How to Use the GitHub MCP in LangChain

Q: What happens to my raw repository code and issue data during execution?

Your source code retrieved via getfilecontent and issue text from listrepositoryissues are never stored. Vinkius runs the server in an ephemeral, zero-trust V8 isolate sandbox, meaning your raw files and ticket descriptions are processed in memory and instantly wiped after the tool execution finishes.

Run multi-step LangChain chains that inspect repositories, open issues, and manage pull requests directly within your agent pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GitHub MCP to LangChain

Create your Vinkius account to connect GitHub 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 GitHub with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain GitHub MCP Server tools into autonomous workflows

Your LangChain agent can now run sequential operations across your codebases using this MCP connection, starting with `list_my_repositories` to fetch your projects. The agent pulls a list of active repositories and immediately scans for open tickets. It feeds these issues directly into the next step of your chain to prioritize work. This setup lets you build self-correcting pipelines. When a test fails in your CI, the agent runs `get_file_content` to inspect the broken code, then uses `create_new_issue` to document the exact line that failed. You get a fully traced execution path in LangSmith showing every tool call.

Trace LangChain tool execution with pinpoint accuracy

LangChain pipelines thrive on observability, and this integration exposes every raw API payload when calling `list_pull_requests` to audit open code reviews. LangSmith tracks the exact latency and token cost of that specific call. You see exactly what repository data went in and what came out. If an agent gets stuck trying to locate a specific branch using `list_repo_branches`, you do not have to guess what went wrong. The trace logs show the exact parameters passed to the GitHub API. This visibility makes debugging complex multi-agent reasoning chains straightforward with this MCP integration.

Automate repository audits using composable chains

Combine different data sources into a single, logical flow by pulling organization data with `list_my_organizations` first. The agent can then search across projects with `search_repositories` and list active code snippets with `list_my_gists`. It connects these steps without manual glue code. You control the decision-making loop. The agent evaluates the output of `get_repository_details` to decide if a repo needs maintenance. If it does, the chain automatically triggers the next tool to flag the issue, keeping your codebases clean.

Setup guide

Set up GitHub 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 GitHub 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({
    "github-extended-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 GitHub 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 GitHub. 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 GitHub 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 GitHub MCP in LangChain

You pass your Vinkius token to the MultiServerMCPClient during setup. This single token handles the handshake, allowing your LangChain chains to safely call tools like `get_my_profile` and `list_my_repositories` without hardcoding raw developer credentials.

Yes, that is how the ReAct agent model works. The agent decides to call `list_pull_requests` first, reads the status, and then immediately decides to execute `create_new_issue` if a PR fails checks.

The server runs in a managed sandbox that handles connection pooling. If your LangChain agent makes rapid sequential calls to `search_repositories` or `get_file_content`, the infrastructure manages the request pacing to prevent your token from getting blocked.

You control access at the GitHub token level before connecting to Vinkius. If your token only has read access to public repos, the MCP Server will only return those public projects.

Your source code retrieved via `get_file_content` and issue text from `list_repository_issues` are never stored. Vinkius runs the server in an ephemeral, zero-trust V8 isolate sandbox, meaning your raw files and ticket descriptions are processed in memory and instantly wiped after the tool execution 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