Coda MCP. Manage structured data and automate document workflows.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Coda MCP Server connects your AI agent directly to your Coda workspace. It lets you manage structured data, automate document tasks, and perform CRUD operations on your collaborative documents using natural conversation.
You can list documents, inspect tables, and update rows without opening the Coda app. It's full document orchestration and data architecture, all via your agent.
What your AI agents can do
Delete rows
Removes specified rows from a Coda table.
Get doc details
Retrieves metadata for a specific Coda document.
Get table details
Gets metadata and structure details for a specific table within a document.
List all documents and list tables within a specified document ID using list_docs and list_tables.
Determine the structure of a table by listing columns (list_columns) or getting detailed table metadata (get_table_details).
Retrieve specific row data from a table using list_rows, optionally filtering the results.
Add new data records (insert_rows) or modify existing fields in a row (update_row).
Permanently remove specified rows from a table using delete_rows.
Get the current value of named formulas and retrieve detailed document metadata using list_formulas and get_doc_details.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Coda MCP Server: 11 Tools for Document & Data Ops
These tools allow your agent to perform every basic data operation on your Coda workspace, from reading rows to updating complex formulas.
019dd0d3delete rows
Removes specified rows from a Coda table.
019dd0d3get doc details
Retrieves metadata for a specific Coda document.
019dd0d3get table details
Gets metadata and structure details for a specific table within a document.
019dd0d3get user profile
Retrieves your personal Coda user profile information.
019dd0d3insert rows
Adds one or more new rows of data to a specified table.
019dd0d3list columns
Lists all column names and types for a given table.
019dd0d3list docs
Lists all documents accessible to your account.
019dd0d3list formulas
Retrieves a list of all named formulas available in a document.
019dd0d3list rows
Lists the contents of a table, supporting filtering by criteria.
019dd0d3list tables
Lists all tables contained within a specific document.
019dd0d3update row
Modifies the values in specific fields of an existing row.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Coda, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
Coda MCP Server connects your AI agent directly to your Coda workspace. You'll manage structured data, automate document tasks, and perform CRUD operations on your collaborative documents using natural conversation. You can list documents, inspect tables, and update rows without ever opening the Coda app. It's full document orchestration and data architecture, all through your agent.
How Coda MCP Works
- 1 Get your Coda API Token from your Account Settings > API Settings.
- 2 Connect your AI client (like Cursor or Claude) to the Coda MCP Server via Vinkius.
- 3 Tell your agent what you need: 'List all project tables in my main document' or 'Update the status of the 'Design API' row to Done.'
The bottom line is, your AI agent handles the entire document data flow, letting you treat your Coda workspace like a database accessible via natural language.
Who Is Coda MCP For?
The Project Manager who needs to update task statuses across dozens of linked sheets without opening a browser tab. The Operations Analyst who manages high-volume lead tracking and needs to audit data structures. Product Leads who need to pull specific formula-driven metrics for reports without manual data exports.
Retrieves task lists and updates row statuses across multiple project hubs using natural language commands.
Automates lead tracking and manages relational data sets, coordinating inserts, updates, and deletes without leaving their primary workspace.
Monitors project hub activity and pulls specific metrics driven by Coda formulas through simple AI queries.
What Changes When You Connect
- Update task statuses and track leads instantly. Use
update_rowandinsert_rowsto modify project data without navigating multiple sheets. - See the full structure of any table.
list_columnsgives you the column names and types, so you always know what data you're working with. - Get a bird's-eye view of your workspace. Use
list_docsto see every document you own andlist_tablesto map out your entire data architecture. - Run complex calculations via AI.
list_formulaslets you retrieve the current value of a named formula, pulling insights from Coda's native math engine. - Audit your data trail. Use
delete_rowswhen you need to permanently remove records, or uselist_rowsto pull an exportable list of everything currently in a table. - Access profile data.
get_user_profileprovides your account details, which is useful for reporting and logging user activity.
Real-World Use Cases
The Quarterly Audit
The Operations Analyst needs to check all lead records from the last quarter. They ask their agent, 'List all rows in the 'Leads' table where Status is 'Nurturing' and Date is before 2024-01-01.' The agent uses list_rows and filters the results, giving the analyst a precise, actionable list without manual spreadsheet filtering.
Project Status Update
A Project Manager needs to mark three tasks as 'Complete' and update the completion date. They tell their agent, 'Update the row for 'Design API' in the 'Tasks' table to Status: Complete and Date: Today.' The agent calls update_row three times, updating the project hub instantly.
Schema Discovery
A new user joins and needs to know what data lives in the 'Resource Tracker' table. Instead of clicking through settings, they ask, 'What columns does the 'Resource Tracker' table have?' The agent calls list_columns and returns the full schema list, solving the initial discovery headache.
Archiving Old Data
An Operations Analyst must remove all test records from a development table. They tell their agent, 'Delete all rows from the 'Test Data' table that have no Owner.' The agent uses delete_rows and confirms the records are gone, keeping the dataset clean.
The Tradeoffs
Manual Tab Switching
Opening Coda in a browser, manually clicking between the 'Tasks' table, the 'Resources' table, and the 'Summary' view to gather a status report.
→
Ask your agent to coordinate it. For instance, tell your agent to list_tables first, then list_columns on the necessary tables, and finally list_rows to build the full report. It handles the orchestration.
Forgetting Metadata
Trying to update a row without knowing the exact field name, leading to an error because the field name changed last week.
→
First, ask your agent to use list_columns on the target table. This confirms the precise field names you need before you run update_row.
Partial Updates
Manually updating a single row, forgetting to update the linked 'Project Budget' row that needs the same change.
→
Use the agent to run multiple, coordinated actions. Tell it: 'First, run update_row on the 'Tasks' table. Then, use update_row again on the 'Project Budget' table.' It manages the sequence.
When It Fits, When It Doesn't
Use this if you need to treat your Coda workspace like a database that can be queried and modified entirely through natural conversation. This is for data architects, ops engineers, and PMs who deal with structured data daily. You need the agent to perform multi-step data operations, like 'get the user profile, then list the documents, then update the row.'
Don't use this if you only need to view a single, static document or if your required workflow is simple enough to live entirely within Coda's UI without external data calls. If you only need to read data, list_rows is enough, but if you need to change the data, you need the full set of tools.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Coda. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 11 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Juggling tabs just to get a status report is a huge waste of time.
Right now, getting a status report means opening the main Coda document. You click into the 'Tasks' table to check row statuses. Then you have to switch to the 'Project Resources' tab to see who owns the task. If you need the total budget, you have to manually click on the 'Summary' view and copy the formula output into a separate spreadsheet.
With the Coda MCP Server, your AI acts as a data coordinator. You just ask it, 'What is the current status of the Q3 launch?' It runs `list_rows` on the 'Tasks' table, checks `list_formulas` for the budget, and gives you a single, consolidated answer.
Coda MCP Server: Control your data, not the UI.
Forget manually clicking to update a task. You don't have to navigate to the row, open the field, and type in the new status. You just tell your agent, 'Mark the 'Design API' task as complete.' The agent uses `update_row` behind the scenes, instantly modifying the source data.
The difference is control. You're no longer restricted to the Coda interface. Your AI agent manages the data layer directly, making your entire workflow faster and more reliable.
Common Questions About Coda MCP
How do I list all my Coda documents using list_docs? +
It lists every document you have access to. This helps you find the specific document ID you need to work with before running any other commands.
Can I update a row with the update_row tool? +
Yes, you update fields in an existing row. You must provide the specific row ID and the column names/values you want to change.
What is the difference between list_rows and get_table_details? +
Use get_table_details to understand the table's structure (columns and metadata). Use list_rows when you want to see the actual data records inside the table.
Does the Coda MCP Server let me run formulas? +
Yes, you can use list_formulas to retrieve the value of named formulas in your document, letting your AI agent access Coda's computational logic.
How do I use list_columns to understand the structure of a table? +
The list_columns tool returns the schema of any specified table. This lets you see all column names and their data types before you try to read or write data to them.
What is the best way to update data using the update_row tool? +
You must provide the unique row ID, the table ID, and a key-value map of the fields you want to change. The tool only updates the specified fields, leaving the rest of the row untouched.
How does get_user_profile help me understand my current workspace? +
The get_user_profile tool retrieves your personal Coda profile metadata. This includes details like your name and email, which is useful for generating operational reports.
Can I delete rows using delete_rows and what are the limitations? +
The delete_rows tool removes specified rows from a table. Be careful, as this action is irreversible and you must provide the exact row IDs you intend to delete.
How do I find my Coda API Token? +
Log in to Coda, navigate to Account Settings > API Settings, and generate a new token for your integration.
Where do I find my Doc ID? +
The Doc ID is the string of characters in your Coda document's URL after the '/d/'.
Can I filter rows using natural language? +
Yes! The list_rows tool supports a query parameter where the agent can apply filters like Status:"Done" to find specific data.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
PrecisionConvert Unit Engine
Universal unit conversion intelligence — transform physical values via AI.
BoardMix
Collaborative whiteboard and visual production platform — manage whiteboards, design nodes, and teams via AI.
Make.com Webhook Trigger
This MCP does exactly one thing: it sends JSON payloads to Make.com Webhooks. That's its only function. Incredible for connecting AI agents to thousands of visual automation workflows instantly.
You might also like
Klaviyo
Drive revenue with email and SMS marketing powered by customer data that personalizes every message to increase lifetime value.
Chuanglan 253 / 创蓝
Leading cloud communication and KYC platform in China — send ultra-high volume SMS and verify user identities via AI.
Bitso Exchange
Trade dynamically on Mexico's biggest Crypto Exchange. Access live balances, order books, and command trades programmatically.