How to Use the CodeRabbit MCP in LlamaIndex

Q: How do I ingest CodeRabbit metrics into a LlamaIndex vector store?

You use llama-index-tools-mcp to initialize the client and fetch the tools. The agent calls getmetrics to pull the data, which you then convert into document nodes for indexing.

Q: Can LlamaIndex query CodeRabbit audit logs using natural language?

Yes, by indexing the output of getauditlogs, your agent can answer complex questions about past admin actions. This turns raw log data into a searchable semantic index.

Q: How does the LlamaIndex MCP tool spec handle CodeRabbit seat management?

The McpToolSpec exposes tools like assignseats and unassignseats as standard LlamaIndex tools. Your agent calls them asynchronously during query execution to update seat allocations.

Q: Can I restrict which CodeRabbit tools LlamaIndex can access?

Yes, you can use the allowedtools filter when configuring your MCP client. This ensures the agent only has access to read-only tools like getseatmode if you want to prevent accidental updates.

Index CodeRabbit audit logs and PR metrics directly into LlamaIndex vector stores for semantic search and automated seat management.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CodeRabbit MCP to LlamaIndex

Create your Vinkius account to connect CodeRabbit 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 CodeRabbit with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index CodeRabbit metrics into LlamaIndex

The `get_metrics` tool retrieves raw engineering performance data and PR review statistics for indexing. LlamaIndex ingestion pipelines convert these metrics into searchable vectors, allowing you to query historical team performance. This MCP Server connection helps your agent ground its answers in real historical data rather than guessing. You can ask about code review bottlenecks and get answers backed by hard numbers.

Search administrative audit logs semantically

The `get_audit_logs` tool pulls compliance records directly into your document store. LlamaIndex parses these logs so you can run semantic queries over administrator changes and seat updates. When users ask who changed settings, the agent queries the vector index instead of making raw API calls. This search capability turns dry compliance text into an interactive, natural-language knowledge base.

Manage LlamaIndex-driven seat assignments

The `list_users` tool outputs your entire team roster along with their current seat assignment status. Your agent analyzes this index to find inactive accounts that are wasting paid licenses. To modify access, the agent invokes `unassign_seats` or `assign_seats` based on the patterns it finds in your database. This links your user directory directly to actionable license recovery workflows.

Setup guide

Set up CodeRabbit 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 CodeRabbit 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 CodeRabbit tools.",
)
response = await agent.run("List recent CodeRabbit 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 CodeRabbit. 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 CodeRabbit 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 CodeRabbit MCP in LlamaIndex

You use `llama-index-tools-mcp` to initialize the client and fetch the tools. The agent calls `get_metrics` to pull the data, which you then convert into document nodes for indexing.

Yes, by indexing the output of `get_audit_logs`, your agent can answer complex questions about past admin actions. This turns raw log data into a searchable semantic index.

The `McpToolSpec` exposes tools like `assign_seats` and `unassign_seats` as standard LlamaIndex tools. Your agent calls them asynchronously during query execution to update seat allocations.

Yes, you can use the `allowed_tools` filter when configuring your MCP client. This ensures the agent only has access to read-only tools like `get_seat_mode` if you want to prevent accidental updates.

Your local or cloud vector database stores the indexed data, while Vinkius secures the active API connection. No raw user data or review metrics are cached on the Vinkius platform.

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