Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Berg CRM 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%2Fbergsystem.pl%2Fbergsystem" | 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%2Fbergsystem.pl%2Fbergsystem" | 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 Berg CRM API.
List and create customers and companies
Create and update sales and sales opportunities
Progress a sales opportunity through its selling-process steps and checklist
Record payments, installments, and paychecks against sales
Create products and product categories and producers
GET STARTED
Create and update calendar events and employee goals
Patterns agents use Berg CRM API for, with concrete tasks.
★ AI Agent CRM Updates
An AI agent keeps Berg CRM current without a developer building a sync integration. Through Jentic the agent creates customers, opens sales opportunities, and records payments against sales, while the OAuth credentials stay on the developer's own machine.
Create a customer, open a sales opportunity linked to that customer, and advance it to the next selling-process step
Sales Pipeline Progression
Sales teams move each opportunity through defined stages. Berg CRM exposes selling processes with ordered steps and a checklist per opportunity, so an agent can read where an opportunity stands, check off a requirement, and advance it.
Read the steps of a selling process for an opportunity, mark a checklist question answered, and update the opportunity
Payment Recording
Closed sales need payments logged against them. Berg CRM lets an agent record payments and installments on a sale and read what has been paid, so finance stays in sync with the pipeline.
Record a payment against a sale and list that sale's payments to confirm the balance
119 endpoints — the berg crm api manages customers, sales, and sales opportunities for the berg system platform.
METHOD
PATH
DESCRIPTION
/customers
Get customers list
/customers
Create a customer
/sales
Get all sales
/sales
Create a sale
/sales_opportunities
Get all sales opportunities
/sales_opportunities
Create a sales opportunity
/selling_processes
Get selling processes list
/payments
Get all payments
/customers
Get customers list
/customers
Create a customer
/sales
Get all sales
/sales
Create a sale
/sales_opportunities
Get all sales opportunities
/sales_opportunities
Create a sales opportunity
/selling_processes
Get selling processes list
/payments
Get all payments
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Berg CRM by hand means implementing its OAuth 2.0 token exchange, learning its selling-process step model, and matching payments to sales yourself. Through Jentic you install once, import Berg CRM from the API Directory, store the credentials once, and your agent calls it.
Permission scoping
Access runs through one OAuth client, so a rule bounds the agent to the operations it needs, such as reading customers and creating sales. You choose which operations it may call, so deleting events or files is not included unless you add them.
Credential isolation
Your Berg CRM OAuth credentials are stored once, encrypted, by your own Jentic One instance and injected at execution time. They never enter the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'create a sales opportunity' or 'record a payment', and Jentic returns the matching Berg CRM 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 Berg CRM API through Jentic.
Is there a Berg CRM MCP server?
You don't need an MCP server to give your agent the Berg CRM API. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls it. Operations are discovered on demand, so nothing extra loads into the agent's context.
Can I limit what my agent is allowed to do with the Berg CRM API?
Yes. Write a rule that allows only the customer-read and sale-create operations, so the agent can look up customers and log new sales but cannot delete events or files, and every call is logged.
What authentication does the Berg CRM API use?
The Berg CRM API authenticates with OAuth 2.0, obtaining an access token from its token endpoint using the password or authorization-code flow declared in its OpenAPI spec. Through Jentic the credentials are stored encrypted by your own Jentic One instance and exchanged for a token at call time, so they never reach the agent's prompt or logs.
Can I progress a sales opportunity through its pipeline with the Berg CRM API?
Yes. Read the selling process and its ordered steps for an opportunity, mark a checklist question answered, and update the opportunity, so the agent advances it through the pipeline the same way a sales rep would.
How do I create a sales opportunity through Jentic?
Install Jentic One with `curl -fsSL https://raw.githubusercontent.com/jentic/jentic-one/main/tools/install.sh | sh`, then import the Berg CRM API from the Jentic API Directory and store your OAuth credentials. Your agent searches for 'create a sales opportunity' and Jentic returns the create operation with its input schema. To run it on your own infrastructure, install Jentic One from its GitHub repo.
What are the rate limits for the Berg CRM API?
The Berg CRM OpenAPI spec does not define rate limits. Berg System documents operational detail in its knowledge base, so confirm the current limits there before high-volume syncing.
For Agents
Manage a sales pipeline in Berg CRM: create customers and companies, open and progress sales opportunities through selling-process steps, record payments, and schedule calendar events.
Use for: Create a new customer, I want to create a sales opportunity, List all open sales opportunities, Record a payment against a sale
Not supported: Does not handle email marketing, telephony, or e-commerce checkout. Use for managing customers, sales, and sales opportunities in Berg CRM only.
The Berg CRM API manages customers, sales, and sales opportunities for the Berg System platform. It lists and creates customers and companies, moves sales opportunities through selling-process steps and checklists, and records payments, installments, and paychecks against sales. Supporting operations cover products, calendar events, employees and their goals, and GDPR records, all behind an OAuth 2.0 authorization.
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>