How to Use the GitHub MCP in LangChain

Q: Can my LangChain agent write code using this GitHub MCP Server?

Yes, your agent can write and track work. It uses createnewissue to log bugs or document required code changes based on what it finds during repository analysis.

Q: How does the agent know which repository to search?

Your agent runs searchgithubrepositories to find the target repository name based on your prompt. Once it locates the correct repository, it passes that exact name to subsequent tools in the chain.

Run multi-step repository analysis pipelines directly in LangChain using this GitHub MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect GitHub MCP to LangChain

Create your Vinkius account to connect GitHub to LangChain — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup GitHub with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chain repository checks with LangChain

`list_repo_issues` pulls the active backlog directly into your LangChain run context. Your agent uses this raw data to decide which issues need immediate attention without you writing manual fetching scripts. You feed this issue list straight into `get_file_contents` in the next step of your chain. LangSmith tracks every transition, showing you the exact file contents passed between tools in real time.

Trace code search runs in LangSmith

`search_github_code` executes inside your ReAct agent loop to find specific patterns across your repositories. The agent inspects the code snippets and automatically decides whether to open a pull request or modify an existing issue. Every single code query and matching result is logged as a distinct step in your LangChain trace. You see the latency of the search and the exact token usage of the payload before the next agent step triggers.

Run multi-server GitHub MCP Server chains

`verify_api_connection` confirms your credentials are valid before your LangChain agent starts executing complex write operations. If the connection check passes, the agent aggregates this server with others in a single client session. Your agent then runs `list_pull_requests` to fetch open reviews and matches them against external database schemas. This setup lets you build complex pipelines that bridge repository state with your internal systems.

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-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

Look, monitor your LangSmith traces to see exactly when rate limits hit. The MCP Server forwards raw API headers, letting your LangChain agent pause or back off when limits approach.

Yes, your agent can write and track work. It uses `create_new_issue` to log bugs or document required code changes based on what it finds during repository analysis.

Use the MultiServerMCPClient in your Python code to merge this server with others. This allows your LangChain agent to call `get_repository_details` and then pass that metadata directly to a database tool in the same chain.

Your agent runs `search_github_repositories` to find the target repository name based on your prompt. Once it locates the correct repository, it passes that exact name to subsequent tools in the chain.

Your code files, issues, and pull request data remain inside your local runtime. The MCP Server acts as a local proxy, passing data directly to your LangChain agent without storing copies on external servers.

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