Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Ringg AI API Documentation, 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%2Fringg.ai%2Fringg" | 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%2Fringg.ai%2Fringg" | 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 Ringg AI API Documentation API.
Place a single outbound call with a voice agent to a mobile_number, from a fixed number or a number pool
Upload a campaign contact list and start a campaign, or terminate in-flight calls by call_ids or mobile_numbers
Create voice agents with a prompt, task, primary_language, voice_id, and intro_message, and edit settings such as voice, knowledge base, or inbound number
Create and edit knowledge bases from files, URLs, and FAQs and attach them to an agent
GET STARTED
Filter call history by status, call_type, agent_id, and date range, and fetch one call's analysis and metrics
Rent and release workspace phone numbers by country_code and prefix
Allocate concurrency and credit limits across Ringg Spaces, and report volume, connectivity, and latency analytics
Patterns agents use Ringg AI API Documentation API for, with concrete tasks.
★ Agent-triggered calls with a narrow permission set
A developer's CRM agent should be able to ring a fresh lead with a Ringg voice agent, and nothing more. Through Jentic the agent searches by intent, gets the initiateIndividualCall operation with its input schema, and calls it with the X-API-KEY injected at execution time. The developer's rule allows that call operation and the call-details read, so the agent cannot buy numbers, delete agents, or start a whole campaign.
Call POST /calling/outbound/individual with name 'Priya Shah', mobile_number '+919876543210', and the sales agent_id, then poll GET /calling/call-details with the returned call id and send_analysis true
Outbound campaigns from a contact list
Collections, reminders, and lead qualification often mean calling hundreds of people with the same script. POST /campaign/save uploads a contact file with a variables_map, agent_id, call_config, country_code, campaign_name, and start and end times, and POST /campaign/start or POST /campaign/v2/start launches it from fixed numbers or a number pool. PATCH /campaign/terminate stops calls in flight.
Upload a CSV via POST /campaign/save with campaign_name 'November renewals', the agent_id, country_code '+91', a variables_map, and campaign_start_time and campaign_end_time, then start it via POST /campaign/v2/start with the list_id and number_pool_id
Building and tuning voice agents
Teams iterate on voice agents as scripts change. POST /public/agent creates an agent with agent_name, introduction_and_objective, response_guidelines, task, primary_language, voice_id, and intro_message, while PATCH /agent/v1 applies one targeted change per call through its operation field, such as edit_prompt, edit_voice, attach_kb, or attach_inbound_number. GET /agent/voices lists voices by language.
Create a knowledge base via POST /external/kb with kb_name 'Refund policy' and a policy URL, then call PATCH /agent/v1 with operation 'attach_kb', the agent_id, and the new kb_id
Call quality and performance reporting
Operations leads want to know how calls are going without exporting spreadsheets. GET /calling/history filters by status values such as completed, failed, or forwarded and by call_type such as inbound or outbound, and POST /calling/history/download exports the same view. The analytics endpoints report volume, connectivity, agent performance, latency, and concurrency over a date range, optionally per Ringg Space.
Call GET /analytics/v4/connectivity and GET /analytics/v4/agent-performance with start_date and end_date for last week and the agent_id, then list failed calls via GET /calling/history with status ['failed']
49 endpoints — the ringg ai api places outbound phone calls with ringg's voice ai agents, one at a time or as large campaigns from an uploaded contact list.
METHOD
PATH
DESCRIPTION
/calling/outbound/individual
Initiate an individual call
/calling/history
Get call history
/calling/call-details
Get call details
/campaign/save
Upload a campaign contact list
/campaign/v2/start
Start a campaign from a number pool
/public/agent
Create a voice agent
/agent/v1
Edit agent settings
/external/kb
Create a knowledge base
/calling/outbound/individual
Initiate an individual call
/calling/history
Get call history
/calling/call-details
Get call details
/campaign/save
Upload a campaign contact list
/campaign/v2/start
Start a campaign from a number pool
/public/agent
Create a voice agent
/agent/v1
Edit agent settings
/external/kb
Create a knowledge base
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Ringg AI by hand means sending the X-API-KEY header on each call, picking between fixed numbers and number pools, and handling multipart contact-list uploads for campaigns. Through Jentic you install once, import Ringg AI from the API Directory, store the key once, and your agent calls it.
Permission scoping
Ringg AI carries the agent, contact, and campaign in the request body for calls and campaigns, so rules bound which operations your agent may call, not which agent or contact list. Limit it to the operations it needs, such as placing one call and reading call details, so ones like buying a number or deleting an agent are not included unless you add them.
Credential isolation
Your Ringg AI 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 'place an outbound call with a voice agent' or 'get call history', and Jentic returns the matching Ringg AI operation with its input schema, including required fields like mobile_number and agent_id.
Alternatives and complements available in the Jentic catalogue.
Specific to using Ringg AI API Documentation API through Jentic.
What authentication does the Ringg AI API use?
The Ringg AI API authenticates with an API key sent in the X-API-KEY request header, as declared in its OpenAPI spec under ApiKeyAuth. Through Jentic the key is stored by your own Jentic One instance and added to each call at execution time, so the agent never sees it.
Can I place a single call with the Ringg AI API without a campaign?
Yes. POST /calling/outbound/individual places one call and needs name, mobile_number with country code, and agent_id. POST /calling/v2/outbound/individual does the same from a number pool via number_pool_id. You can pass custom_args_values for the agent's variables and a call_deadline or call_validity_hours to bound when the call may run.
What are the rate limits for the Ringg AI API?
The OpenAPI spec does not specify request rate limits. Call throughput is governed by workspace concurrency, which you can allocate per Ringg Space with PATCH /workspace/sub/{sub_workspace_id}/concurrency. Check https://docs.ringg.ai for current limits.
Is there a Ringg AI MCP server?
You don't need an MCP server to give your agent Ringg AI. Jentic connects it directly from the API Directory: import it, store your API key once, and your agent calls the calling, campaign, and analytics operations on demand without another server's tool definitions in its context.
How do I place a Ringg AI call through Jentic?
Search Jentic for 'place an outbound call with a voice agent', load the initiateIndividualCall operation, and execute POST /calling/outbound/individual with the contact's name, mobile_number, and your agent_id. Then read GET /calling/call-details for the outcome. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Can I limit what my agent is allowed to do with the Ringg AI API?
Yes. Write a rule that allows only POST /calling/outbound/individual and GET /calling/call-details. Your agent can ring one contact at a time and check how the call went, but it cannot launch a campaign, buy or release numbers, or delete a voice agent, and every call it makes is logged.
How do I change one setting on a Ringg AI voice agent?
Call PATCH /agent/v1 with agent_id and an operation value such as edit_prompt, edit_voice, attach_kb, or edit_intro_message. Each operation reads only its own fields, so you send the field for that change and leave the rest of the agent untouched.
For Agents
Place outbound calls with Ringg AI voice agents, run contact-list campaigns, build agents with knowledge bases, rent numbers, and read call history and analytics.
Use for: Call this lead now with my sales qualification voice agent, Start a campaign to the uploaded contact list using the number pool, List all failed calls from yesterday for the support agent, Get the transcript analysis for call id abc123
Not supported: Does not send SMS, email, or chat outside Ringg, and does not host a CRM. Use for running Ringg AI voice agents, calls, campaigns, and their analytics only.
The Ringg AI API places outbound phone calls with Ringg's voice AI agents, one at a time or as large campaigns from an uploaded contact list. It creates and edits voice agents with a prompt, task, language, voice, intro message, and attached knowledge base, rents and releases phone numbers, and manages sub workspaces called Ringg Spaces with their own concurrency and credit allocations. Call history can be filtered by status, call_type, agent, and number, and each call's details include analysis and metrics. Analytics endpoints report call volume, connectivity, agent performance, latency, concurrency, and cohort breakdowns.
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>