How to Use the DeepSource MCP in OpenAI Agents SDK

Q: How do I configure DeepSource with the OpenAI Agents SDK?

Install openai-agents via pip. Create an MCPServerStreamableHttp instance pointing to your DeepSource endpoint and pass it to the Agent constructor in the mcpservers array. Set cacheToolsList=True to speed up tool discovery.

Q: Can my OpenAI agent pause DeepSource billing for inactive repositories?

Yes. The agent calls deactivaterepository with the target ID. This stops all new analyses and halts billing for that specific project.

Q: How does the agent handle vulnerability triage?

It starts with listvulnerabilities to map out CVEs and CVSS scores. Then it calls getvulnerability to read the exact remediation steps for a specific dependency flaw.

Connect the DeepSource MCP Server to your OpenAI Agents SDK production system to automate code quality checks and track test coverage.

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 OpenAI Agents SDK

Create your Vinkius account to connect DeepSource to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate code analysis with the DeepSource MCP Server

`activate_repository` turns on code quality monitoring for a specific project. You pass the repository ID, and the DeepSource MCP Server starts tracking every push and pull request instantly. `deactivate_repository` pauses the billing and analysis for archived projects. Your agent can also adjust configuration on the fly. `update_default_branch` shifts the primary branch target when your team moves from master to main. `regenerate_dsn` rotates the authentication keys if you suspect a leak, ensuring your analysis pipeline remains secure.

Inspect vulnerabilities and supply chain targets

`list_vulnerabilities` pulls a direct list of security risks in your dependencies. The tool returns CVSS scores, CVE IDs, and reachability status so your OpenAI agent can prioritize fixes based on actual threat levels. `get_vulnerability` lets the agent grab exact details for a specific dependency flaw. Tracking down where these flaws live requires knowing your manifests. `list_sca_targets` exposes the exact package managers and manifest file paths being scanned. Your production agent can cross-reference this data to generate targeted pull requests across your ecosystem.

Grade repository health and code metrics

`get_report_card` gives your agent an instant grade on code quality. You feed it the repository name and VCS provider, and it returns the overall status. `get_repository_metrics` digs deeper by extracting specific shortcodes like line coverage or cyclomatic complexity. Test coverage drops are a common failure point in CI/CD. `get_test_coverage` pulls the exact percentage and configured thresholds for any tracked codebase. `list_issues` surfaces up to 50 code smells or anti-patterns, complete with file paths and line numbers so your agent can flag them in code review.

Setup guide

Set up DeepSource MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all DeepSource tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives DeepSource tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate DeepSource tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="DeepSource Agent",
            instructions="You have access to DeepSource tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` via pip. Create an `MCPServerStreamableHttp` instance pointing to your DeepSource endpoint and pass it to the Agent constructor in the `mcp_servers` array. Set `cacheToolsList=True` to speed up tool discovery.

Yes. The agent calls `deactivate_repository` with the target ID. This stops all new analyses and halts billing for that specific project.

The agent accesses maintainability indexes, cyclomatic complexity, and line coverage via `get_repository_metrics`. It can also grab the high-level grade using `get_report_card`.

It starts with `list_vulnerabilities` to map out CVEs and CVSS scores. Then it calls `get_vulnerability` to read the exact remediation steps for a specific dependency flaw.

No. This integration only handles metadata like file paths, line numbers, CVSS scores, and coverage percentages. Your OpenAI Agents SDK setup communicates through an ephemeral V8 isolate that drops all state after the request finishes.

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