How to Use the GitHub MCP in LlamaIndex

Q: How do I index my GitHub issues into LlamaIndex?

You use the McpToolSpec to load tools like listrepositoryissues into your LlamaIndex agent. This MCP adapter retrieves the raw issue payloads and passes them to your vector indexer as structured documents.

Q: How is my private code protected when indexed by the server?

Your proprietary code retrieved via getfilecontent and code snippets from listmygists are processed strictly within isolated memory. Vinkius uses a zero-trust architecture that never logs the payloads of your files or code snippets, ensuring your intellectual property remains private.

Index your GitHub repositories, pull requests, and issues directly into LlamaIndex vector stores for semantic search.

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 LlamaIndex

Create your Vinkius account to connect GitHub to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query GitHub repositories using LlamaIndex RAG pipelines

Turn your active codebases into a searchable knowledge base by fetching file structures with `get_repository_details` to feed your document indexes. By connecting this MCP Server to your LlamaIndex pipeline, your agent can answer complex questions about your architecture. The tool output is treated as live data documents. When the agent calls `get_file_content`, LlamaIndex parses the code, splits it into nodes, and indexes it. This lets you run semantic queries over your actual source code instead of relying on outdated documentation.

Ground agent responses in live GitHub issue data

Stop letting your LLM hallucinate about project status by running `list_repository_issues` to fetch real-time state. Your agent can run these queries alongside `list_pull_requests` using our MCP tools to fetch real-time state, then index these records on the fly. You can combine historical documentation with live ticket updates. The agent queries your vector store for context, pulls the latest notifications using `list_recent_notifications`, and synthesizes a response that reflects the absolute latest changes in your repository.

Build semantic search indexes across organizations

Scale your knowledge retrieval across multiple teams by using `list_my_organizations` to map your workspace. The agent then searches across projects with `search_repositories` to find relevant code snippets. All retrieved metadata is structured and indexed automatically. This creates a unified index of your development footprint. Whether searching through code snippets via `list_my_gists` or tracking branch structures using `list_repo_branches`, the MCP Server converts raw JSON payloads into searchable vector embeddings for rapid retrieval.

Setup guide

Set up GitHub MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all GitHub MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to GitHub tools.",
)
response = await agent.run("List recent GitHub data")

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 LlamaIndex

You use the McpToolSpec to load tools like `list_repository_issues` into your LlamaIndex agent. This MCP adapter retrieves the raw issue payloads and passes them to your vector indexer as structured documents.

Yes, provided your Vinkius credential has the correct scopes. The MCP Server can run `get_file_content` to fetch private files and index them, allowing you to perform semantic search over proprietary code.

Yes, you can configure LlamaIndex to store vector embeddings of your repository data. Instead of calling `list_my_repositories` on every query, the agent searches the local vector store first and only queries the live API when it needs fresh data.

The agent uses function calling to determine if a query requires live data. If a user asks about recent changes, the agent triggers `list_pull_requests` or `list_recent_notifications` to pull the latest state before generating an answer.

Your proprietary code retrieved via `get_file_content` and code snippets from `list_my_gists` are processed strictly within isolated memory. Vinkius uses a zero-trust architecture that never logs the payloads of your files or code snippets, ensuring your intellectual property remains private.

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