< Back to all integrations

CSV

Data & Infrastructure

Read CSV files into rows and turn rows into CSV files, so AI agents and workflows can move data between file drops and systems of record.

Book a demo
[ CSV + engini ]

CSV for AI agents and workflows.

Banks, payroll providers, partners and older systems still send and expect CSV. engini parses a CSV file into rows a workflow or an agent can use, and builds a CSV file from rows, so data moves between SFTP drops, email attachments and shared folders on one side and your ERP, CRM and databases on the other.

MCPPython and TypeScript SDKCLIREST APIWorkflow Studio
Read the CSV guide →
ToolsParse CSV into rows; create a CSV file from rows
Works withSFTP, FTP, On Prem Files, Google Drive, OneDrive, Box, Gmail and Outlook attachments
[ 01 / What agents can do ]

What your agent can do in CSV. Every tool is one you allow or leave out.

The CSV tools in engini, grouped by what they change. Read tools are safe to hand out widely. Write and delete tools go only to the agents that need them.

Files

Parse CSV

Read a CSV file into rows and columns.

Read
Create CSV

Turn rows into a CSV file.

Write

Triggers

CSV has no triggers of its own. The workflow starts when the file arrives, for example on a schedule that checks an SFTP folder or on a new email.

[ 02 / Connect your agent ]

Connect your AI agent to CSV. Four ways in, one set of permissions.

MCP

Claude, ChatGPT, Cursor

Create an MCP server in engini with your CSV connection and only the tools you choose. Add its address to your client and sign in through engini. There is no key to copy.

MCP client setup →
SDK

Python and TypeScript

Hand your agent a toolset of CSV tools. The SDK gives OpenAI and Anthropic models the tools in the format they expect and runs the ones they pick.

SDK guide →
CLI

For coding agents

The engini CLI connects CSV and runs its tools from a terminal, with machine-readable output, so an AI coding agent can drive it without getting stuck.

CLI guide →
REST API

Any language

Every CSV tool is an endpoint. Call it with exact inputs from a scheduled job or a sync, with no model in the loop.

API reference →
MCP in four steps
In engini, connect CSV and create an MCP server with that connection and the tools this agent may use.
Claude: Settings, Connectors, Add custom connector, then paste the server address.
Cursor: add the address to .cursor/mcp.json. Claude Code: claude mcp add.
Sign in through engini when the client asks. The agent sees only the tools you chose.
Cursor, connected to CSV through engini
// .cursor/mcp.json: Cursor, connected to CSV through engini
{
"mcpServers": {
"engini-csv": {
"url": "<your engini MCP server address>"
}
}
}

Create the MCP server in engini with your CSV connection and the tools this agent may use, then paste its address. The client signs in through engini on first use. Claude, VS Code and other clients take the same address: see the MCP client setup guide.

Try asking your agent
“Read the bank file from today and list the payments.”
“Make a CSV of open invoices for the collections agency.”
“Parse the partner price list and update the ERP.”
“Export this week's new customers as CSV for the payroll provider.”
“Which rows in this file failed to load?”
“Turn these Salesforce accounts into a CSV.”

Each request runs through the CSV tools in the agent's toolset or MCP server. If a tool is not allowed, the agent cannot call it.

[ 03 / What teams build ]

What teams build on CSV. Agents and workflows, across systems.

Finance

Bank files into the ERP

A statement file from the bank's SFTP folder is parsed and the payments are matched to open invoices.

SFTPCSVNetSuite
Payroll

Exports the provider expects

Rows from Workday become the CSV file the payroll provider wants, uploaded on schedule.

WorkdayCSVSFTP
Operations

Partner lists into the catalog

A partner's CSV price list updates items in the ERP and the store.

CSVNetSuiteShopify
Sales

Bulk loads into Salesforce

A CSV of accounts loads through the Salesforce Bulk API, and failed rows come back as a CSV.

CSVSalesforce

Every integration runs both ways, so any of these flows can also run in reverse. These are examples, not the limit: any flow between CSV and another system engini connects is available.

[ 04 / Agent Policy ]

You decide what each agent may do in CSV. engini enforces it on every call.

Toolsets

Only the tools you allow

A toolset lists the CSV tools an agent may call and the connection each one uses. Give one agent read tools only and another the write it needs. engini refuses any call outside the toolset.

MCP servers

Scoped when you set them up

An MCP server exposes only the connections and tools chosen when it is created, and engini shows who uses each server.

Identity

Whose permissions apply

Connect a person's own CSV account and engini acts as that person, with their CSV permissions. Use a shared integration account and it acts as that account. Every run is recorded under the user who started it.

Credentials

Kept out of prompts

Your agent never needs your credentials: engini stores them and adds them when it runs each call, so keys stay out of prompts and tool inputs.

Audit

Every call on record

Every call lands in History and the audit log, which you can export or stream to your SIEM.

Environments

Test before production

Workspaces keep teams apart, and development, staging and production environments keep a test agent away from live data.

SOC 2 Type IIISO 27001GDPRSecurity at engini →
[ 05 / Set up ]

Connect CSV in three steps. Then decide what each agent may do.

Step 01

Sign in to CSV

CSV needs no sign-in. Add the CSV tools to a workflow, or to a toolset next to the connection that holds the file.

Step 02

Choose the tools

Add the connection to an MCP server or a toolset with only the tools each agent needs.

Step 03

Build or ask

Use the connection as a step in a workflow, or ask your agent to work in CSV from Claude, ChatGPT, Cursor or your own code.

Full CSV setup guide →
[ 06 / Questions ]

CSV and engini. Straight answers.

Can an AI agent write to CSV, or only read?

Both. engini builds CSV files from rows; where a file goes is up to the connection that writes it (SFTP, Drive, email). Whether a given agent may use them is up to you: give it a toolset or an MCP server with read tools only, and it cannot call the rest.

Does the agent act as me in CSV?

CSV tools work on the file they are given; access comes from the connection that reads or writes the file. Every run is recorded under the person who started it.