Retable MCP server for AI agents and assistants

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with Retable MCP or direct API to read tables, create and update rows, query records, and upload files through natural language.

Retable logoRetable
Api Key

Retable is a collaborative spreadsheet and database platform for organizing workspaces, tables, and files. Use it to manage projects, structure data, and collaborate with teammates in flexible tables.

11 Tools

Try Retable now

Type what you want done — sign in and watch it run live in the Tool Router playground.

TOOL ROUTER PLAYGROUND
Retable
Try asking
TOOLS

Supported Tools

Every Retable action and event your agent gets out of the box.

Add Columns

Append one or more typed columns to a table and return the complete resulting column list.

Delete Columns

Permanently delete one or more columns and their cell data, then return the complete remaining column list.

Delete Rows

Permanently delete one or more rows from a table; missing row IDs are ignored and count as zero deletions.

Get Rows

Retrieve all rows or up to 50 selected rows from a Retable.

Get Table

Get one table's metadata, column IDs and types, and views before reading or changing its data.

Insert Rows

Insert one or more rows into a table in one request and return the created rows with their IDs.

List Project Tables

List tables in one Retable project with their IDs, columns, and parent workspace and project IDs.

List Workspace Projects

List projects accessible in one workspace, including project IDs needed to discover tables.

List Workspaces

List workspaces visible to the connected Retable account, including each workspace ID needed to discover projects.

Search Rows

Search a table for a value in a primary column and return matching rows from an optional starting offset.

Update Rows

Update cells in one or more existing rows in one request and return the updated row IDs.

SETUP GUIDE

Connect Retable MCP Tool with your Agent

1

Install Composio

typescript
npm install @composio/core ai @ai-sdk/mcp @ai-sdk/openai
Install the Composio SDK and your agent framework
2

Create a session with MCP enabled

typescript
import { Composio } from "@composio/core";

const composio = new Composio();
const { mcp } = await composio.create("your-user-id", {
  toolkits: ["retable"],
  mcp: true,
});
Create a session scoped to Retable and read its MCP URL and headers
3

Connect your agent to the MCP server

typescript
import { createMCPClient } from "@ai-sdk/mcp";
import { openai } from "@ai-sdk/openai";
import { generateText, stepCountIs } from "ai";

const client = await createMCPClient({
  transport: { type: "http", url: mcp.url, headers: mcp.headers },
});

const { text } = await generateText({
  model: openai("gpt-5.6-sol"),
  tools: await client.tools(),
  prompt: "List all tables in the 'Marketing' workspace and show the first 10 rows of the 'Campaigns' table.",
  stopWhen: stepCountIs(10),
});

console.log(text);
await client.close();
Pass the session's MCP URL and headers to your agent and run a Retable request
SETUP GUIDE

Connect Retable API Tool with your Agent

1

Install Composio

typescript
npm install @composio/core @composio/openai openai
Install the Composio SDK, the OpenAI provider, and the OpenAI SDK
2

Create a Composio session

typescript
import OpenAI from "openai";
import { Composio } from "@composio/core";
import { OpenAIResponsesProvider } from "@composio/openai";

const composio = new Composio({ provider: new OpenAIResponsesProvider() });
const client = new OpenAI();

const session = await composio.create("your-user-id", { toolkits: ["retable"] });
const tools = await session.tools();
Initialize Composio with the OpenAI Responses provider and create a session scoped to Retable
3

Run Retable tools with your agent

typescript
let response = await client.responses.create({
  model: "gpt-5.6-sol",
  tools,
  input: [{ role: "user", content: "List all tables in the 'Marketing' workspace and show the first 10 rows of the 'Campaigns' table." }],
});

while (response.output.some((o) => o.type === "function_call")) {
  const outputs = await composio.provider.handleToolCalls(session, response.output);
  response = await client.responses.create({
    model: "gpt-5.6-sol",
    tools,
    previous_response_id: response.id,
    input: outputs,
  });
}

console.log(response.output_text);
Send a request, execute the Retable tool calls through the session, and print the final answer

Why Use Composio?

AI Native Retable Integration

  • Supports both Retable MCP and direct API based integrations
  • Structured, LLM-friendly schemas for reliable tool execution
  • Rich coverage for reading, writing, and querying your Retable data

Managed Auth

  • Built-in API key handling with secure storage
  • Central place to manage, scope, and revoke Retable access
  • Per user and per environment credentials instead of hard-coded keys

Agent Optimized Design

  • Tools are tuned using real error and success rates to improve reliability over time
  • Comprehensive execution logs so you always know what ran, when, and on whose behalf

Enterprise Grade Security

  • Fine-grained RBAC so you control which agents and users can access Retable
  • Scoped, least privilege access to Retable resources
  • Full audit trail of agent actions to support review and compliance

Rolling this out across your team?

Give your team centralized access control across every framework with Composio’s MCP Gateway.

EXPLORE MCP GATEWAY
FAQ

Frequently asked questions

Start with Retable.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Retable tool your agent needs.Free to start.

Start building