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/`.

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.

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 r

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.

DeepSource MCP Server for CrewAI 14 tools — connect in under 2 minutes

Name: DeepSource
Availability: InStock
Author: Vinkius

docs.crewai.com/mcp/overview

Built by Vinkius GDPR 14 Tools Framework

Connect your CrewAI agents to DeepSource through Vinkius, pass the Edge URL in the `mcps` parameter and every DeepSource tool is auto-discovered at runtime. No credentials to manage, no infrastructure to maintain.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from crewai import Agent, Task, Crew

agent = Agent(
    role="DeepSource Specialist",
    goal="Help users interact with DeepSource effectively",
    backstory=(
        "You are an expert at leveraging DeepSource tools "
        "for automation and data analysis."
    ),
    # Your Vinkius token. get it at cloud.vinkius.com
    mcps=["https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"],
)

task = Task(
    description=(
        "Explore all available tools in DeepSource "
        "and summarize their capabilities."
    ),
    agent=agent,
    expected_output=(
        "A detailed summary of 14 available tools "
        "and what they can do."
    ),
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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.

When paired with CrewAI, DeepSource becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call DeepSource tools autonomously, one agent queries data, another analyzes results, a third compiles reports, all orchestrated through Vinkius with zero configuration overhead.

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 CrewAI 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 CrewAI via MCP

Follow these steps to integrate the DeepSource MCP Server with CrewAI.

Install CrewAI

Run pip install crewai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Customize the agent

Adjust the role, goal, and backstory to fit your use case

Run the crew

Run python crew.py. CrewAI auto-discovers 14 tools from DeepSource

Why Use CrewAI with the DeepSource MCP Server

CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with DeepSource through the Model Context Protocol.

Multi-agent collaboration lets you decompose complex workflows into specialized roles, one agent researches, another analyzes, a third generates reports, each with access to MCP tools

CrewAI's native MCP integration requires zero adapter code: pass Vinkius Edge URL directly in the `mcps` parameter and agents auto-discover every available tool at runtime

Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls

Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports

DeepSource + CrewAI Use Cases

Practical scenarios where CrewAI combined with the DeepSource MCP Server delivers measurable value.

Automated multi-step research: a reconnaissance agent queries DeepSource for raw data, then a second analyst agent cross-references findings and flags anomalies. all without human handoff

Scheduled intelligence reports: set up a crew that periodically queries DeepSource, analyzes trends over time, and generates executive briefings in markdown or PDF format

Multi-source enrichment pipelines: chain DeepSource tools with other MCP servers in the same crew, letting agents correlate data across multiple providers in a single workflow

Compliance and audit automation: a compliance agent queries DeepSource against predefined policy rules, generates deviation reports, and routes findings to the appropriate team

DeepSource MCP Tools for CrewAI (14)

These 14 tools become available when you connect DeepSource to CrewAI 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 CrewAI

Ready-to-use prompts you can give your CrewAI 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 CrewAI

Common issues when connecting DeepSource to CrewAI through the Vinkius, and how to resolve them.

MCP tools not discovered

Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts. check console output.

Agent not using tools

Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".

Timeout errors

CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.

Rate limiting or 429 errors

Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.

DeepSource + CrewAI FAQ

Common questions about integrating DeepSource MCP Server with CrewAI.

How does CrewAI discover and connect to MCP tools?

CrewAI connects to MCP servers lazily. when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.

Can different agents in the same crew use different MCP servers?

Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.

What happens when an MCP tool call fails during a crew run?

CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.

Can CrewAI agents call multiple MCP tools in parallel?

CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.

Can I run CrewAI crews on a schedule (cron)?

Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.