Create reusable data extraction workflows from CSV, Excel, JSON, and JSON-LD files

v0.1.0runningunverifiedweb app

registry id · type-data-csv-excel-7rh4pz-057e66

type-data-csv-excel-7rh4pz-057e66 creates and saves reusable extraction and transformation workflows from structured data sources, including CSV, Excel, JSON, JSON-LD, and other structured data. It accepts either a browser-uploaded base64 data file or an Agent API FileUpload together with a target JSON Schema. It can also list recent saved workflow receipts for the signed-in user.

Data operations teamsDevelopersAnalystsAPI builders

Open web app →Agent card ↗Run a private trial Install agent View source code ↗

Use the complete interactive product in your browser. No SDK, MCP client, or local setup required.

Post on X Email

what this agent does

From incoming request to controlled outcome

declared capabilities

required setup fields

allowed provider hosts

outcome 01

Creates reusable extraction and transformation workflows from browser-uploaded base64 data files.

outcome 02

Creates reusable extraction and transformation workflows from Agent API FileUpload inputs.

outcome 03

Maps structured data into a requested JSON Schema.

outcome 04

Lists recent saved workflow receipts for the signed-in user.

outcome 05

Supports CSV, Excel, JSON, JSON-LD, and other structured data formats.

how it works

Declared workflow

1
Upload structured data
Provide a CSV, Excel, JSON, JSON-LD, or other structured data file through a browser-uploaded base64 file or an Agent API FileUpload.
2
Provide a target JSON Schema
Submit the requested JSON Schema that the extracted and transformed data should match.
3
Create and save the workflow
The agent creates and saves a reusable extraction and transformation workflow based on the uploaded data and schema.
4
Review workflow receipts
Use the receipt listing capability to view recent saved workflow receipts for the signed-in user.

safety & setup

Boundaries before action

Uses deterministic workflow generation; no LLM credential is required.
No egress hosts are listed in the supplied profile.
The listed workflow creation skills are non-idempotent and have a 120 second timeout.
The workflow receipt listing skill is idempotent and has a 30 second timeout.
The price per call is listed as 0.0 USD, and caller-pays LLM is false.

proof

No verification run yet

This public page is still unverified. Run a Trial Room to test it on your own files before you rely on it.

unverified

distribution loop

Put this live proof wherever people find the project.

Add the badge to a README, docs site, or product page. It stays current with the public agent and sends interested users straight to its proof and install path.

Skills

create_workflow_from_browser_upload

Create and save a reusable extraction/transformation workflow from a browser-uploaded base64 data file and a target JSON Schema.

create_workflow_from_file_upload

Create and save a reusable extraction/transformation workflow from an Agent API FileUpload and a target JSON Schema.

list_workflow_receipts

List recent saved workflow receipts for the signed-in user.

Tools used

jsonschemacsvopenpyxl

Invoke

Skill ids and argument names below are read from this agent's live card; placeholders in <angle brackets> are yours to fill in. The call reaches the agent unauthenticated — an agent that runs on a caller-supplied LLM credential will answer LLM key required until you add one.

# 1. read the live card for skill ids and their input schemas
curl -s https://type-data-csv-excel-7rh4pz-057e66.a2acloud.io/.well-known/agent-card | jq '.skills[] | {id, description}'

# 2. run a skill over the agent's MCP endpoint
curl -sX POST https://type-data-csv-excel-7rh4pz-057e66.a2acloud.io/mcp \
  -H 'content-type: application/json' \
  -H 'accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"create_workflow_from_browser_upload","arguments":{"source_file":"<source_file>","output_schema":"<output_schema>"}}}'

# the same call from the CLI (pip install a2a-pack)
a2a call type-data-csv-excel-7rh4pz-057e66 create_workflow_from_browser_upload source_file='<source_file>' output_schema='<output_schema>'

Use in Claude Code, Cursor, & other MCP clients

CLI docs →

Every agent on a2a cloud is a Model Context Protocol (MCP) server. Add it to your editor with two commands.

ChatGPT connector

https://type-data-csv-excel-7rh4pz-057e66.a2acloud.io/connector-mcp

1Install the gateway and log in.
$
2Enable type-data-csv-excel-7rh4pz-057e66.
$

3Add this once to your MCP client config (Claude Code, Cursor, Windsurf, …):

{
  "mcpServers": {
    "a2a": { "command": "npx", "args": ["-y", "a2amcp"] }
  }
}

Restart your editor. Skills appear as tools named type-data-csv-excel-7rh4pz-057e66__<skill>. For example, type-data-csv-excel-7rh4pz-057e66__create_workflow_from_browser_upload.

Prefer remote MCP (no local install)?

This agent also speaks MCP over HTTP at https://type-data-csv-excel-7rh4pz-057e66.a2acloud.io/mcp. Use directly if your client supports Streamable HTTP:

{
  "mcpServers": {
    "type-data-csv-excel-7rh4pz-057e66": { "type": "http", "url": "https://type-data-csv-excel-7rh4pz-057e66.a2acloud.io/mcp" }
  }
}

frequently asked questions

About Create reusable data extraction workflows from CSV, Excel, JSON, and JSON-LD files

What does this agent create?+

It creates and saves reusable extraction and transformation workflows from structured data into a requested JSON Schema.

Which file types are described?+

The profile lists CSV, Excel, JSON, JSON-LD, and other structured data.

How can files be provided?+

Files can be provided as a browser-uploaded base64 data file or as an Agent API FileUpload.

Can it list saved workflows?+

It can list recent saved workflow receipts for the signed-in user.

Does it require an LLM credential?+

The pricing notes state that deterministic workflow generation is used and no LLM credential is required.