Connect DeepSource to ChatGPT, Claude and Gemini

• 01 / 02How to audit vulnerabilities
• 02 / 02How to monitor code quality

Fastest day

847ms

Slowest day

1292ms

14-day trend

Stable0%

DeepSource Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_gRojrYBqBJYk2MB0kmqFd1Bq7M9JWeWmipQYTeBA/mcpCopy

Claude Desktop

Follow the steps below to connect in seconds.

1. 1In Claude Desktop, open Settings → Connectors.
2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3. 3Click Add and start a new chat — DeepSource capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "deepsource-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_gRojrYBqBJYk2MB0kmqFd1Bq7M9JWeWmipQYTeBA/mcp"
    }
  }
}

• Claude
• ChatGPT
• Cursor
• VS Code
• Windsurf
• Claude Code
• JetBrains
• Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up DeepSource in Claude and other AIs

See all the AI clients this connector works with ↑

• 01

  Engineering Managers

  They ask the agent for high-level health grades and issue counts across multiple repos.

• 02

  Security Teams

  They use the agent to monitor CVEs and prioritize fixes based on CVSS scores and reachability.

• 03

  Developers

  They check specific code issues and test coverage directly from their IDE.

• 04

  DevOps Leads

  They manage repository activation and DSN rotation through the agent.

• 01

  How do I connect DeepSource to my AI client?

  Subscribe to the MCP on Vinkius and enter your DeepSource Personal Access Token. Once connected, you can use it immediately in any compatible client like Claude or Cursor.

• 02

  Can I manage my repositories through the AI?

  Yes. You can use the MCP to activate or deactivate repositories, update default branches, and regenerate DSN tokens.

• 03

  What kind of security data can my agent access?

  Your agent can list dependency vulnerabilities, check CVE IDs, view CVSS scores, and determine if a vulnerability is reachable in your code.

• 04

  Does this work with GitHub and GitLab?

  Yes. The MCP works with repositories hosted on GitHub, GitLab, and Bitbucket.

• 05

  Can I check test coverage with this MCP?

  Yes. You can ask your agent to retrieve test coverage percentages and compare them against your configured thresholds.

• 06

  How do I get a DeepSource Personal Access Token and where do I find it?

  Log in to your DeepSource account, go to Account Settings → Personal Access Tokens, and click Create New Token. Give it a descriptive name (e.g., 'Vinkius MCP') and copy the token immediately. it won't be shown again. Paste this token into the API key field below. The token is used as a Bearer token in the Authorization header for all GraphQL requests to https://api.deepsource.com/graphql/.

• 07

  What types of code issues can DeepSource detect and how are they categorized?

  DeepSource detects various code quality issues including code smells, anti-patterns, performance issues, security vulnerabilities, and bugs. Issues are categorized by severity (CRITICAL, HIGH, MEDIUM, LOW) and by analyzer type (e.g., PYTHON for Python issues, JS-A1 for JavaScript anti-patterns, GO for Go issues). Each issue includes a shortcode, title, category, and file locations with line numbers. You can filter issues by analyzer short code when querying repositories.

• 08

  How does DeepSource detect dependency vulnerabilities and what information is provided?

  DeepSource uses Supply Chain Analysis (SCA) to scan dependency manifest files (package.json, requirements.txt, Gemfile, etc.) for known vulnerabilities. Each vulnerability includes: CVE ID, CVSS score (0-10), severity level, description, affected package name and version, ecosystem (npm, pip, etc.), reachability status (whether the vulnerable code is actually called), and fixability (whether a fix version is available). This helps prioritize which vulnerabilities to address first based on real risk rather than just theoretical severity.

• 09

  What is the API rate limit and how many requests can I make per hour?

  DeepSource enforces a rate limit of 5,000 requests per hour per user account. This limit covers both read (queries) and write (mutations) operations. If you exceed this limit, the API will return HTTP 429 (Too Many Requests). For most code review and monitoring workflows, this limit is more than sufficient. If you need higher limits for large-scale analysis, contact DeepSource support.

• 

  Katalon TestOps (AI Test Management) AI Connector

  Manage test orchestration via Katalon TestOps — rerun test runs, monitor execution results, and audit software

  View
• 

  Codacy AI Connector

  Manage code quality and automated reviews via Codacy — track grades, monitor issues, and audit repository anal

  View
• 

  Beagle Security AI Connector

  Automate security testing via Beagle Security — list projects, start tests, and retrieve results directly from

  View
• 

  Mabl (AI-Powered Test Automation) AI Connector

  Manage E2E testing via Mabl — trigger test plans, monitor execution results, and perform AI-driven failure ana

  View

Suggestions

• 

  Codecov AI Connector

  Manage test coverage and engineering metrics via Codecov — track coverage reports, monitor commit totals, and

  View
• 

  CodeRabbit AI Connector

  Manage AI-powered code reviews via CodeRabbit — list users, track PR review metrics, audit admin actions, and

  View
• 

  Testim AI Connector

  Trigger automated AI tests, inspect execution logs, and manage branches natively via your AI agent.

  View
• 

  Security Vulnerability Scanner AI Connector

  Scans code for security vulnerabilities like SQL injection and command injection using AST pattern matching.

  View