How to Use the DeepSource MCP in Mastra AI

Q: How does Mastra AI handle failed DeepSource tool calls?

The workflow engine has built-in retry logic. If a call to getrepositorymetrics fails due to network issues, Mastra AI automatically retries the operation using exponential backoff.

Q: How do I set the default branch for analysis in Mastra AI?

Use updatedefaultbranch within a workflow step. The agent passes the repository ID and the target branch name to update your configuration automatically.

Build reliable self-healing workflows with Mastra AI and DeepSource to auto-remediate code quality issues.

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 Mastra AI

Create your Vinkius account to connect DeepSource to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate quality checks in Mastra AI workflows

The `list_analysis_runs` tool monitors the status of your recent code checks. If a run fails, the Mastra AI workflow engine catches the failure, triggers a retry with exponential backoff, and alerts the developer if the issue persists. When a run succeeds, the agent calls `get_report_card` to evaluate the overall quality grade. Based on the grade, the workflow can conditionally branch to either merge the pull request or flag it for manual review.

Build automated dependency triage pipelines

The `list_sca_targets` tool identifies every package manager manifest file in your repository. Mastra AI uses this tool to map out your software supply chain before running deeper security checks. Once targets are mapped, the agent invokes `list_vulnerabilities` to find high-severity risks. The workflow can automatically generate a Jira ticket or Slack alert containing the CVSS score and the fixable version.

Manage repositories with this MCP Server

The `get_repository` tool inspects your repository configuration to confirm the VCS provider and owner login are correct. Your Mastra AI agent uses this metadata to decide whether to activate analysis. If the repository is active, the agent runs `get_test_coverage` to check if coverage falls below your team's minimum threshold. If it does, the workflow flags the commit and prevents the deployment pipeline from moving forward.

Setup guide

Set up DeepSource MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All DeepSource tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "deepsource-mcp-client",
  servers: {
    "deepsource-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "DeepSource Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to DeepSource tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent DeepSource transactions"
);
console.log(result.text);

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 Mastra AI

The workflow engine has built-in retry logic. If a call to `get_repository_metrics` fails due to network issues, Mastra AI automatically retries the operation using exponential backoff.

Yes. You can configure requireToolApproval on critical tools like `deactivate_repository` or `regenerate_dsn`. This pauses the workflow until a team member approves the action.

Register the tools from this server in your Mastra agent definition. The agent can then call `list_analysis_runs` to inspect recent analyzer runs and make decisions based on the output.

Use `update_default_branch` within a workflow step. The agent passes the repository ID and the target branch name to update your configuration automatically.

Yes. Your DeepSource API token is stored as an environment variable and is only used to authenticate requests. This server only touches metadata, metrics, and vulnerability reports, keeping your credentials secure.

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