Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the ACA 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%2Fautomatedclientacquisition.com%2Fautomatedclientacquisition" | 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%2Fautomatedclientacquisition.com%2Fautomatedclientacquisition" | 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 ACA API.
Store contacts with custom fields and merge variables
Build and segment lead lists and manage their members
Enroll leads into an outreach sequence
Send a message to a lead and read the conversation thread
Search a shared lead pool and build a list from the matches
GET STARTED
Register webhook subscriptions for outreach events
Patterns agents use ACA API for, with concrete tasks.
★ Agent-Driven Outreach
An AI agent connected through Jentic enrolls a lead into a sequence, sends the first message, and reads the conversation as replies come back, so a cadence runs without a person clicking through each step. Because enrollment and messaging reach real people, those operations sit behind an approval rule while the agent prepares the work.
Enroll this lead into the onboarding sequence and send the first message, then report any reply
Lead Pool Prospecting
A workflow searches the shared lead pool for prospects that match a profile and builds a lead list from the matches, so the next campaign starts from a fresh, targeted list. The pool search previews matches before a build job commits them to a list.
Search the lead pool for matching prospects and build a list from the first hundred matches
Conversation Monitoring
A monitor reads the conversations and messages tied to each contact and subscribes to webhooks for new replies, so an agent can surface responses and route them without polling. The webhook subscription makes reply handling event-driven.
Register a webhook for new replies and summarise each contact's latest conversation when one arrives
32 endpoints — the aca api runs outbound client acquisition: it stores contacts with custom fields, groups them into lead lists, enrolls leads into outreach sequences, sends messages, and tracks the resulting conversations.
METHOD
PATH
DESCRIPTION
/v1/enrollments
Enroll leads in a sequence
/v1/messages
Send a message
/v1/contacts
List contacts
/v1/pool/search
Preview lead pool matches
/v1/pool/lists
Build a lead list from the pool
/v1/webhooks
Register a webhook subscription
/v1/enrollments
Enroll leads in a sequence
/v1/messages
Send a message
/v1/contacts
List contacts
/v1/pool/search
Preview lead pool matches
/v1/pool/lists
Build a lead list from the pool
/v1/webhooks
Register a webhook subscription
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the ACA API by hand means creating an organization-scoped aca_ token, following keyset pagination with a cursor on every list, and wiring the webhook secret for inbound events. Through Jentic you install once, import ACA from the API Directory, store the token once, and your agent calls it.
Permission scoping
ACA puts the contact, list, and sequence ids in the URL path, so a rule can let your agent read contacts and conversations while leaving the send-message, enroll, and delete operations out. You choose the operations it may call, so sending outreach is included only if you add it.
Credential isolation
Your ACA token 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 'enroll a lead in a sequence' or 'send a message to a contact', and Jentic returns the matching ACA 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 ACA API through Jentic.
Is there an ACA MCP server?
You don't need an MCP server to give your agent the ACA API. Jentic connects it directly from the API Directory: import it, store your token once, and your agent can enroll leads and send messages straight away, with no extra server to run and no tool definitions to load into the agent's context.
Can I limit what my agent is allowed to do with the ACA API?
Yes. Write a rule that allows reading contacts and conversations but not the send-message, enroll, or delete operations, so the agent can prepare outreach while a person approves anything that contacts a real lead, and every call it makes is logged. Because contact, list, and sequence ids are in the URL path, you can also bound the agent to one list.
What authentication does the ACA API use?
The ACA API authenticates with a bearer token, an organization-scoped aca_ API key sent as an Authorization header, per its OpenAPI spec; the token is frozen to one organization when it is created. Inbound webhook calls carry a separate x-webhook-secret header. Through Jentic the token is stored encrypted by your own instance and added at call time, so it never appears in the agent's prompt or logs.
Can I enroll leads into a sequence with the ACA API?
Yes. You enroll one or more leads into a sequence, then send messages and read the resulting conversation threads, so an agent can run an outreach cadence end to end. The lead pool search lets it build the target list before enrollment begins.
What are the rate limits for the ACA API?
The API is limited to 120 requests per minute per token, counted in fixed one-minute windows according to its own description, and exceeding it returns a 429 with a Retry-After header. For details and plan limits, see the ACA documentation at https://www.automatedclientacquisition.com.
How do I enroll a lead into a sequence with the ACA API through Jentic?
Import the ACA API from the Jentic API Directory, then have your agent issue a request such as 'enroll this lead into my onboarding sequence'. Jentic matches the intent to the enrollment operation and returns its input schema so the agent builds the correct request; because enrollment reaches real people, keep it behind your approval rules. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Manage contacts and lead lists, enroll leads into outreach sequences, send messages, and read conversations. Authenticates with an organization-scoped aca_ bearer token; inbound webhooks carry a separate secret.
Use for: Enroll a lead into an outreach sequence, Send a message to a contact, Search the lead pool for matching prospects, Build a lead list from pool matches
Not supported: Does not run ad campaigns, host landing pages, or process payments. Use for managing contacts, lead lists, outreach sequences, and conversations only.
The ACA API runs outbound client acquisition: it stores contacts with custom fields, groups them into lead lists, enrolls leads into outreach sequences, sends messages, and tracks the resulting conversations. A shared lead pool can be searched and turned into a list, so an agent can source prospects and then work them through a cadence. List endpoints are keyset-paginated for large tables, and webhook subscriptions deliver outreach events as they happen.
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>