How to Use the DeepSource MCP in Claude

Q: How do I configure DeepSource with Claude Desktop?

Open your claudedesktopconfig.json file and add the server configuration under the mcpServers key. Once you restart the desktop app, the hammer icon will display your new tools.

Q: How does this MCP Server handle secret rotation?

You can use regeneratedsn to instantly rotate your repository credentials from the chat interface. This invalidates the old DSN and returns a fresh one to secure your build pipelines.

Q: Can I pause analysis runs using Claude Desktop?

Yes, you can run deactivaterepository directly from the prompt. This halts all active analysis runs and prevents new analyses from triggering on push events.

Get instant code quality grades and dependency vulnerability checks right inside your Claude Desktop workspace using this MCP Server.

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 Claude Desktop

Create your Vinkius account to connect DeepSource to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit repository health directly in Claude Desktop

Stop switching tabs to check your static analysis status. When you ask Claude Desktop to inspect a repository, it'll call `get_repository` and `get_report_card` to pull your current quality grades. You see the exact state of your code directly in the chat window. If a repository is not currently monitored, you can run `activate_repository` to start tracking it. This allows your agent to configure code analysis on the fly without leaving your desktop client.

Track test coverage and metrics via MCP Server

The MCP Server lets Claude query `get_test_coverage` and `get_repository_metrics` to grab real-time coverage percentages. Your agent reads the exact lines of code missing test coverage. You can filter the data by specific metrics like cyclomatic complexity or maintainability index. This keeps your team updated on code quality trends before you push changes to production.

Investigate dependency risks and security flaws

Spotting open-source vulnerabilities early saves hours of clean-up later. Your agent runs `list_vulnerabilities` and `get_vulnerability` to pull detailed CVE data and severity scores directly into your local workspace. To inspect the files targeted for supply chain analysis, Claude uses `list_sca_targets`. You get a clear view of which package managers and lockfiles require immediate attention.

Setup guide

Set up DeepSource MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The DeepSource MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the DeepSource MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under deepsource-mcp.

json

{
  "mcpServers": {
    "deepsource-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Desktop

Open your claude_desktop_config.json file and add the server configuration under the mcpServers key. Once you restart the desktop app, the hammer icon will display your new tools.

Yes. The server uses your token to check private repositories via `get_repository`. Ensure your DeepSource token has the correct permissions for your VCS provider.

You can use `regenerate_dsn` to instantly rotate your repository credentials from the chat interface. This invalidates the old DSN and returns a fresh one to secure your build pipelines.

Yes, you can run `deactivate_repository` directly from the prompt. This halts all active analysis runs and prevents new analyses from triggering on push events.

No source code is stored or processed. The server only pulls metadata, vulnerability reports, and quality metrics via secure HTTPS endpoints. Your actual code files remain in your local workspace or VCS provider.

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