How to Use the Convex MCP in Google ADK

Q: Can Gemini use Google ADK to write data to Convex?

Yes, the agent uses the runmutation tool to execute writes. Google ADK passes the model's generated parameters directly to your Convex backend, updating your state in real time.

Q: How do I limit which Convex tools are exposed to Google ADK?

You use the toolnames filter when initializing your McpToolset. This restricts Gemini to a specific list of queries or mutations, keeping your production database safe.

Q: Does this MCP Server support long-context operations with Gemini?

Yes, this MCP Server handles large payloads generated by runquery efficiently. Because Google ADK runs Gemini models with huge context windows, you can pipe massive Convex datasets directly into your agent's reasoning loop.

Q: How does the Convex MCP Server secure database queries in Google ADK?

All data from runquery and runmutation calls runs through isolated, ephemeral V8 runtimes on Vinkius. Your actual Convex database records and action payloads are never cached or logged, satisfying enterprise security requirements.

Build enterprise Gemini agents using Google ADK to run Convex mutations and query your live database.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Convex MCP to Google ADK

Create your Vinkius account to connect Convex 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 Convex with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Convex Inside Google ADK Workflows

The `run_query` tool pulls real-time database state from Convex directly into your Google ADK agent via this MCP tool. This enables Gemini to reason over live application data alongside enterprise datasets stored in BigQuery. Since Gemini supports massive context windows, your agent can process huge query payloads without hitting token limits. You get deep analysis of your backend state in a single step.

Modify Backend State with the Convex MCP Server

The `run_mutation` tool writes validated updates back to your Convex database directly from Google ADK. Your Gemini model decides on an action, and this tool executes the write immediately. You can restrict which mutations are exposed by using the tool names filter in your Python setup. This prevents enterprise agents from accidentally altering sensitive production records.

Trigger Actions and Custom Functions

The `run_action` tool runs complex side effects on Convex, like sending emails or calling external APIs. This lets your Google ADK agent offload heavy compute tasks to your serverless backend. For targeted endpoints, the `run_function` tool calls any Convex function using its exact URL identifier. Your agent gets precise access to specific backend logic without exposing the entire database schema.

Setup guide

Set up Convex 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 Convex 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="Convex_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Convex 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 Convex. 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 Convex 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 Convex MCP in Google ADK

You pass your Vinkius HTTP endpoint URL when initializing the `McpToolset` in Python. The underlying MCP Server handles the authentication handshake, allowing Gemini to query Convex securely.

Yes, the agent uses the `run_mutation` tool to execute writes. Google ADK passes the model's generated parameters directly to your Convex backend, updating your state in real time.

You use the `tool_names` filter when initializing your `McpToolset`. This restricts Gemini to a specific list of queries or mutations, keeping your production database safe.

Yes, this MCP Server handles large payloads generated by `run_query` efficiently. Because Google ADK runs Gemini models with huge context windows, you can pipe massive Convex datasets directly into your agent's reasoning loop.

All data from `run_query` and `run_mutation` calls runs through isolated, ephemeral V8 runtimes on Vinkius. Your actual Convex database records and action payloads are never cached or logged, satisfying enterprise security requirements.

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