Coda connector for AI agents

Tools your docs agent reaches for on Coda, scoped per user.

CALL ANY TOOL

37 tools for collaborative docs in Coda: list docs and folders, read pages, tables, and formulas, upsert and update rows, create pages, and run automations.

coda_automation_trigger

Trigger automation

Run a Coda doc automation whose trigger is set to "Webhook invoked", optionally passing a JSON payload the automation can read. Returns a requestId; the automation runs asynchronously, so check coda_mutation_status_get with the requestId if you need to confirm. Use coda_automation_trigger to run a webhook-invoked automation. Use coda_row_button_push to press a button in a table row instead. The automation must already exist with a Webhook invoked trigger; its rule ID is shown in the automation's settings.

Parameters

Name

Type

Required

Description

doc_id

string

Required

ID of the Coda doc. Get it from coda_docs_list, or from the doc's URL: it is the part after `_d` in a link like https://coda.io/d/Project-Tracker_dAbCDeFGH (here AbCDeFGH).

rule_id

string

Required

ID of the automation rule to run, e.g. grid-auto-b3Jmey6jBS. It appears in the doc's automation settings when the rule's trigger is "Webhook invoked".

payload

object

Optional

JSON object to send to the automation. The automation can read it through Step 1 Result. Leave empty to send an empty object. Example: {"customer": "Acme", "amount": 120}.

coda_browser_link_resolve

Resolve browser link

coda_column_get

Get column

coda_columns_list

List columns

coda_control_get

Get control

coda_controls_list

List controls

coda_current_user_get

Get current user

coda_doc_acl_settings_get

Get doc acl settings

coda_doc_create

Create doc

coda_doc_get

Get doc

coda_doc_permissions_list

List doc permissions

coda_doc_principals_search

Search doc principals

coda_doc_sharing_metadata_get

Get doc sharing metadata

coda_doc_update

Update doc

coda_docs_list

List docs

coda_folder_children_list

List folder children

coda_folder_create

Create folder

coda_folder_update

Update folder

coda_formula_get

Get formula

coda_formulas_list

List formulas

coda_mutation_status_get

Get mutation status

coda_page_content_list

List page content

coda_page_export_begin

Page export begin

coda_page_export_status_get

Get page export status

coda_page_get

Get page

coda_page_update

Update page

Update a page in a Coda doc: rename it, change its subtitle, icon, cover image or hidden state, and append, prepend or replace its content with Markdown or HTML. Returns the page id and a requestId; the update is applied asynchronously, so check coda_mutation_status_get with the requestId if you need to confirm it. Use coda_page_update to edit an existing page. Use coda_page_create to add a new page, or coda_doc_update to rename the doc itself. Changing the page name or icon requires Doc Maker rights in the doc's workspace.

Parameters

Name

Type

Required

Description

doc_id

string

Required

ID of the Coda doc. Get it from coda_docs_list, or from the doc's URL: it is the part after `_d` in a link like https://coda.io/d/Project-Tracker_dAbCDeFGH (here AbCDeFGH).

page_id_or_name

string

Required

ID of the page, e.g. canvas-IjkLmnO. Get it from coda_pages_list. A page name also works, but Coda discourages names because users can rename pages, and duplicate names resolve to an arbitrary page.

content

string

Optional

New content to write to the page, in the format chosen in content_format. Leave empty to leave the content unchanged. Example: ## Action items\n- Send recap.

content_format

string

Optional

Format of content: `markdown` (default) or `html`. One of: `markdown`, `html`. Default: `markdown`.

element_id

string

Optional

ID of a content element on the page (from coda_page_content_list) to insert relative to, instead of the start or end of the page. Only used when content is set.

icon_name

string

Optional

Name of a Coda icon to set on the page, e.g. notes. Leave empty to keep it.

image_url

string

Optional

URL of a new cover image for the page. Leave empty to keep it.

insertion_mode

string

Optional

Where to put the new content: `append` (default) adds it at the end, `prepend` at the start, and `replace` overwrites the existing page content. Only used when content is set. One of: `append`, `prepend`, `replace`. Default: `append`.

is_hidden

boolean

Optional

Set true to hide the page from the doc's page list, false to show it. Leave empty to keep the current state.

name

string

Optional

New name for the page. Leave empty to keep it. Example: Meeting Notes (archived).

subtitle

string

Optional

New subtitle for the page. Leave empty to keep it.

coda_pages_list

List pages

coda_row_get

Get row

coda_rows_list

List rows

List rows in a Coda table or view, optionally filtered by a column value and sorted by creation, update or natural order. Returns a page of rows with each row's id, name, index, browser link, created and updated times, and cell values keyed by column ID (or name), plus nextPageToken and nextSyncToken. Use coda_rows_list to read or search table data. Use coda_row_get when you already have a row ID.

Parameters

Name

Type

Required

Description

doc_id

string

Required

ID of the Coda doc. Get it from coda_docs_list, or from the doc's URL: it is the part after `_d` in a link like https://coda.io/d/Project-Tracker_dAbCDeFGH (here AbCDeFGH).

table_id_or_name

string

Required

ID of the table or view, e.g. grid-pqRst-U. Get it from coda_tables_list. A table name also works, but Coda discourages names because users can rename tables.

limit

integer

Optional

Maximum number of results to return in one page. Defaults to 25. Example: 10. Default: `25`.

page_token

string

Optional

Opaque token for the next page of results. Pass the nextPageToken value from the previous response; leave empty for the first page.

query

string

Optional

Filter rows by one column value, written as <column_id_or_name>:<json value>. Column names must be in double quotes and string values must be JSON-quoted. Examples: c-tuVwxYz:"Apple" or "Status":"Done" or c-AbCd:42.

sort_by

string

Optional

Row order: `createdAt` (default, oldest first), `natural` (the order shown in the table or view in the UI), or `updatedAt` (by last value change). One of: `createdAt`, `natural`, `updatedAt`.

sync_token

string

Optional

nextSyncToken from a previous full listing. Pass it to get only rows changed since that call.

use_column_names

boolean

Optional

If true, the row values are keyed by column name instead of column ID. Coda discourages this because names break when columns are renamed. Defaults to false.

value_format

string

Optional

Format of the cell values in the response. `simple` (default) returns strings, numbers and booleans, with multi-value cells as comma-separated text; `simpleWithArrays` returns multi-value cells as JSON arrays; `rich` returns lossless structured values (Markdown text, currency and date objects, linked-row references). One of: `simple`, `simpleWithArrays`, `rich`.

visible_only

boolean

Optional

If true, return only visible rows and columns. Defaults to false.

coda_rows_upsert

Upsert rows

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);

// Coda tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["coda"], toolNames: [
    "coda_docs_list",
    "coda_rows_list",
    "coda_rows_upsert"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Find open tasks in the Q4 Launch tracker and add a row for the pricing page task" }] });

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: ["coda"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Find open tasks in the Q4 Launch tracker and add a row for the pricing page task" }],
  tools,
});

// Execute the tool call with the user's vaulted Coda 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: ["coda"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Find open tasks in the Q4 Launch tracker and add a row for the pricing page task" }],
  tools,
});

// Tool call runs with the user's vaulted Coda 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: ["coda"] }, pageSize: 100,
});

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

await agent.run("Find open tasks in the Q4 Launch tracker and add a row for the pricing page task");

Try these prompts

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

Docs and pages

Copy the prompt

Copied

List the Coda docs I can access.

Copy the prompt

Copied

Create a page called Retro notes in the Q4 Launch doc.

Copy the prompt

Copied

Export the Launch plan page as Markdown.

Tables

Copy the prompt

Copied

List open tasks in the Q4 Launch tracker.

Copy the prompt

Copied

Add a row for the pricing page task, owned by Dana.

Copy the prompt

Copied

Mark the onboarding email task as done.

Automation and sharing

Copy the prompt

Copied

Press the Notify owner button on the pricing task row.

Copy the prompt

Copied

Trigger the weekly digest automation in the Q4 Launch doc.

Copy the prompt

Copied

Who is the Q4 Launch doc shared with?

SEE HOW AUTH WORKS

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

Authorize

Your user connects

Coda

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

Coda

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

Coda

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

Coda

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 docs and productivity connectors.

Support and Ops Teams

Meeting prep

Pulls agenda, participant context, and open action items before every meeting.

Engineering Teams

Engineering standup agent

Pulls commits from GitHub and GitLab, tracks issue movement in Jira, and posts a per-engineer standup brief to Slack. Each engineer's activity is read on their own delegated OAuth.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Coda access token looks fine in a demo. In production every row update and page edit 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.

Coda 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 Coda as the user or through a shared token?

As the user. Each user connects their own Coda access token once, and Scalekit sends it with every call. Audit logs attribute every row change, page edit, and automation run to that user, not a shared service account.

Where is the Coda 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 Coda?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example the read tools without coda_row_button_push or coda_automation_trigger, which run whatever action the button or automation defines. No Coda tool deletes data. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Coda 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.

Why does a Coda write not show up right away?

Coda applies some writes asynchronously, such as row inserts. coda_mutation_status_get checks whether a write has finished, so the agent can confirm the change before it reads the table again.