DeepSource MCP Server for Claude Code 14 tools — connect in under 2 minutes
Claude Code is Anthropic's agentic CLI for terminal-first development. Add DeepSource as an MCP server in one command and Claude Code will discover every tool at runtime. ideal for automation pipelines, CI/CD integration, and headless workflows via Vinkius.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
Vinkius Desktop App
The modern way to manage MCP Servers — no config files, no terminal commands. Install DeepSource and 2,500+ MCP Servers from a single visual interface.
# Your Vinkius token. get it at cloud.vinkius.com
claude mcp add deepsource --transport http "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About DeepSource MCP Server
Connect your DeepSource account to any AI agent and take full control of code quality analysis, vulnerability detection, and metrics monitoring through natural conversation.
Claude Code registers DeepSource as an MCP server in a single terminal command. Once connected, Claude Code discovers all 14 tools at runtime and can call them headlessly. ideal for CI/CD pipelines, cron jobs, and automated workflows where DeepSource data drives decisions without human intervention.
What you can do
- Code Issues — List and inspect code quality issues (code smells, anti-patterns, bugs) across repositories with severity and file locations
- Analysis History — View recent analysis runs with status, branch, and analyzer information (Python, JavaScript, Go, etc.)
- Security Vulnerabilities — Identify dependency vulnerabilities (SCA) with CVE IDs, CVSS scores, reachability, and fixability status
- Code Metrics — Query maintainability index, cyclomatic complexity, lines of code, and test coverage percentages
- Report Cards — Get overall repository health grades (A-F) with score breakdowns and trend analysis
- SCA Targets — List all dependency manifest files being scanned for supply chain security
- Repository Management — Activate/deactivate repos, update default branches, and regenerate DSN tokens
The DeepSource MCP Server exposes 14 tools through the Vinkius. Connect it to Claude Code in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect DeepSource to Claude Code via MCP
Follow these steps to integrate the DeepSource MCP Server with Claude Code.
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
Add the MCP Server
Run the command above in your terminal
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
Start using DeepSource
Ask Claude: "Using DeepSource, show me...". 14 tools are ready
Why Use Claude Code with the DeepSource MCP Server
Claude Code provides unique advantages when paired with DeepSource through the Model Context Protocol.
Single-command setup: `claude mcp add` registers the server instantly. no config files to edit or applications to restart
Terminal-native workflow means MCP tools integrate seamlessly into shell scripts, CI/CD pipelines, and automated DevOps tasks
Claude Code runs headlessly, enabling unattended batch processing using DeepSource tools in cron jobs or deployment scripts
Built by the same team that created the MCP protocol, ensuring first-class compatibility and the fastest adoption of new protocol features
DeepSource + Claude Code Use Cases
Practical scenarios where Claude Code combined with the DeepSource MCP Server delivers measurable value.
CI/CD integration: embed DeepSource tool calls in your deployment pipeline to validate configurations or fetch secrets before shipping
Headless batch processing: schedule Claude Code to query DeepSource nightly and generate reports without human intervention
Shell scripting: pipe DeepSource outputs into other CLI tools for data transformation, filtering, and aggregation
Infrastructure monitoring: run Claude Code in a cron job to query DeepSource status endpoints and alert on anomalies
DeepSource MCP Tools for Claude Code (14)
These 14 tools become available when you connect DeepSource to Claude Code via MCP:
activate_repository
Once activated, DeepSource will start analyzing the code on each push/PR. You must provide the repository ID (obtained from get_repository). Use this to enable code quality monitoring for a repository that was previously inactive. Activate a repository for code analysis in DeepSource
deactivate_repository
No new analyses will run until the repository is reactivated. You must provide the repository ID (obtained from get_repository). Use this to pause analysis for archived repositories or when you want to stop billing for a specific repository. Deactivate a repository to stop code analysis in DeepSource
get_report_card
This provides a quick health check of the repository's overall code quality status. You must provide the repository name, login, and VCS provider. Use this to get a high-level view of code quality trends and identify areas needing improvement. Get the overall report card (grade) for a repository
get_repository
You must provide the repository name, login (user or org name), and VCS provider (e.g., GITHUB, GITLAB, BITBUCKET). Use this to inspect repository configuration before querying issues, analyses, or metrics. Get details of a specific repository in DeepSource
get_repository_metrics
You must provide the repository name, login, and VCS provider. Optionally filter by specific metric shortcodes (e.g., "LCV" for line coverage, "MI" for maintainability index, "CC" for cyclomatic complexity). If no shortcodes specified, returns all available metrics with their values and thresholds. Get code quality metrics for a repository
get_test_coverage
Shows the coverage percentage value and any configured thresholds. You must provide the repository name, login, and VCS provider. Use this to monitor code quality and ensure adequate test coverage across your codebase. Get test coverage metrics for a repository
get_viewer
Use this to verify your API token is working and to get your user details from DeepSource. Get the authenticated user profile from DeepSource
get_vulnerability
You must provide the repository name, login, VCS provider, and the vulnerability occurrence ID (obtained from list_vulnerabilities). Use this to deep-dive into a specific vulnerability before deciding on remediation steps. Get details of a specific dependency vulnerability by its ID
list_analysis_runs
You must provide the repository name, login, and VCS provider. Optionally filter by branch name and limit the number of results (default: 20). Each run shows which analyzer was used (e.g., PYTHON, JAVASCRIPT, GO) and whether the analysis succeeded or failed. List recent code analysis runs for a repository
list_issues
You must provide the repository name, login, and VCS provider. Optionally filter by analyzer short code (e.g., "PYTHON", "JS-A1") and limit results (default: 50). Each issue includes up to 3 sample occurrences with file path and line number. Use this to identify code smells, anti-patterns, and potential bugs across your codebase. List code quality issues in a repository
list_sca_targets
Each target includes ecosystem (e.g., npm, pip, gem), package manager, manifest file path, and activation status. You must provide the repository name, login, and VCS provider. Use this to understand which dependency files are being scanned for vulnerabilities. List all SCA (Supply Chain Analysis) targets in a repository
list_vulnerabilities
Each vulnerability includes severity, CVE ID, CVSS score, description, affected package name and version, reachability status, and fixability. You must provide the repository name, login, and VCS provider. Optionally limit the number of results (default: 20). Use this to identify security risks in your dependencies and prioritize remediation. List dependency vulnerabilities in a repository (SCA)
regenerate_dsn
The DSN is used to authenticate DeepSource analysis runs. You must provide the repository ID (obtained from get_repository). This action invalidates the old DSN and returns the new one. Use this if you suspect the DSN has been compromised or needs rotation. Regenerate the DSN (Data Source Name) for a repository
update_default_branch
This affects which branch is analyzed by default. You must provide the repository ID (from get_repository) and the new branch name (e.g., "main", "develop", "master"). Use this when your team changes the default branch name (e.g., migrating from "master" to "main"). Update the default branch for a repository in DeepSource
Example Prompts for DeepSource in Claude Code
Ready-to-use prompts you can give your Claude Code agent to start working with DeepSource immediately.
"Show me the overall code quality report card and current issues for the 'api-service' repository in the 'acme-corp' GitHub organization."
"Check for any critical or high severity dependency vulnerabilities in the 'web-frontend' repo and tell me which packages are affected."
"What's the test coverage for our 'backend-api' repository and show me the most recent analysis runs?"
Troubleshooting DeepSource MCP Server with Claude Code
Common issues when connecting DeepSource to Claude Code through the Vinkius, and how to resolve them.
Command not found: claude
npm install -g @anthropic-ai/claude-codeConnection timeout
DeepSource + Claude Code FAQ
Common questions about integrating DeepSource MCP Server with Claude Code.
How do I add an MCP server to Claude Code?
claude mcp add --transport http "" in your terminal. Claude Code registers the server and discovers all tools immediately.Can Claude Code run MCP tools in headless mode?
How do I list all connected MCP servers?
claude mcp in your terminal to see all registered servers and their status, or type /mcp inside an active Claude Code session.Connect DeepSource with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect DeepSource to Claude Code
Get your token, paste the configuration, and start using 14 tools in under 2 minutes. No API key management needed.