Install Jentic One Beta

Connect the PivotBank API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the PivotBank 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%2Fpivotbank.app%2Fpivotbank" | sh

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%2Fpivotbank.app%2Fpivotbank" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic 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 PivotBank API.

Convert a digital bank statement PDF, sent as multipart form data or a raw application/pdf body, into a JSON list of transactions in printed order

Return the bank name, account number, statement period, page count, and transaction count read from the statement

Gate on the reconciliation verdict, which compares opening balance plus every credit minus every debit against the printed closing balance

Flag individual rows whose running balance does not follow from the row before, using each transaction's check value

GET STARTED

Start building with PivotBank API

Explore with Jentic One

View OpenAPI Document

Use Cases

Patterns agents use PivotBank API for, with concrete tasks.

★ Agent-Driven Statement Extraction via Jentic

An AI agent handling bookkeeping or loan paperwork receives bank statements as PDFs and needs the rows as data. Through Jentic the agent calls the PivotBank convert operation with the PDF, reads back every transaction with debit, credit, and balance, and only passes the result on when the reconciliation verdict is true, sending mismatched statements to a person for review instead.

Upload the March statement PDF to the convert operation, confirm reconciliation.verified is true, and return the list of transactions with a debit over 500

Bookkeeping Import from Statement PDFs

Accountants who receive statements as PDFs from clients convert each file into rows of date, description, money out, money in, and running balance, ready to import into an accounting ledger. Because each row carries its own check value, rows marked gap can be inspected before import instead of discovering a missing transaction at month end.

Convert a client's quarterly statement PDF, list every transaction whose check value is gap, and report the reconciliation difference

Income and Affordability Checks

Lenders and landlords reviewing an applicant's statements need totals they can trust. The PivotBank API returns totalIn and totalOut alongside opening and closing balances, so an agent can summarise money in and money out for the period and refuse to summarise a statement whose reconciliation status is mismatch or unavailable.

Convert an applicant's statement, confirm the reconciliation status is ok, and report totalIn, totalOut, and the statement period

Key Endpoints

2 endpoints — the pivotbank api converts a digital bank statement pdf into structured json transactions, each with its date, description, money out, money in, running balance, and the page it was printed on.

METHOD

PATH

DESCRIPTION

POST

/api/v1/convert

Convert a bank statement PDF to transactions

GET

/api/v1/

Read the API index and auth walkthrough

POST

/api/v1/convert

Convert a bank statement PDF to transactions

GET

/api/v1/

Read the API index and auth walkthrough

Why Jentic?

What agents get from Jentic-routed access to this vendor.

Setup

Wiring PivotBank by hand means creating a Pro account API key, sending it as a bearer token, uploading PDFs as multipart or raw bodies, and managing Idempotency-Key retries yourself. Through Jentic you install once, import PivotBank from the API Directory, store the key once, and your agent converts statements.

Permission scoping

PivotBank exposes a single convert operation plus an open index, with no resource id in the path, so rules bound which operations your agent may call rather than which statement. You choose the operations it may call, so a rule can allow conversion alone.

Credential isolation

Your PivotBank 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 'convert a bank statement PDF' or 'extract statement transactions', and Jentic returns the matching PivotBank operation with its input schema so the agent calls the right endpoint without reading the reference docs.

FAQs

Specific to using PivotBank API through Jentic.

What authentication does the PivotBank API use?

Per its OpenAPI spec, the PivotBank API uses bearer authentication: send an API key of the form pvb_live_... in an Authorization: Bearer header, and the spec notes an x-api-key header is also accepted. Keys are created on the API keys page of your PivotBank account, are shown once, and must belong to a Pro account. The convert operation needs the key, while the index operation at /api/v1/ is open. Through Jentic the key is stored encrypted on your own instance and injected at call time.

Is there a PivotBank MCP server?

You don't need an MCP server to give your agent PivotBank. Jentic connects it directly from the API Directory: import PivotBank, store your API key once, and your agent can convert statements straight away. Operations are discovered on demand, so no extra server's tool definitions sit in your agent's context.

Can I limit what my agent is allowed to do with the PivotBank API?

Yes. Write a rule that allows only the convertStatement operation, so the agent can turn statement PDFs into transactions and nothing else, and every call it makes is logged. The open index operation can stay out of the rule if the agent has no need to read it.

Does the PivotBank API work with scanned statements?

No. The convert operation reads digital bank statements that have a text layer, up to 15 MB per file, and the spec states that scanned statements are not supported on this endpoint. A file that is not a readable PDF returns a 422 with the code unparseable and is not charged.

What are the rate limits for the PivotBank API?

The PivotBank API is metered by pages rather than by request count. Each conversion spends the statement's page count from the plan's monthly allowance, and every response carries X-Pages-Left plus RateLimit-Limit, RateLimit-Remaining, and RateLimit-Policy headers describing that allowance. The spec does not publish fixed numbers for each plan; check https://pivotbank.app for current plan allowances.

How do I convert a bank statement with the PivotBank API through Jentic?

Search Jentic for an intent like 'convert a bank statement PDF to transactions', import PivotBank, and store your API key once. Your agent then calls the convert operation at /api/v1/convert with the PDF and an Idempotency-Key, and reads the reconciliation verdict before using the rows. To run it on your own infrastructure, install Jentic One from its GitHub repo.

Pivotbank App PivotBank API

AI ReadinessAI-Aware (B)64/100

See full scorecard

Official vendor OpenAPI document · agent-readyData EnrichmentData Transformationbearer2 EndpointsREST

For Agents

Turn a text-layer bank statement PDF into a JSON list of transactions with balances, page numbers, and a reconciliation verdict that says whether the reading balances. Includes an open index operation describing the endpoints and auth walkthrough.

Use for: I need to extract the transactions from a bank statement PDF, Convert this bank statement into JSON with running balances, Check whether the extracted statement reconciles to the closing balance, Find all rows in a converted statement that break the running balance

Not supported: Does not handle scanned statement images, live bank account connections, or ledger posting. Use for converting digital bank statement PDFs into reconciled transactions only.

The PivotBank API converts a digital bank statement PDF into structured JSON transactions, each with its date, description, money out, money in, running balance, and the page it was printed on. Every reading is checked against the statement's own running balances: a reconciliation block reports whether opening balance plus every row lands exactly on the closing balance, and each transaction carries its own check value of ok, gap, or uncovered. An Idempotency-Key header lets a retry with the same file return the first answer without spending pages again, and the X-Pages-Left response header reports what remains of the plan's monthly page allowance.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: A-Signals: 4

95%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

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.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: BSignals: 4

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

62%

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.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: C-Signals: 4

51%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

100%

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

60%

Summary Coverage

Coverage of summaries across operations/tags/info.

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.

Security

Trust, risk posture, and security compliance.

Grade: B-Signals: 1

60%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: C-Signals: 1

50%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the PivotBank API to your agent

Capabilities

Start building with PivotBank API

Use Cases

Key Endpoints

Why Jentic?

Related APIs

FAQs

Pivotbank App PivotBank API

Jentic AI Readiness Score

PivotBank API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness