How to Use the Nylas MCP in Google ADK

Q: How do I register the Nylas MCP Server within my Google ADK agent?

Run pip install google-adk and define your toolset using McpToolset with StreamableHttpServerParameters pointing to Vinkius. Pass that toolset to your LlmAgent instance, and the Gemini model will automatically detect the communication tools.

Q: Can I limit which Nylas tools my Google ADK agent can access?

Yes, you can pass an optional toolnames filter array during your McpToolset initialization. This lets you expose read-only tools like listmessages while blocking destructive actions like deleteevent or sendmessage.

Feed Gmail and Outlook data into Google ADK to run deep, long-context reasoning over your communication history.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nylas MCP to Google ADK

Create your Vinkius account to connect Nylas 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 Nylas with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise communication reasoning with Google ADK

`list_messages` pulls massive email threads from Nylas directly into the Gemini model's 1M+ token context window. This massive context allows your Google ADK agent to analyze months of correspondence, extract action items, and cross-reference them with tables in BigQuery. Once the analysis completes, the agent can use `send_message` to dispatch status reports to stakeholders. Because the framework runs natively on Google Cloud, you can trigger these email updates directly from your Vertex AI pipelines.

Cloud-native calendar sync via Nylas MCP Server

This MCP Server gives your Gemini-powered agents direct access to scheduling tools like `list_calendars` and `list_events`. Your enterprise agent can pull external schedules, compare them against corporate resource databases, and execute `create_event` in one continuous run. If a meeting gets canceled on the cloud side, the agent cleans up the schedule using `delete_event`. You can restrict tool access by passing a specific list of allowed tool names to your toolset initialization.

Automated contact enrichment

`list_contacts` lets your agent query address book entries to feed customer data into your enterprise analytics pipelines. The agent reads the synced contacts, matches them against Vertex AI embeddings, and determines which profiles require updates. When a contact's details change, the agent invokes `create_contact` to push those updates back to the source provider. The tool integrates natively with Google ADK's infrastructure, allowing you to manage directories without writing custom API connectors.

Setup guide

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

Run `pip install google-adk` and define your toolset using `McpToolset` with `StreamableHttpServerParameters` pointing to Vinkius. Pass that toolset to your `LlmAgent` instance, and the Gemini model will automatically detect the communication tools.

Yes, you can pass an optional `tool_names` filter array during your `McpToolset` initialization. This lets you expose read-only tools like `list_messages` while blocking destructive actions like `delete_event` or `send_message`.

The framework leverages Gemini's million-token context window to ingest entire folders retrieved by `list_folders` and `list_messages`. This allows the agent to perform deep, long-context reasoning over years of communications without running out of memory.

Yes, the integration supports both connection styles depending on your deployment architecture. For cloud-hosted enterprise agents, the HTTP transport connected to Vinkius is the recommended path for production stability. This keeps your MCP workflow online.

Your contacts and calendar details are processed inside Vinkius's ephemeral V8 Isolate sandboxes and never written to disk. The server acts as a zero-trust pass-through, ensuring your corporate communication data remains strictly isolated.

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