Official vendor OpenAPI document · agent-readyFinanceBankingapiKey8 EndpointsREST
For Agents
Read bank accounts, balances, and categorised transactions from a customer's linked bank account for cash flow analysis and credit decisioning.
Use for: I want to read a borrower's bank transactions for the last 90 days, Get the current balance on a customer's connected bank account, List all bank accounts linked to a company, Retrieve categorised bank transactions for cash flow analysis
Not supported: Does not handle posting transactions into accounting software, payment initiation, or accounting ledger reads - use for reading bank account, balance, and categorised transaction data from linked banking sources only.
Codat's Banking API surfaces bank account, balance, transaction, and transaction-category data from a customer's directly-linked bank or open-banking provider. It is purpose-built for lenders, finance platforms, and underwriters that need cleaned bank transaction history alongside accounting data. Endpoints return account metadata, current balances, and categorised transactions so credit teams can verify cash flow and detect risk signals without parsing raw open-banking output.
Install Jentic One Beta
Connect the Banking API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Banking 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.
1
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%2Fcodat.io%2Fbanking" | sh2
Step 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%2Fcodat.io%2Fbanking" | 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.
Capabilities
What an agent can do with Banking API.
Retrieve a customer's linked bank accounts with account name, currency, and identifier
Read current and historical balances for each linked bank account
Pull categorised bank transactions including merchant, amount, date, and assigned category
List transaction categories used to classify spending and inflows
Fetch a single transaction by ID for detailed inspection or audit
Read banking data scoped to a single connection or aggregated across all connections for a company
Use Cases
Patterns agents use Banking API for, with concrete tasks.
★ Cash Flow Underwriting
Lenders use the Codat Banking API to verify a borrower's cash flow directly from their bank. The /companies/{companyId}/connections/{connectionId}/data/banking-transactions and /banking-accountBalances endpoints provide categorised transactions and balances so credit models can score volatility, recurring income, and overdraft frequency without asking applicants to upload statements.
Fetch the last 90 days of categorised bank transactions for company {companyId} connection {connectionId} and compute total inflow versus outflow.
Bookkeeping Automation
Bookkeeping platforms read bank transactions through the Banking API to suggest matches against unreconciled invoices and bills in the customer's accounting software. The /banking-transactions endpoint plus the /banking-transactionCategories list let the platform group similar transactions and propose categorisations to the bookkeeper for one-click approval.
Pull all bank transactions for company {companyId} since the last reconciliation date and group them by category.
SMB Cash Flow Forecasting
B2B SaaS products that build SMB cash flow forecasts use Banking API balance and transaction history as the input series. The /banking-accounts and /banking-accountBalances endpoints give the current state, and the /banking-transactions endpoint with date filtering supplies the trailing data the forecast model needs.
Retrieve account balances and the last 12 months of transactions for company {companyId} and return a daily ending-balance series.
AI Agent Credit Analyst
AI agents acting as credit analysts use the Codat Banking API through Jentic to assemble the bank-data section of a credit memo. The agent searches Jentic for 'list banking transactions', loads the schema, and pulls categorised transactions and balances. Jentic isolates the Codat API key in its vault, and the unified search means the agent does not have to know the exact Codat path structure.
Search Jentic for 'banking transactions codat', load the operation, then pull the last 12 months of transactions for company {companyId} and summarise the largest five outflows.
Key Endpoints
8 endpoints — codat's banking api surfaces bank account, balance, transaction, and transaction-category data from a customer's directly-linked bank or open-banking provider.
METHOD
PATH
DESCRIPTION
GET
/companies/{companyId}/connections/{connectionId}/data/banking-accounts
List linked bank accounts for a connection
GET
/companies/{companyId}/connections/{connectionId}/data/banking-accountBalances
Read account balances
GET
/companies/{companyId}/connections/{connectionId}/data/banking-transactions
List categorised bank transactions
GET
/companies/{companyId}/data/banking-transactions
List transactions aggregated across all connections for a company
GET
/companies/{companyId}/connections/{connectionId}/data/banking-transactionCategories
List transaction categories
GET
/companies/{companyId}/connections/{connectionId}/data/banking-accounts
List linked bank accounts for a connection
GET
/companies/{companyId}/connections/{connectionId}/data/banking-accountBalances
Read account balances
GET
/companies/{companyId}/connections/{connectionId}/data/banking-transactions
List categorised bank transactions
GET
/companies/{companyId}/data/banking-transactions
List transactions aggregated across all connections for a company
GET
/companies/{companyId}/connections/{connectionId}/data/banking-transactionCategories
List transaction categories
Jentic AI Readiness Score
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.
B
Banking API
- Foundational (C)56/100
71
Foundational Compliance74
Developer Experience & Jentic Compatibility34
AI-Readiness & Agent Experience94
Agent Usability50
Security63
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.0
Show dimension breakdown
71
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: A-Signals: 4
86%
Lint Results
Aggregated quality score from linter diagnostics, weighted by severity.
100%
Resolution Completeness
Percentage of `$ref` references that resolve successfully.
0%
Specification Validity
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
100%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
74
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: A-Signals: 4
21%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
75%
Response Coverage
Percentage of operations with complete response definitions (success, client error, server error).
100%
Tooling Readiness
Health of API ingestion, bundling, and resolution within Jentic pipelines.
34
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: FSignals: 4
28%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
100%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
6%
Summary Coverage
Coverage of summaries across operations/tags/info.
94
Agent Usability
Functional utility, complexity comfort, and AI orchestration readiness.
Grade: A+Signals: 1
94%
Complexity Comfort
Agent comfort level based on API operational and structural complexity.
50
Security
Trust, risk posture, and security compliance.
Grade: C-Signals: 1
50%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
63
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: B-Signals: 1
62%
Descriptive Richness
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>Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Codat Banking by hand means building its Basic API-key header, targeting api.codat.io, and threading companyId and connectionId through every account, balance, and transaction read yourself. Through Jentic you install once, import the Banking API from the API Directory, store the Codat API key once, and your agent calls it.
Permission scoping
Banking puts the company id in the URL path (/companies/{companyId}/connections/{connectionId}/data/banking-...), so a rule can pin your agent to one company: it reads that company's bank accounts, balances, transactions, and categories and nothing else. Since Banking exposes read-only data here, you choose which of those reads the agent may call.
Credential isolation
Your Codat API key is stored once, encrypted, by your own Jentic One instance and injected at execution time as the Basic Authorization header. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'list bank transactions for a borrower' or 'get categorised banking transactions', and Jentic returns the matching Banking operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Banking API through Jentic.
What authentication does the Codat Banking API use?
The API uses an API key passed in the Authorization header as 'Basic <base64-encoded-key>'. The single security scheme in the spec is named auth_header. Through Jentic, the Codat API key is stored encrypted in the vault and the Authorization header is constructed inside Jentic at execution time.
Can I read categorised bank transactions with the Codat Banking API?
Yes. Use GET /companies/{companyId}/connections/{connectionId}/data/banking-transactions to list categorised transactions, and GET /companies/{companyId}/connections/{connectionId}/data/banking-transactionCategories to retrieve the category taxonomy. Both return data normalised by Codat from the underlying bank or open-banking source.
What are the rate limits for the Codat Banking API?
Codat does not publish a fixed rate limit in the OpenAPI spec; limits are governed at the company and connection level and depend on the underlying bank or open-banking provider. Codat returns HTTP 429 with a Retry-After header when limits are hit and recommends exponential backoff.
How do I pull bank balances through Jentic?
Search Jentic for 'bank account balances codat', load the GET /companies/{companyId}/connections/{connectionId}/data/banking-accountBalances operation, and execute it. Install with pip install jentic and use the standard async search, load, and execute flow.
Can I aggregate transactions across multiple connections for one company?
Yes. Use GET /companies/{companyId}/data/banking-transactions which returns transactions across every banking connection linked to the company, rather than scoping to a single connection. Use the connection-scoped endpoint when you need per-account isolation.
Can I limit what my agent is allowed to do with the Codat Banking API?
Yes. Because you run Jentic One yourself, your own rules decide which Codat Banking operations and credentials the agent may use. Since this API carries the company id in the URL path, a rule can pin your agent to a single company so it only reads that company's bank accounts, balances, categorised transactions, and transaction categories. The API is read-only here, so you choose exactly which of those reads the agent is allowed to call and which company or connection it is scoped to.
GET STARTED