How to Use the Linear MCP in Google ADK

Q: How do I register the Linear MCP toolset inside Google ADK?

Import McpToolset and pass the HTTP transport parameters pointing to your Vinkius MCP server. Add this toolset to your LlmAgent configuration. Gemini models will immediately see tools like searchissues and getissue in their function-calling interface.

Q: Can I limit which Linear MCP tools are exposed to my Google ADK agent?

Yes, you can pass a toolnames list to the McpToolset constructor. This lets you restrict your Google ADK agent to read-only actions like listissues and getproject while hiding write operations.

Q: How do I verify the authenticated account with this setup?

Have your agent call getviewer at the start of a session. This tool returns the authenticated user's name and email, ensuring your agent is operating under the correct credentials before altering any team boards.

Connect your Google ADK agents to Linear to track sprints, update tickets, and sync engineering progress with BigQuery data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Linear MCP to Google ADK

Create your Vinkius account to connect Linear 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 Linear with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise sprint tracking for Google ADK

This Linear MCP Server gives your Gemini models direct access to active development pipelines. By invoking `list_cycles`, your agent pulls down sprint timelines and completion percentages, matching them against enterprise metrics stored in BigQuery. This setup allows your Google ADK agent to perform long-context reasoning over years of ticket history. It queries issues with `list_issues`, analyzes cycle trends, and writes back status summaries without hitting context limits.

Automated ticket management via Gemini MCP Server

The server provides standard tools for managing ticket lifecycles directly from Google Cloud. Your agent uses `create_issue` to open tickets when system logs indicate a failure, and uses `list_labels` to apply the correct priority tags instantly. When developers resolve issues, the agent triggers `update_issue` to change the state. You can restrict the toolset so the agent only accesses specific teams, preventing accidental modifications across other projects.

Cross-team visibility and reporting

The server exposes `list_projects` and `list_teams` to help your agent map out your entire organization. Your agent runs these tools to find which team owns a specific feature before assigning a bug report. Once the owner is found, the agent uses `create_comment` to link the new issue to existing project epics. This keeps cross-functional teams aligned without manual copy-pasting between systems.

Setup guide

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

Import `McpToolset` and pass the HTTP transport parameters pointing to your Vinkius MCP server. Add this toolset to your `LlmAgent` configuration. Gemini models will immediately see tools like `search_issues` and `get_issue` in their function-calling interface.

Yes, you can pass a `tool_names` list to the `McpToolset` constructor. This lets you restrict your Google ADK agent to read-only actions like `list_issues` and `get_project` while hiding write operations.

Gemini models use the ADK to execute multi-step tasks. For example, the model can search for duplicate bugs with `search_issues`, retrieve the details of the original with `get_issue`, and close the duplicate using `update_issue` in a single execution turn.

Have your agent call `get_viewer` at the start of a session. This tool returns the authenticated user's name and email, ensuring your agent is operating under the correct credentials before altering any team boards.

Yes, your team configurations, project specs, and issue titles are processed through ephemeral execution environments. Vinkius secures the token handshake, meaning Google ADK only receives the specific JSON outputs from tools like `list_teams` without exposing raw database credentials.

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