Get started

Gigasheet for AI agents

Gigasheet is a spreadsheet-style interface for exploring and cleaning very large datasets. Data and operations teams use it to analyze big files without a database. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect GigasheetSee the 150 actions ↓
Databases and spreadsheetsAPI keyMCP + RESTgigasheet.com
AUDIT LOG · GIGASHEETPOLICY: acme-support
09:41:07 · claude · u_8f2read
gigasheet.list_datasets
List All Datasets✓ allowed · 212ms
09:41:08 · claude · u_8f2read
gigasheet.get_library
Get Library Files✓ allowed · 164ms
09:41:09 · claude · u_8f2write
gigasheet.create_mcp
Send MCP Request to Sheet Assistant✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
gigasheet.delete_delete_handle
Delete sheet or folder by handle✕ blocked · policy: deny
EVERY GIGASHEET CALL, ON THE RECORD
01 · USE CASES

What agents do in Gigasheet.

01

Append new rows to a dataset

Add a fresh batch of exported rows to an existing dataset so it stays current for analysis.

02

Count rows matching a filter

Count how many rows in a dataset match a condition, as a read-only check before running a bigger job.

03

Build a formula column

Create a formula column that flags rows meeting a business rule, like orders over a spend threshold.

02 · ACTIONS

150 Gigasheet actions, graded by risk.

Every Gigasheet action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

59

Look things up. Allowed by default.

  • gigasheet.get_library
    Get Library Files
  • gigasheet.list_datasets
    List All Datasets
  • gigasheet.search_library
    Search Library
  • gigasheet.get_user_whoami
    Get Authenticated User Info
  • gigasheet.get_library_home
    Get Library Home Page Files
  • gigasheet.get_library_path
    Get Library Path
  • gigasheet.get_user_details
    Get User Details
  • gigasheet.get_cell_comments
    Get Cell Comments
  • gigasheet.get_dataset_views
    Get Dataset View Metadata
  • gigasheet.get_user_metadata
    Get User Metadata
  • gigasheet.get_ai_handle_logs
    Get Sheet AI Chat History
  • gigasheet.get_dataset_handle
    Get Dataset by Handle
  • gigasheet.get_library_handle
    Get Library Files in Directory
  • gigasheet.get_users_autofill
    Get User Autofill Suggestions
  • gigasheet.list_billing_plans
    List Billing Plans
  • gigasheet.get_generate_handle
    Generate New Handle
+ 43 MORE

write

74

Create and change things. Allow, or ask the user first.

  • gigasheet.create_mcp
    Send MCP Request to Sheet Assistant
  • gigasheet.send_invite
    Send Invite Emails
  • gigasheet.create_lookup
    Create Cross-File Lookup
  • gigasheet.create_ai_chat
    Create AI Chat Query
  • gigasheet.post_upload_url
    Upload from URL
  • gigasheet.post_maven_export
    Export Gigasheet to S3
  • gigasheet.post_maven_import
    Import from S3
  • gigasheet.create_files_blank
    Create Blank File
  • gigasheet.post_upload_direct
    Upload Raw Data Direct
  • gigasheet.create_dataset_view
    Create Dataset View
  • gigasheet.create_explode_json
    Explode JSON Column
  • gigasheet.create_split_column
    Split Column
  • gigasheet.update_dataset_cell
    Update Dataset Cell
  • gigasheet.update_dataset_views
    Update Dataset View
  • gigasheet.create_dataset_comment
    Add Comment to Cell
  • gigasheet.create_dataset_formula
    Create Formula Column
+ 58 MORE

destructive

17

Delete, cancel or archive. Ask first, or deny outright.

  • gigasheet.delete_delete_handle
    Delete sheet or folder by handle
  • gigasheet.delete_ai_handle_logs
    Delete Sheet Assistant Logs
  • gigasheet.delete_columns_by_name
    Delete columns by name
  • gigasheet.delete_dataset_comment
    Delete Dataset Comment
  • gigasheet.delete_multiple_columns
    Delete multiple columns from file
  • gigasheet.delete_files_columns_column
    Delete column from sheet
  • gigasheet.delete_dataset_handle_views_view
    Delete dataset view
  • gigasheet.delete_dataset_liveshare_shareid
    Delete dataset live share
  • gigasheet.delete_dataset_handle_delete_rows
    Delete Rows from Dataset
  • gigasheet.cancel_enrich_user_defined_http_task
    Cancel HTTP Enrichment Task
  • gigasheet.delete_filter_templates_filter_handle
    Delete Filter Template
  • gigasheet.delete_dataset_handle_deduplicate_rows
    Delete Duplicated Rows from Dataset
  • gigasheet.delete_connectors_sources_connectorname
    Delete Connector Source
  • gigasheet.delete_dataset_delete_rows_not_matching_filter
    Delete Rows Not Matching Filter
  • gigasheet.delete_dataset_handle_delete_rows_matching_filter
    Delete Rows Matching Filter
  • gigasheet.reset_client_state
    Reset Client State to Default
+ 1 MORE
03 · HOW IT WORKS

Gigasheet in three steps.

  1. 01Your users connect GigasheetThey add their Gigasheet api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “send MCP Request to Sheet Assistant” can wait for the user, and “delete sheet or folder by handle” can be denied outright.
  3. 03Any agent can actYour agent calls Gigasheet through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('gigasheet', {
  read: 'allow',
  write: 'ask',        // create_mcp
  destructive: 'deny',  // delete_delete_handle
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Gigasheet connects.

Users add their Gigasheet api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Gigasheet connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Gigasheet from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More databases and spreadsheets apps.

Google Sheets58 actionsExcel55 actionsSnowflake17 actionsAnyDB9 actionsNeon110 actionsGoogle BigQuery63 actionsNocoDB28 actionsPrisma22 actions
ALL DATABASES AND SPREADSHEETS APPS →
07 · FAQ

Gigasheet and Arc0, answered.

Q01

Can I use Gigasheet with Claude, ChatGPT or Cursor?

Yes. Connect Gigasheet to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Gigasheet actions you allow.

Q02

How do users connect Gigasheet?

Users add their Gigasheet api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Gigasheet actions can my agent take?

150 in total: 59 read, 74 write and 17 destructive, such as “send MCP Request to Sheet Assistant”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Gigasheet?

Yes. Actions like “delete sheet or folder by handle” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Gigasheet too?

Yes. The same Gigasheet connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Gigasheet into your agent.

Your users connect Gigasheet once, under your brand. Your agent gets 150 actions behind your policies, with every call on the record.

Connect GigasheetBrowse all apps →

Free to build · MCP + REST · Audit log on every plan