Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the CurrentClient Public 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%2Fcurrentclient.io%2Fcurrentclient" | 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%2Fcurrentclient.io%2Fcurrentclient" | 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 CurrentClient Public API.
Read and create client contacts and look them up by phone number
Attach, update, and remove notes on a contact
Schedule client messages and list or cancel scheduled sends
Send messages and read a client's conversations and message history
List calls and conversations tied to each client
GET STARTED
Register webhook endpoints and update their subscribed events
Tag contacts and list the available tags
Patterns agents use CurrentClient Public API for, with concrete tasks.
★ Agent-Managed Client Records
An AI agent connected through Jentic can keep a client book current without a developer wiring the calls: it creates a contact, looks one up by phone number, adds a note summarising a call, and tags the record. Because contacts, notes, and tags are separate operations, the agent can enrich an existing record or build a new one in a single run.
Create a contact, add a note summarising a call, and tag the contact as a new lead
Client Messaging and Scheduling
Advisor and support teams use CurrentClient to reach clients on their own schedule. The API sends a message now, schedules one for later, lists and cancels scheduled sends, and reads a client's conversation and message history. Calls tied to a client appear alongside their conversations so an agent has the full thread.
Schedule a follow-up message to a client for next week and list their recent conversation history
Event-Driven Integrations
Teams that sync CurrentClient with other tools rely on its webhooks. An agent registers a webhook endpoint, chooses which events it subscribes to, and rotates the endpoint secret when needed. New messages and other events then push to the endpoint instead of being polled.
Register a webhook endpoint subscribed to new message events and verify it was created
35 endpoints — the currentclient api stores client contacts and the conversations around them for client-facing teams.
METHOD
PATH
DESCRIPTION
/api/v1/contacts/
Read contacts
/api/v1/contacts/
Create contacts
/api/v1/contacts/{id}
Read a single contact
/api/v1/contacts/{contactId}/notes/
Create a note on a contact
/api/v1/scheduled-messages/
Create a scheduled message
/api/v1/messages/send
Send a message
/api/v1/conversations
List conversations
/api/v1/contacts/
Read contacts
/api/v1/contacts/
Create contacts
/api/v1/contacts/{id}
Read a single contact
/api/v1/contacts/{contactId}/notes/
Create a note on a contact
/api/v1/scheduled-messages/
Create a scheduled message
/api/v1/messages/send
Send a message
/api/v1/conversations
List conversations
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the CurrentClient API by hand means handling its JWT bearer tokens, a separate admin bearer scheme, and webhook registration with secret rotation. Through Jentic you install once, import CurrentClient from the API Directory, store the token once, and your agent calls it.
Permission scoping
CurrentClient puts the contact id, note id, and webhook id in the URL path, so a rule can pin your agent to the contact and note operations it needs. Destructive operations like note deletion or webhook secret rotation stay out of that set unless you add them.
Credential isolation
Your CurrentClient 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 'add a client note' or 'schedule a message', and Jentic returns the matching CurrentClient 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 CurrentClient Public API through Jentic.
What authentication does the CurrentClient API use?
The CurrentClient API authenticates with a JWT bearer token per its OpenAPI spec: you send an Authorization header carrying a signed JWT, and the spec also declares a separate admin bearer scheme for administrative routes. Through Jentic the token is stored once, encrypted, by your own Jentic One instance and injected at call time.
Can I send messages to clients with the CurrentClient API?
Yes. You can send a message, schedule a message for later, list and cancel scheduled messages, and read a client's conversations and their message history. Calls tied to a client are listed alongside their conversations.
What are the rate limits for the CurrentClient API?
The OpenAPI spec does not define rate limits for the CurrentClient API. Check the CurrentClient website at https://currentclient.io for current limits.
Is there a CurrentClient MCP server?
You don't need an MCP server to connect your agent to the CurrentClient API. Jentic imports it directly from the API Directory: store your token once and your agent can create contacts, add notes, and send messages. Operations are discovered on demand without loading another server's tool definitions into context.
Can I limit what my agent is allowed to do with the CurrentClient API?
Yes. Write a rule that allows only the operations the task needs, such as reading contacts and adding notes, so destructive operations like deleting notes, deleting webhook endpoints, or rotating webhook secrets are not included unless you add them. Every call the agent makes is logged.
How do I create a client contact with the CurrentClient API through Jentic?
Search Jentic for 'create a client contact', and it returns the matching CurrentClient operations with their input schemas. Your agent creates the contact, adds a note, and tags it in a single run. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Manage client contacts and the conversations around them: create contacts, look them up by phone, keep notes and tags, and send or schedule client messages. Register webhooks for new-message events.
Use for: I want to create a new client contact, Look up a contact by phone number, Add a note to a client's record, Schedule a message to a client
Not supported: Does not handle billing, document storage, or marketing email campaigns. Use for managing client contacts, notes, and messaging only.
The CurrentClient API stores client contacts and the conversations around them for client-facing teams. It reads and creates contacts, looks them up by phone number, and keeps notes and tags against each record. Alongside the contact model it schedules and sends client messages, lists calls and conversations, and delivers events to registered webhook endpoints.
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>