How to Use the DeepSource MCP in CrewAI

Q: Can a CrewAI agent pause analysis runs in DeepSource?

Yes. Your agent can call deactivaterepository if a repository is archived or if you need to stop analysis runs to manage billing limits.

Q: How do CrewAI agents collaborate on DeepSource metrics?

One agent can call getrepositorymetrics to gather metrics like cyclomatic complexity, then write those findings to shared memory. Another agent reads those metrics to decide if a refactor is needed.

Deploy a team of CrewAI agents to monitor DeepSource code quality and auto-assign security vulnerabilities.

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 CrewAI

Create your Vinkius account to connect DeepSource to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run autonomous security audits with CrewAI

The `list_vulnerabilities` tool fetches all security risks from your repository dependencies. In a CrewAI setup, a Security Agent analyzes this list to prioritize critical CVSS scores and identify reachable packages. The Security Agent then hands the data to a Remediation Agent, which calls `get_vulnerability` to retrieve specific details on the vulnerable package. The team then drafts a pull request to update the dependency without human intervention.

Monitor codebase health with specialized agents

The `get_report_card` tool tracks the overall grade of your codebase. A Quality Monitor Agent runs this tool daily to watch for any grade drops on your default branch. If the grade drops, the Monitor Agent alerts an Analyst Agent, which calls `list_issues` to find new code smells or anti-patterns. The Analyst Agent groups these issues by file and assigns them to the responsible team members.

Automate repo maintenance using this MCP Server

The `get_repository` tool checks if your repository configurations match company standards. A Compliance Agent queries this tool to verify repository owners, VCS settings, and active branches. If a repository is unmonitored, the Compliance Agent runs `activate_repository` to enable analysis. If the default branch changes in your VCS, the agent calls `update_default_branch` to keep DeepSource aligned.

Setup guide

Set up DeepSource MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke DeepSource tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="DeepSource Analyst",
    goal="Access and analyze DeepSource data via MCP.",
    backstory="Expert analyst with direct DeepSource access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent DeepSource transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

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

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="DeepSource Analyst",
        goal="Access and analyze DeepSource data via MCP.",
        backstory="Expert analyst with direct DeepSource access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent DeepSource transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

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

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 CrewAI

Define your crew and pass the server tools to the agents that need them. For example, give `list_issues` to your Code Quality Agent and `list_vulnerabilities` to your Security Agent.

Yes. Your agent can call `deactivate_repository` if a repository is archived or if you need to stop analysis runs to manage billing limits.

One agent can call `get_repository_metrics` to gather metrics like cyclomatic complexity, then write those findings to shared memory. Another agent reads those metrics to decide if a refactor is needed.

Pass the MCP Server URL directly into your agent's mcps array. This gives your crew immediate access to tools like `get_test_coverage` and `list_analysis_runs`.

The integration only shares code quality metrics, dependency vulnerability details, and repository configuration metadata. Your source code files are never accessed or stored by the server.

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