How to Use the Coda MCP in Google ADK

Q: Can my Google ADK agent write data back to Coda?

Yes, the agent can write data. By exposing tools like insertrows and updaterow, the agent can modify tables in real time based on triggers from your Google Cloud infrastructure or BigQuery analysis.

Q: Can I limit the tools exposed to my enterprise Google ADK agent?

Yes, you can use the toolnames filter when setting up your McpToolset. If you want a read-only agent, simply restrict the toolset to listdocs and listrows, blocking access to destructive tools like deleterows.

Feed entire Coda documents into Gemini's million-token context window using the enterprise-ready Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Coda MCP to Google ADK

Create your Vinkius account to connect Coda to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Coda with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze whole Coda documents using Google ADK

Stop chunking your team's knowledge bases into tiny vector snippets. With this MCP Server, your Google ADK agent runs `list_rows` to pull entire tables and feeds the raw text directly into Gemini's massive context window. The agent processes thousands of rows at once, maintaining the complete context of your project history. By calling `get_doc_details`, the agent understands the structural relationship between different sections. It can cross-reference multiple documents retrieved via `list_docs` without losing track of the overarching project goals.

Sync Google Cloud and BigQuery data with Coda

Keep your team's tracking sheets updated with live data from your warehouse. Your Google ADK agent uses this MCP Server to query BigQuery, formats the dataset, and uses `insert_rows` to push the fresh metrics directly into your live documents. It eliminates the need for manual CSV exports or brittle third-party integration pipelines. When schemas change in your warehouse, the agent calls `list_tables` to identify which document needs updating. It then uses `update_row` to modify only the changed records, ensuring your internal project trackers match your production database.

Secure table audits using Google ADK

Run compliance checks on your internal databases using automated agents. The agent uses `list_columns` to audit your table structures, checking for sensitive fields or incorrect data types. It combines this with `get_table_details` to map out the exact schema of your operational documents. To ensure audit trails are accurate, the agent calls `get_user_profile` to verify the identity of the user running the process. This metadata can be logged directly to Google Cloud Logging, keeping your enterprise compliance team happy.

Setup guide

Set up Coda MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Coda tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Coda_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Coda tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Coda now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Coda MCP in Google ADK

You initialize the McpToolset in your Python script with the secure HTTP URL provided by Vinkius. Pass this toolset directly into your LlmAgent's tools list, allowing Gemini to call tools like `list_tables` or `get_doc_details` during execution.

Yes, the agent can write data. By exposing tools like `insert_rows` and `update_row`, the agent can modify tables in real time based on triggers from your Google Cloud infrastructure or BigQuery analysis.

Instead of searching for individual rows, the agent can call `list_rows` to retrieve a massive table and analyze the entire dataset in one pass. This utilizes Gemini's million-token limit to spot trends across your entire document that traditional search methods would miss.

Yes, you can use the tool_names filter when setting up your McpToolset. If you want a read-only agent, simply restrict the toolset to `list_docs` and `list_rows`, blocking access to destructive tools like `delete_rows`.

All requests to read your tables or rows run through an isolated, ephemeral runtime environment. No Coda document content, table schemas, or user profile metadata are stored on the Vinkius platform, maintaining strict enterprise data isolation.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript