How to Use the DeepSource MCP in LangChain

Q: Can a LangChain chain automatically pause DeepSource monitoring?

Yes, your chain can execute the deactivaterepository tool based on external triggers like an archived GitHub project. The agent passes the repository ID to stop further analysis runs and pause billing.

Q: How does LangChain trace DeepSource MCP Server tool calls?

LangSmith logs every execution of tools like gettestcoverage as a distinct run in your trace history. You see the exact input arguments, execution latency, and the returned coverage percentage directly in your debugging console.

Q: What happens if my LangChain agent needs to change the target branch?

The agent invokes updatedefaultbranch with the new target branch name. This updates the configuration so that subsequent runs of listanalysisruns pull data from your new main development branch.

Link code quality metrics and security alerts directly to your LangChain reasoning loops to catch bugs before they hit production.

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 LangChain

Create your Vinkius account to connect DeepSource to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build LangChain chains that audit repo health

The `get_report_card` tool pulls the overall grade of your codebase directly into your LangChain decision chains. Your agent checks this grade first, then branches based on whether the codebase meets your team's quality standards. If the grade drops, the chain triggers `get_repository_metrics` to grab specific numbers like line coverage or cyclomatic complexity. This lets you build automated blockers that stop deployment pipelines when code quality slips below your defined thresholds.

Track down vulnerabilities in LangChain pipelines

The `list_vulnerabilities` tool retrieves active dependency risks directly within your LangChain agentic workflow using this MCP Server. When a high-severity CVE pops up, your agent automatically passes that data to the next link in the chain. From there, the agent uses `get_vulnerability` to inspect the exact package version and reachability details. LangSmith traces every step of this analysis, giving you a clear audit trail of how your agent evaluated the security risk.

Run automated branch checks via this MCP Server

The `list_analysis_runs` tool exposes the status of recent code evaluations to your LangChain runtime. Your agent reads these runs to confirm whether the latest analyzer execution succeeded or failed on a specific branch. If a run fails, the agent calls `list_issues` to extract the exact file paths and line numbers of the offending code. This turns static telemetry into active debugging loops where your agent writes the fix and verifies it against the same analyzer.

Setup guide

Set up DeepSource MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes DeepSource tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "deepsource-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent DeepSource transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You load the tools into your agent using the LangChain MCP adapter. Once connected, your agent calls `list_issues` to fetch code smells and automatically feeds those file paths into its next reasoning step.

Yes, your chain can execute the `deactivate_repository` tool based on external triggers like an archived GitHub project. The agent passes the repository ID to stop further analysis runs and pause billing.

LangSmith logs every execution of tools like `get_test_coverage` as a distinct run in your trace history. You see the exact input arguments, execution latency, and the returned coverage percentage directly in your debugging console.

The agent invokes `update_default_branch` with the new target branch name. This updates the configuration so that subsequent runs of `list_analysis_runs` pull data from your new main development branch.

This MCP Server runs in a zero-trust sandbox where your repository metrics and analysis grades never persist. Your API token is transmitted securely via the Vinkius gateway, meaning your LangChain orchestration layer never exposes credentials to external logs.

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