inbox
/v1/workflows
Create an outreach workflow
/v1/enrollments
Enroll contacts into a workflow
/v1/extractions/otp
Extract an OTP from a message
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>What agents get from Jentic-routed access to this vendor.
Setup
Wiring OutreachAgent by hand means handling its bearer auth, verifying sending domains, and wiring webhook replay yourself. Through Jentic you install once, import OutreachAgent from the API Directory, store the credential once, and your agent calls it.
Permission scoping
OutreachAgent carries the recipient and message content in the request body, so a rule bounds which operations your agent may call rather than which inbox. Pick the operations it needs, such as sending and searching messages, and leave inbox deletion or policy changes out unless you add them.
Credential isolation
Your OutreachAgent credential 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 'extract an OTP', and Jentic returns the matching OutreachAgent 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 OutreachAgent API through Jentic.
Is there an OutreachAgent MCP server?
You don't need an MCP server to give your agent the OutreachAgent API. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent can send mail, manage inboxes, and run workflows. Operations are discovered on demand, so your agent's context stays lean.
Can I limit what my agent is allowed to do with the OutreachAgent API?
Yes. Write a rule that allows only the message-send and search operations, so the agent can send and read mail but cannot delete inboxes or change policies unless you add those operations. OutreachAgent also has approval policies that gate sends, and every call Jentic makes is logged.
What authentication does the OutreachAgent API use?
The OutreachAgent API authenticates with a bearer token in the Authorization header per its OpenAPI spec, accepting either a Clerk JWT or an OutreachAgent API key. With Jentic, the token is stored encrypted by your own Jentic One instance and injected at call time.
Can I extract an OTP code from an email with the OutreachAgent API?
Yes. The OTP extraction endpoint takes a message or text input and returns the one-time passcode, and a separate endpoint extracts basic invoice fields. An agent can act on inbound mail without parsing raw email itself.
What are the rate limits for the OutreachAgent API?
The spec exposes send-limit endpoints you can configure, but it does not specify API rate limits. Check the OutreachAgent documentation at https://outreachagent.dev for current limits.
How do I send an email with the OutreachAgent API through Jentic?
Import the OutreachAgent API from the Jentic API Directory, store your credential once, and have your agent search by intent such as 'send an email'. Jentic returns the send operation with its input schema, and your agent passes the inbox and recipient. To run it on your own infrastructure, install Jentic One from its GitHub repo.
GET STARTED