How to Use the CockroachDB Cloud MCP in LlamaIndex

Q: How do I connect the CockroachDB Cloud MCP Server to LlamaIndex?

Use pip install llama-index-tools-mcp to get the adapter. Set up BasicMCPClient with the Vinkius endpoint, convert it to a tool spec, and pass it to your FunctionAgent.

Q: Can LlamaIndex index CockroachDB Cloud metadata for offline retrieval?

Yes, you can load tool outputs from listcockroachclusters into documents and index them in a vector store. This allows your agent to answer status questions even when offline.

Q: How does LlamaIndex handle tool filtering for CockroachDB Cloud MCP Server?

You can pass an allowedtools list to the McpToolSpec constructor. This restricts the agent to specific tools like listclusternodes while ignoring administrative actions.

Q: Does this integration expose SQL data to the LlamaIndex vector store?

No, it only indexes control plane metadata. Tools like listencryptionkeys and cluster lists expose infrastructure configurations, keeping your actual database tables private.

Index CockroachDB Cloud cluster metadata directly into your LlamaIndex vector store using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CockroachDB Cloud MCP to LlamaIndex

Create your Vinkius account to connect CockroachDB Cloud 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 CockroachDB Cloud with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Indexing Live Cluster Metadata

Index live database configurations directly into your vector store by pulling real-time data from `list_cockroach_clusters`. Your RAG pipeline gets access to real-time cluster states by combining this metadata with `get_cluster_cloud_details`. Your agent queries this indexed data to answer complex infrastructure questions without hitting the live API every single time. This reduces latency and keeps your API consumption efficient.

Semantically Search Your MCP Server Logs

Search your operational history semantically by indexing the output of `list_cluster_operations` into a queryable knowledge base. Instead of scrolling through text logs, your agent retrieves the exact JSON block from `list_cluster_nodes` that matches your query. This semantic search grounds your agent's answers in actual system facts. You get reliable answers about database upgrades and scaling events.

Unified Cloud Provider RAG

Audit active network access rules by feeding `list_network_allowlist` outputs into your semantic security checks. The agent matches these rules against `list_supported_cloud_providers` to highlight region mismatches. You can ask if a specific server is allowed to connect and get an immediate answer. This semantic check prevents manual firewall audits.

Setup guide

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

Use `pip install llama-index-tools-mcp` to get the adapter. Set up `BasicMCPClient` with the Vinkius endpoint, convert it to a tool spec, and pass it to your `FunctionAgent`.

Yes, you can load tool outputs from `list_cockroach_clusters` into documents and index them in a vector store. This allows your agent to answer status questions even when offline.

You can pass an `allowed_tools` list to the `McpToolSpec` constructor. This restricts the agent to specific tools like `list_cluster_nodes` while ignoring administrative actions.

No, it only indexes control plane metadata. Tools like `list_encryption_keys` and cluster lists expose infrastructure configurations, keeping your actual database tables private.

The token is injected securely at the Vinkius sandbox layer. LlamaIndex only interacts with the sandboxed MCP endpoint, meaning your master API keys are never exposed to the LLM or the vector storage layer.

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