Know of an official OpenAPI document? Contribute it →
For Agents
Check a consumer's eligibility for employee credit, simulate an offer by amount and installments, and confirm the proposal.
Use for: I need to check if this employee is eligible for credit, Simulate a loan of 5000 over 12 installments with insurance, Confirm the credit proposal for solicitation 12345, Run a test eligibility check without affecting live data
Not supported: Does not disburse funds, collect installments, or run credit bureau reports. Use for the employee credit eligibility, simulation, and proposal confirmation flow only.
The Limbo employee credit API lets a partner run the acquisition flow for an employee credit offer: it checks whether a consumer is eligible, simulates an offer from a desired amount, installment count, employer CNPJ, and an insurance choice, and confirms the resulting proposal. Calls carry the consumer_id in a header and can be flagged as test calls with the is_test header, and access is granted through an OAuth2 client credentials token.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the 00.1 Recuperação Partner Addition CDT, 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%2Flimbo.work%2Flimbo" | 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%2Flimbo.work%2Flimbo" | 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 00.1 Recuperação Partner Addition CDT API.
Check whether a consumer is eligible for employee credit using their consumer_id
Simulate a credit offer from a desired amount, installment count, employer CNPJ, and insurance choice
Confirm a credit proposal for a simulated solicitation
Run any step of the flow as a test call with the is_test header
Exchange a client_id and client_secret for a bearer token
Patterns agents use 00.1 Recuperação Partner Addition CDT API for, with concrete tasks.
★ Agent-guided employee credit application through Jentic
An AI agent assisting an employee can check eligibility, run a simulation with the amount and number of installments the employee asks for, and confirm the proposal once they accept it. Through Jentic the agent finds the eligibility, simulation, and confirmation operations by intent and loads their schemas, while the OAuth2 client credentials stay out of its context.
Check eligibility for consumer_id 26252690, simulate an offer with desiredAmount 5000, desiredInstallment 12, the employer cnpj, and withInsurance true, then confirm the proposal by passing the same solicitation id in the solicitation_id header.
Offer comparison with and without insurance
The simulation step takes a withInsurance flag, so a partner can run the same amount and installment count twice and show the employee both offers side by side before they commit to a proposal.
Run two simulations for desiredAmount 3000 and desiredInstallment 10, one with withInsurance true and one with withInsurance false, and report both results.
Integration testing in test mode
Each acquisition call accepts an is_test header, which lets a partner exercise eligibility, simulation, and confirmation while building the integration, then drop the flag for live consumers.
Call the eligibility check with is_test set to true and consumer_id 12345 and confirm the call succeeds before switching to live consumers.
5 endpoints — the limbo employee credit api lets a partner run the acquisition flow for an employee credit offer: it checks whether a consumer is eligible, simulates an offer from a desired amount, installment count, employer cnpj, and an insurance choice, and confirms the resulting proposal.
METHOD
PATH
DESCRIPTION
/oauth2/token
Get a client credentials token
/v1/employee-credit/eligibility
Check consumer eligibility
/v1/employee-credit/simulation
Simulate a credit offer
/v1/employee-credit/confirmation
Confirm a credit proposal
/oauth2/token
Get a client credentials token
/v1/employee-credit/eligibility
Check consumer eligibility
/v1/employee-credit/simulation
Simulate a credit offer
/v1/employee-credit/confirmation
Confirm a credit proposal
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>What agents get from Jentic-routed access to this vendor.
Setup
Wiring Limbo by hand means running the OAuth2 client credentials exchange, attaching the bearer token, and setting the consumer_id and is_test headers on each acquisition call. Through Jentic you install once, import Limbo from the API Directory, store the client credentials once, and your agent calls it.
Permission scoping
Limbo carries the consumer and solicitation in headers and the request body, not the URL path, so rules bound which operations your agent may call, not which consumer. You choose the operations it may call, so proposal confirmation is not included unless you add it.
Credential isolation
Your Limbo client 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 'check credit eligibility' or 'simulate a loan offer', and Jentic returns the matching Limbo 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 00.1 Recuperação Partner Addition CDT API through Jentic.
What authentication does the Limbo employee credit API use?
Per its OpenAPI spec the API uses HTTP bearer authentication. You get the token from the token operation by posting your client_id and client_secret with grant_type client_credentials, then send it in the Authorization header. Acquisition calls also carry a consumer_id header. Through Jentic the client credentials are stored encrypted by your own Jentic One instance and injected at request time.
Is there a Limbo MCP server?
You don't need an MCP server to give your agent the Limbo employee credit API. Jentic connects it directly from the API Directory: import it, store your credential once, and your agent calls the eligibility, simulation, and confirmation operations on demand.
Can I simulate a credit offer with the Limbo API?
Yes. The simulation operation takes cnpj, desiredAmount, desiredInstallment, solicitationId, and withInsurance in the body, with the consumer_id in a header, and returns the simulated offer for that consumer.
What are the rate limits for the Limbo employee credit API?
The OpenAPI spec does not specify rate limits. Check with Limbo at https://limbo.work for the limits on your partner account.
Can I limit what my agent is allowed to do with the Limbo API?
Yes. For example, allow only the eligibility check and the simulation operations, so the agent can tell an employee what they qualify for and what an offer looks like, but cannot confirm a proposal on their behalf. Every call it makes is logged.
How do I check employee credit eligibility with the Limbo API through Jentic?
Search Jentic for 'check employee credit eligibility', load the eligibility operation, and pass the consumer_id header, adding is_test while you build. Jentic fetches and injects the bearer token at call time. To run it on your own infrastructure, install Jentic One from its GitHub repo.
GET STARTED