For Agents
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the CallFire 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%2Fwww.callfire.com%2Fcallfire" | 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%2Fwww.callfire.com%2Fcallfire" | 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 CallFire API Documentation API.
Send calls
Find calls
Update a batch
Create an IVR
GET STARTED
Programmatically send calls, find calls. Covers 107 operations with basic authentication.
Use for: I need to send calls, I want to calls, Search for a specific call, Find all a specific batch
Not supported: Does not handle payments, crm, or developer tools - use for communications only.
CallFire API Documentation provides programmatic access to communications functionality. The API exposes 107 endpoints secured with basic authentication.
Monitor CallFire API Documentation operational status and events
Patterns agents use CallFire API Documentation API for, with concrete tasks.
★ Communications Operations
Use the CallFire API Documentation to perform communications operations programmatically. The API provides 107 endpoints covering core functionality including send calls, find calls, find a specific call.
Call POST /calls to send calls
Automated keyword-leases Management
Automate keyword-leases operations by combining multiple CallFire API Documentation endpoints. Agents can find calls and then find a specific call in a single workflow.
Call GET /calls to find calls, then verify the result
AI Agent Integration via Jentic
AI agents discover and call CallFire API Documentation endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle basic tokens manually.
Search Jentic for 'send calls', load the operation schema, and execute with Jentic-managed credentials
107 endpoints — callfire api documentation provides programmatic access to communications functionality.
METHOD
PATH
DESCRIPTION
/calls
Send calls
/calls
Find calls
/calls/{id}
Find a specific call
/campaigns/batches/{id}
Find a specific batch
/campaigns/batches/{id}
Update a batch
/campaigns/ivrs
Create an IVR
/campaigns/ivrs
Find IVRs
/campaigns/ivrs/{id}
Find a specific IVR
/calls
Send calls
/calls
Find calls
/calls/{id}
Find a specific call
/campaigns/batches/{id}
Find a specific batch
/campaigns/batches/{id}
Update a batch
/campaigns/ivrs
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the CallFire API by hand means setting up its basic auth and managing calls and campaigns across 107 operations yourself. Through Jentic you install once, import the CallFire API from the API Directory, store the credential once, and your agent calls it.
Permission scoping
The CallFire API puts the call or campaign id in the URL path (/calls/{id}, /campaigns/batches/{id}), so a rule can pin your agent to one call or campaign batch. You choose the operations it may call, so send-call actions and batch updates are not included unless you add them, and read-only lookups can stand alone.
Credential isolation
Your CallFire API 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 calls' or 'get a campaign batch', and Jentic returns the matching CallFire API 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 CallFire API Documentation API through Jentic.
What authentication does the CallFire API Documentation use?
The CallFire API Documentation uses HTTP Basic authentication with username and password. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.
Can I send calls with the CallFire API Documentation?
Yes. Use the POST /calls endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the CallFire API Documentation?
Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.
How do I send calls through Jentic?
Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'send calls'. Jentic returns the matching CallFire API Documentation operation with its input schema. Load the schema and execute the call - credentials are injected automatically.
How many endpoints does the CallFire API Documentation have?
The CallFire API Documentation exposes 107 endpoints covering keyword-leases, campaigns, campaign-sounds operations.
Can I limit what my agent is allowed to do with the CallFire API?
Yes. Because you run Jentic One yourself, your own rules decide which CallFire operations and credentials the agent may use. Since CallFire puts the call or campaign id in the URL path (/calls/{id}, /campaigns/batches/{id}), you can pin the agent to a single call or campaign batch and grant only read-only lookups such as GET /calls. Write actions like POST /calls to send calls or PUT /campaigns/batches/{id} to update a batch are excluded unless you explicitly add them.
Create an IVR
/campaigns/ivrs
Find IVRs
/campaigns/ivrs/{id}
Find a specific IVR