Get started free
All integrations

DeepSource integration

DeepSource GraphQL API for static code analysis and automated code review. Detect bugs, security vulnerabilities, anti-patterns, and code quality issues across 20+ programming languages. Integrates with CI/CD pipelines, provides actionable recommendations, and supports autofix for common issues. Features include code health tracking, issue management, dependency vulnerability scanning, compliance reporting, and team collaboration.

17 toolsTokenAPI docs

Common DeepSource use cases

  • dashboard building
  • CI/CD integration
  • policy update
  • PR monitoring
  • issue reporting
  • branch migration
  • pausing analysis
  • analysis tracking
  • security auditing
  • security rotation

What you can do with DeepSource

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Repository, 6 operations

  • POSTactivate_repository

    Activates a repository for DeepSource code analysis.

  • POSTdeactivate_repository

    Deactivates a repository, stopping DeepSource code analysis.

  • POSTget_repository

    Retrieves detailed repository information including enabled analyzers, activation status, and configuration.

  • POSTlist_repositories

    Lists repositories connected to DeepSource with their analysis status and configuration.

  • POSTregenerate_repository_dsn

    Regenerates the DSN (project key) for a repository, invalidating the old one.

  • POSTupdate_default_branch

    Updates the default branch for a repository used as the analysis baseline.

Analysis run, 2 operations

  • POSTget_analysis_run

    Retrieves analysis run results including new issues introduced, issues resolved, report card grades, and metrics changes.

  • POSTlist_analysis_runs

    Lists analysis run history for a repository with status, issue counts, and timestamps for each run.

Pull request, 2 operations

  • POSTget_pull_request

    Retrieves pull request analysis results including issues raised, resolved, and vulnerability data.

  • POSTlist_pull_requests

    Lists pull requests with their analysis summaries, states, and issue counts.

Team suppression, 2 operations

  • POSTsuppress_issue_for_team

    Suppresses an issue at the team level across all repositories.

  • POSTunsuppress_issue_for_team

    Removes a team-level issue suppression, re-enabling analysis for that issue across all repositories.

Ignore rule, 1 operation

  • POSTget_ignore_rules

    Lists ignore rules configured for a repository with issue shortcode and file path filters.

Issue, 1 operation

  • POSTlist_issues

    Lists code issues detected in a repository with category, severity, and autofix availability.

Metric, 1 operation

  • POSTget_code_health_metrics

    Retrieves code health metrics showing coverage, duplication, and quality metrics with thresholds for a repository.

Report, 1 operation

  • POSTget_report

    Retrieves compliance and quality reports including OWASP Top 10, SANS Top 25, issue distribution, and code coverage.

Vulnerability, 1 operation

  • POSTlist_vulnerabilities

    Lists dependency vulnerability occurrences in a repository with severity, CVSS scores, and fix availability.

Use DeepSource from Claude Code, Cursor or Codex

Connect DeepSource in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its DeepSource operations become tools the client can call, next to every other integration you connected.

Claude Code
claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"
Codex (~/.codex/config.toml)
[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"
Cursor, Claude Desktop and other JSON configs
{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect DeepSource

  1. Create your workspace

    Sign up free. Nothing to install.

  2. Connect DeepSource once

    Add your DeepSource connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.

  3. Describe the job in chat

    The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

DeepSource integration FAQ

What can you do with the DeepSource integration?
LiveContext exposes 17 operations on DeepSource, covering repository, analysis run, pull request and team suppression. Common uses include dashboard building, CI/CD integration and policy update.

Popular integrations

Browse the whole catalog