How to Use the DeepSource MCP in Google ADK

Q: How do I load DeepSource MCP tools into Google ADK?

Install google-adk and configure an McpToolset using StreamableHttpServerParameters. Pass this toolset into your LlmAgent initialization array. You can restrict the exposed tools using the toolnames filter.

Q: Can Google ADK track DeepSource analysis history?

Your agent calls listanalysisruns to get the status of recent pipeline executions. It filters by branch name to see if specific language analyzers passed or failed.

Q: How does Google ADK interact with DeepSource repository settings?

The agent uses updatedefaultbranch to change the primary tracking target. It also calls activaterepository or deactivaterepository to toggle active analysis on specific projects.

Give your Google ADK agents direct access to the DeepSource MCP Server for code quality metrics, vulnerability scans, and repository data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeepSource MCP to Google ADK

Create your Vinkius account to connect DeepSource 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 DeepSource with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query repository data with Google ADK

`get_repository` pulls the core configuration for any project tracked in DeepSource. Your Gemini-powered agent needs this baseline data before it can start querying specific metrics or issues. `get_viewer` validates the active API token and returns the authenticated user profile. Tracking historical performance requires pulling past execution data. `list_analysis_runs` returns the last 20 pipeline executions, showing which language analyzer ran and whether it succeeded. Your Google ADK agent can dump this history straight into BigQuery for long-term trend analysis.

Map dependency risks and security flaws

`list_sca_targets` identifies every manifest file and package manager active in your project. This tells your agent exactly where supply chain scans are happening. `list_vulnerabilities` then extracts the actual CVEs, severity levels, and fixability status for those dependencies. Deep dives into specific threats happen through `get_vulnerability`. The agent passes the occurrence ID to read the exact description and affected package versions. Gemini's massive context window can process hundreds of these vulnerability reports simultaneously to plan a massive dependency update.

Track code smells and test coverage

`list_issues` exposes up to 50 anti-patterns or bugs in a single call. The tool provides the exact file path and line number for up to three sample occurrences per issue. `get_test_coverage` reports the current coverage percentage against your configured thresholds. Overall project health is surfaced via `get_report_card`, which returns the top-level grade. `get_repository_metrics` lets the agent filter for specific data points like maintainability index. This MCP Server gives your agents the exact numbers they need to block bad deployments.

Setup guide

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

Install `google-adk` and configure an `McpToolset` using `StreamableHttpServerParameters`. Pass this toolset into your `LlmAgent` initialization array. You can restrict the exposed tools using the `tool_names` filter.

Your agent calls `list_analysis_runs` to get the status of recent pipeline executions. It filters by branch name to see if specific language analyzers passed or failed.

The agent uses `update_default_branch` to change the primary tracking target. It also calls `activate_repository` or `deactivate_repository` to toggle active analysis on specific projects.

It needs the repository name, login, VCS provider, and the occurrence ID. The agent gets that ID by first calling `list_vulnerabilities`.

The connection relies on a strict zero-trust sandbox. Your Google Cloud infrastructure only receives CVE IDs, package names, and CVSS scores, while the underlying execution environment destroys itself immediately after returning the payload.

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