coda-mcp-server
Provides tools for managing Coda documents, pages, tables, rows, formulas, and user authentication, enabling AI-powered document automation and data manipulation through the Coda API.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@coda-mcp-server list my documents in Coda"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Coda MCP Server
A Model Context Protocol (MCP) server that provides seamless integration between Claude and Coda.io, enabling AI-powered document automation and data manipulation.
Note: This is an unofficial MCP server developed by TJC L.P. and is not affiliated with, endorsed by, or supported by Coda. For official Coda support and documentation, please visit coda.io.
Note: Version 1.1.0+ uses
snake_casefield names (e.g.,browser_linkinstead ofbrowserLink) for Python ecosystem compatibility. See CHANGELOG for migration details if upgrading from 1.0.x.
Features
Document Operations
List documents - Search and filter your Coda docs
Create documents - Generate new docs with optional templates
Read document info - Get metadata about any doc
Update documents - Modify doc properties like title and icon
Delete documents - Remove docs (use with caution!)
Page Management
List pages - Browse all pages in a doc
Create pages - Add new pages with rich content
Read pages - Get page details and content
Update pages - Modify page properties and content
Delete pages - Remove pages from docs
Export page content - Get full HTML/Markdown content with
begin_page_content_exportandget_page_content_export_status
Table & Data Operations
List tables - Find all tables and views in a doc
Get table details - Access table metadata and structure
List columns - Browse table columns with properties
Get column info - Access column formulas and formats
Row Operations
List rows - Query and filter table data
Get specific rows - Access individual row data
Insert/Update rows - Add or modify data with
upsert_rowsUpdate single row - Modify specific row data
Delete rows - Remove single or multiple rows
Push buttons - Trigger button columns in tables
Formula Operations
List formulas - Find all named formulas in a doc
Get formula details - Access formula expressions
Authentication
Who am I - Get current user information
Related MCP server: Grist MCP Server
Installation
Prerequisites
Coda API Key: Get your API token from Coda Account Settings
Python 3.11+ (including 3.14): Required for the MCP server
Option 1: Install from PyPI (Recommended)
The Coda MCP server is available on PyPI and can be installed directly using uvx (recommended) or pip:
# Using uvx (no installation needed, just run)
uvx coda-mcp-server
# Or install globally with pip
pip install coda-mcp-serverOption 2: Install from Source
Clone the repository
git clone https://github.com/TJC-LP/coda-mcp-server.git cd coda-mcp-serverInstall dependencies
uv syncSet your API key as an environment variable (see Configuration section below)
Configuration
Option 1: Claude Code (Recommended for Development)
For using with Claude Code during development:
Set your API key as a shell environment variable:
# Add to your shell profile (~/.zshrc, ~/.bashrc, etc.) export CODA_API_KEY="your-coda-api-key-here" # Or set it for the current session export CODA_API_KEY="your-coda-api-key-here"MCP configuration is already included!
The repository includes a
.mcp.jsonfile that automatically configures the Coda MCP server:{ "mcpServers": { "coda": { "command": "uv", "args": ["run", "coda-mcp-server"], "env": { "CODA_API_KEY": "${CODA_API_KEY}" } } } }The
${CODA_API_KEY}syntax reads the API key from your shell environment.Reload Claude Code - The MCP server will be automatically available
Security Note: API keys are read from your shell environment, not from files. This prevents accidental commits and arbitrary file loading.
Alternative: Using .env files with dotenv-cli
If you prefer file-based configuration, you can use dotenv-cli to inject environment variables:
# Create .env file from example (gitignored)
cp .env.example .env
# Edit .env and replace 'changeme' with your API key
# Run Claude Code with dotenv (no installation needed)
bunx dotenv-cli -- claude
# or
npx dotenv-cli -- claudeOption 2: Claude Desktop
To use the Coda MCP server with Claude Desktop, you need to add it to your Claude Desktop configuration file.
Configuration File Location:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
Add the Coda MCP Server:
Edit the configuration file and add the Coda server to the mcpServers section:
{
"mcpServers": {
"coda": {
"command": "uvx",
"args": ["coda-mcp-server"],
"env": {
"CODA_API_KEY": "your-coda-api-key-here"
}
}
}
}Important: Replace
your-coda-api-key-herewith your actual Coda API key from Coda Account Settings.
Alternative: Using Local Installation
If you installed from source, you can point to your local installation:
{
"mcpServers": {
"coda": {
"command": "uv",
"args": [
"run",
"--directory",
"/path/to/repo",
"coda-mcp-server"
],
"env": {
"CODA_API_KEY": "your-coda-api-key-here"
}
}
}
}Verify Installation
After adding the configuration:
Restart Claude Desktop
Look for the settings icon in the bottom of your conversation
Click it and verify that "coda" is listed as a connected server
You should see 26 available Coda tools when you click
codain the dropdown and can toggle the ones that you need specifically.
Usage in Claude
Once installed, you can use Coda operations directly in Claude by prefixing commands with coda:. Here are some examples:
Document Operations
# List all your docs
Use coda:list_docs with is_owner: true, is_published: false, query: ""
# Get info about a specific doc
Use coda:get_doc_info with doc_id: "your-doc-id"
# Create a new doc
Use coda:create_doc with title: "My New Doc"Working with Tables
# List tables in a doc
Use coda:list_tables with doc_id: "your-doc-id"
# Get all rows from a table with column names
Use coda:list_rows with doc_id: "your-doc-id", table_id_or_name: "Table Name", use_column_names: true
# Insert a new row
Use coda:upsert_rows with doc_id: "your-doc-id", table_id_or_name: "Table Name", rows_data: [{
cells: [
{column: "Name", value: "John Doe"},
{column: "Email", value: "john@example.com"}
]
}]Page Content Export
# Start page export
Use coda:begin_page_content_export with doc_id: "your-doc-id", page_id_or_name: "Page Name", output_format: "markdown"
# Check export status and get content
Use coda:get_page_content_export_status with doc_id: "your-doc-id", page_id_or_name: "Page Name", request_id: "request-id-from-previous-step"API Reference
Core Functions
Document Management
list_docs(is_owner, is_published, query, ...)- List available docsget_doc_info(doc_id)- Get document metadatacreate_doc(title, source_doc?, timezone?, ...)- Create new documentupdate_doc(doc_id, title?, icon_name?)- Update document propertiesdelete_doc(doc_id)- Delete a document
Page Operations
list_pages(doc_id, limit?, page_token?)- List pages in a docget_page(doc_id, page_id_or_name)- Get page detailscreate_page(doc_id, name, subtitle?, ...)- Create new pageupdate_page(doc_id, page_id_or_name, ...)- Update page propertiesdelete_page(doc_id, page_id_or_name)- Delete a pagebegin_page_content_export(doc_id, page_id_or_name, output_format?)- Start async page exportget_page_content_export_status(doc_id, page_id_or_name, request_id)- Poll export status and download content
Table Operations
list_tables(doc_id, limit?, sort_by?, ...)- List all tablesget_table(doc_id, table_id_or_name)- Get table detailslist_columns(doc_id, table_id_or_name, ...)- List table columnsget_column(doc_id, table_id_or_name, column_id_or_name)- Get column details
Row Operations
list_rows(doc_id, table_id_or_name, query?, ...)- List and filter rowsget_row(doc_id, table_id_or_name, row_id_or_name, ...)- Get specific rowupsert_rows(doc_id, table_id_or_name, rows_data, ...)- Insert or update rowsupdate_row(doc_id, table_id_or_name, row_id_or_name, row, ...)- Update single rowdelete_row(doc_id, table_id_or_name, row_id_or_name)- Delete single rowdelete_rows(doc_id, table_id_or_name, row_ids)- Delete multiple rowspush_button(doc_id, table_id_or_name, row_id_or_name, column_id_or_name)- Trigger button
Formula Operations
list_formulas(doc_id, limit?, sort_by?)- List named formulasget_formula(doc_id, formula_id_or_name)- Get formula details
Authentication
whoami()- Get current user information
Development
Project Structure
coda-mcp-server/
├── src/
│ ├── coda_mcp_server/
│ │ ├── server.py # MCP server orchestrator (700 lines)
│ │ ├── client.py # HTTP client with Pydantic serialization
│ │ ├── models/ # 83 Pydantic models (7 modules)
│ │ │ ├── __init__.py
│ │ │ ├── common.py # Shared types and base models
│ │ │ ├── docs.py # Document models
│ │ │ ├── pages.py # Page models
│ │ │ ├── tables.py # Table and column models
│ │ │ ├── rows.py # Row and cell models
│ │ │ ├── exports.py # Export workflow models
│ │ │ └── formulas.py # Formula models
│ │ └── tools/ # Pure functions (5 modules)
│ │ ├── __init__.py
│ │ ├── docs.py # Document operations
│ │ ├── pages.py # Page operations
│ │ ├── tables.py # Table operations
│ │ ├── rows.py # Row operations
│ │ └── formulas.py # Formula operations
│ └── resources/
│ └── coda-openapi.yml # Coda API specification
├── tests/ # 44 tests
│ ├── conftest.py
│ ├── test_models.py
│ └── test_client_requests.py
├── .env.example
├── .mcp.json # Claude Code integration
└── pyproject.tomlRunning Locally for Development
# Install dependencies
uv sync
# Set your API key (if not already in your shell profile)
export CODA_API_KEY="your-coda-api-key-here"
# Run the server directly
uv run python src/coda_mcp_server/server.pyTroubleshooting
Common Issues
"API Error 401: Unauthorized"
Check that your
CODA_API_KEYenvironment variable is set correctlyVerify with:
echo $CODA_API_KEYEnsure your API key has the necessary permissions
"Rate limit exceeded"
Coda API has rate limits; wait for the specified time before retrying
The server includes automatic rate limit detection
Boolean parameters not working
The server automatically converts boolean values to strings ("true"/"false")
This is handled internally, just use boolean values normally
Page export issues
Use the two-step export workflow:
begin_page_content_exportthenget_page_content_export_statusThe status check automatically downloads content when ready
License
This project is licensed under the MIT License - see the LICENSE file for details.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Support
For issues and feature requests, please use the GitHub Issues page.
Available Tools
26 toolsbegin_page_content_exportA
Start an async export of page content in HTML or markdown format - returns request ID to poll for completion with get_page_content_export_status
Inputs: doc_id (required), page_id_or_name (required), output_format. Returns: Response when beginning an export of page content. Contains the export request…
create_docB
Create a new Coda doc with optional configuration including title, timezone, folder placement, and initial page content
Inputs: title (required), source_doc, timezone, folder_id, +1 more. Returns: The result of a doc creation. Similar to Doc but includes a requestId for track…
create_pageB
Create a new page in a Coda doc with optional subtitle, icon, parent page, and initial HTML/markdown content
Inputs: doc_id (required), name (required), subtitle, icon_name, +3 more. Returns: The result of a page creation.
delete_docB
Permanently delete a Coda doc by ID - use with extreme caution as this cannot be undone
Inputs: doc_id (required). Returns: The result of a doc deletion. Returned when a doc is successfully deleted.
delete_pageB
Delete a page from a Coda doc by its ID or name
Inputs: doc_id (required), page_id_or_name (required). Returns: The result of a page deletion.
delete_rowB
Delete a specific row from a table by its ID or name
Inputs: doc_id (required), table_id_or_name (required), row_id_or_name (required). Returns: The result of a row deletion.
delete_rowsC
Delete multiple rows from a table at once using a list of row IDs
Inputs: doc_id (required), table_id_or_name (required), row_ids (required). Returns: The result of a rows delete operation.
get_columnB
Get detailed information about a specific column including its type, format, and formula
Inputs: doc_id (required), table_id_or_name (required), column_id_or_name (required). Returns: Info about a column.
get_doc_infoA
Get detailed metadata about a specific Coda doc by its ID
Inputs: doc_id (required). Returns: Metadata about a Coda doc. Contains comprehensive information about a doc inclu…
get_formulaB
Get details about a specific named formula including its computed value
Inputs: doc_id (required), formula_id_or_name (required). Returns: Details about a formula. Extends FormulaReference with the computed value of th…
get_pageB
Get detailed metadata about a specific page by its ID or name
Inputs: doc_id (required), page_id_or_name (required). Returns: Metadata about a page.
get_page_content_export_statusA
Check status of a page export and auto-download content when ready - poll this after starting export with begin_page_content_export
Inputs: doc_id (required), page_id_or_name (required), request_id (required). Returns: Response when requesting the status of a page content export. Poll this endpoin…
get_rowA
Get a specific row from a table by its ID or name with all cell values
Inputs: doc_id (required), table_id_or_name (required), row_id_or_name (required), use_column_names, +1 more. Returns: Info about a row.
get_tableB
Get detailed information about a specific table including its schema, columns, and metadata
Inputs: doc_id (required), table_id_or_name (required). Returns: Metadata about a table.
list_columnsC
List all columns in a table with their properties, formats, and formulas
Inputs: doc_id (required), table_id_or_name (required), limit, page_token, +1 more. Returns: List of columns.
list_docsB
List Coda docs accessible by the user (defaults to your own unpublished docs) - returns docs in reverse chronological order by most recent activity
Inputs: is_owner, is_published, query, source_doc, +6 more. Returns: List of Coda docs. Contains a paginated list of docs with optional pagination t…
list_formulasC
List all named formulas in a Coda doc with their names and IDs
Inputs: doc_id (required), limit, page_token, sort_by. Returns: List of formulas in a doc. Paginated response containing formula references.
list_pagesB
List all pages in a Coda doc with pagination support
Inputs: doc_id (required), limit, page_token. Returns: List of pages.
list_rowsC
List rows in a table with optional filtering, sorting, and pagination - returns row data with cell values
Inputs: doc_id (required), table_id_or_name (required), query, sort_by, +6 more. Returns: List of rows.
list_tablesC
List all tables and views in a Coda doc with optional filtering and sorting
Inputs: doc_id (required), limit, page_token, sort_by, +1 more. Returns: List of tables.
push_buttonA
Trigger a button column in a table row to execute its automation or action (buttons can run formulas, modify data, or trigger workflows)
Inputs: doc_id (required), table_id_or_name (required), row_id_or_name (required), column_id_or_name (required). Returns: The result of a push button.
update_docC
Update properties of a Coda doc including title and icon
Inputs: doc_id (required), title, icon_name. Returns: The result of a doc update. Returned when a doc is successfully updated.
update_pageB
Update properties and content of a page including name, subtitle, icon, visibility, and HTML/markdown content
Inputs: doc_id (required), page_id_or_name (required), name, subtitle, +4 more. Returns: The result of a page update.
update_rowC
Update cell values in a specific row by its ID or name
Inputs: doc_id (required), table_id_or_name (required), row_id_or_name (required), row (required), +1 more. Returns: The result of a row update.
upsert_rowsB
Insert new rows or update existing rows in a table based on key columns - ideal for bulk operations
Inputs: doc_id (required), table_id_or_name (required), rows_data (required), key_columns, +1 more. Returns: The result of a rows insert/upsert operation.
whoamiA
Get information about the current authenticated Coda user including name, email, and scoped token info
Inputs: no named parameters. Returns: Information about the current authenticated Coda user.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 26 tools
Every tool targets a distinct resource and operation (doc, page, table, row, column, formula, export, user). There is no ambiguity between tools; even related tools like delete_row and delete_rows are clearly differentiated by singular vs plural.
Most tools follow a consistent verb_noun pattern (e.g., create_doc, list_pages, get_row). Minor deviations include 'whoami' and 'push_button', but overall the naming is predictable and readable.
26 tools cover a broad domain (docs, pages, tables, rows, columns, formulas, exports, user). While slightly on the higher side, the count is justified by the complexity of Coda's API and does not feel excessive.
Significant gaps exist: there is no single create_row tool (only upsert_rows), columns are read-only (no create/update/delete column), and formulas have no mutation tools. The surface is incomplete for basic CRUD on rows and columns.
Maintenance
Related MCP Connectors
Convert, create and edit Word, PowerPoint, Excel and PDF documents from any AI agent.
Shared tables and Markdown docs for teams and AI-built apps, with scoped access and audited changes.
Create documents and reusable templates, request signatures, and track approvals — for AI agents.
AI access to Quadratic spreadsheets: open files, run Python/SQL, query connected databases.
Related MCP Servers
- AlicenseAqualityDmaintenanceA Model Context Protocol server that enables AI assistants to interact with Coda documents, allowing operations like listing, creating, reading, updating, and duplicating pages.19884 npm62MIT
- AlicenseAqualityBmaintenanceEnables interaction with Grist documents, workspaces, and records via the Model Context Protocol. It supports comprehensive operations including SQL querying, schema management, and record CRUD functionality.11462 npm4Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to interact directly with Google Sheets to create, read, and edit spreadsheets through the Model Context Protocol. It supports a wide range of actions including cell manipulation, row and column management, and sheet organization.MIT

Cyoda Calculation Node MCPofficial
AlicenseBqualityDmaintenanceEnables AI assistants to interact with Cyoda platform entities and workflows through the Model Context Protocol, supporting entity management, workflow execution, and data synchronization.131Apache 2.0