Grist connector for AI agents

Tools your data agent reaches for on Grist, scoped per user.

CALL ANY TOOL

48 tools for spreadsheet databases in Grist: fetch, add, update, and upsert records, run read-only SQL, create tables and columns, copy, fork, and compare documents, manage workspaces, and change access.

grist_add_columns

Add columns

Add one or more columns to an existing table. Returns a columns array with the id of each column created. Use update_columns to change existing columns. Use create_tables to make a whole new table.

Parameters

Name

Type

Required

Description

columns

array

Required

Columns to add. Each item is an object with an id (the column name) and an optional fields object such as type (Any, Text, Numeric, Int, Bool, Date, DateTime:<timezone>, Choice, ChoiceList, Ref:<tableId>, RefList:<tableId>, Attachments), label, formula, isFormula, and widgetOptions (a JSON string). Example: [{"id": "Email", "fields": {"type": "Text", "label": "Email"}}].

doc_id

string

Required

ID of the Grist document (a UUID-style string, also shown as the document's id in its URL or from Grist list workspaces results).

table_id

string

Required

Table identifier: the normalized table name shown as TABLE ID in the document's Raw Data page (for example Table1), or its numeric row ID in _grist_Tables.

grist_add_records

Add records

grist_apply_user_actions

Apply user actions

grist_compare_docs

Compare docs

grist_create_doc

Create doc

grist_create_tables

Create tables

grist_delete_column

Delete column

grist_delete_records

Delete records

grist_fork_doc

Fork doc

grist_get_attachment_metadata

Get attachment metadata

grist_get_current_user

Get current user

grist_get_doc_states

Get doc states

grist_get_org

Get org

grist_get_table_schema

Get table schema

grist_list_attachments

List attachments

grist_list_columns

List columns

grist_list_doc_snapshots

List doc snapshots

grist_list_orgs

List orgs

grist_list_records

List records

grist_list_workspace_access

List workspace access

grist_move_doc

Move doc

grist_restore_doc

Restore doc

grist_restore_workspace

Restore workspace

grist_run_sql_query

Query run sql

grist_trash_workspace

Trash workspace

grist_update_columns

Update columns

grist_update_doc

Update doc

grist_update_records

Update records

grist_update_workspace

Update workspace

grist_upsert_columns

Upsert columns

For more tools, view docs.

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Grist tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["grist"], toolNames: [
    "grist_list_tables",
    "grist_run_sql_query",
    "grist_update_records"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Find overdue invoices in the Billing document and mark them for follow-up" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["grist"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Find overdue invoices in the Billing document and mark them for follow-up" }],
  tools,
});

// Execute the tool call with the user's vaulted Grist access token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["grist"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Find overdue invoices in the Billing document and mark them for follow-up" }],
  tools,
});

// Tool call runs with the user's vaulted Grist access token
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["grist"] }, pageSize: 100,
});

const agent = new Agent({
  name: "data_agent",
  model: "gemini-2.5-pro",
  instruction: "Grist tools scoped to this user",
  tools,
});

await agent.run("Find overdue invoices in the Billing document and mark them for follow-up");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Grist tool. Click to copy, paste into your agent, done.

Records

Copy the prompt

Copied

List records in the Invoices table where Status is Overdue.

Copy the prompt

Copied

Add a record to Invoices for Acme, $4,200, due November 30.

Copy the prompt

Copied

Upsert these 15 customers into the Accounts table by email.

Queries and schema

Copy the prompt

Copied

Run a SQL query for total invoice amount by customer.

Copy the prompt

Copied

Show the columns and types in the Projects table.

Copy the prompt

Copied

Add a Renewal Date column to the Accounts table.

Documents and sharing

Copy the prompt

Copied

List the workspaces and documents in our team site.

Copy the prompt

Copied

Fork the Q4 Budget document so I can try changes.

Copy the prompt

Copied

Give priya@acme.com editor access to the Billing document.

SEE HOW AUTH WORKS

Each user connects their own Grist access token once, and Scalekit sends it with every call. Access tokens stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Grist

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Grist

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Grist

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Grist

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other database connectors.

GTM and RevOps Teams

CRM AI agent

Reads the Granola transcript after every call, extracts next steps and updates the HubSpot record, drafts the follow-up in Gmail, and confirms in Slack, all on the rep's own delegated OAuth.

GTM and RevOps Teams

Deal room sync

Pulls opportunity context from Salesforce, captures key decisions from Slack, and syncs a running summary to the deal room doc in Google Drive, but only when the deal actually changed.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Grist access token looks fine in a demo. In production every record and access change looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Grist today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Grist as the user or through a shared access token?

As the user. Each user connects their own Grist access token once, and Scalekit sends it with every call. Audit logs attribute every record, schema, and access change to that user, not a shared service account.

Where is the Grist access token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new access token. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Grist?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example grist_list_records and grist_run_sql_query without grist_delete_doc or grist_delete_workspace, which permanently remove documents. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Grist access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Can the agent run SQL against a Grist document?

Yes. grist_run_sql_query runs a read-only SQL SELECT query against the document's SQLite database, so the agent can join and aggregate across tables. Writes go through record tools such as grist_add_records and grist_update_records.