How to Use the Nango (Unified API & Integration Platform) MCP in LlamaIndex

Q: How do I index unified records from Nango (Unified API & Integration Platform) using LlamaIndex?

You use the MCP tool spec to call listrecords directly from your ingestion pipeline. LlamaIndex takes those standardized JSON records, parses them into document nodes, and writes them to your chosen vector store.

Q: Can LlamaIndex query connection statuses in Nango (Unified API & Integration Platform)?

Yes, your agent can call listconnections or getconnection to retrieve connection metadata. This allows the agent to verify if a user's account is linked before attempting to index their data.

Q: Does the Nango (Unified API & Integration Platform) MCP Server support asynchronous loading in LlamaIndex?

Yes, using totoollistasync() allows LlamaIndex to fetch integration parameters via listintegrations asynchronously. This keeps your data loading fast even when querying multiple integrations at once.

Q: How do I restrict which tools my LlamaIndex agent can access?

You can use the MCP server's allowedtools filter during initialization to limit the agent's scope. For example, you can restrict it to listrecords and listsyncs if you only want it reading synced data.

Q: Where does the synchronized SaaS data go when queried by the server?

Synced records retrieved via listrecords pass straight to your local LlamaIndex instance for indexing. No raw data is cached or stored inside the Vinkius sandbox, keeping your customer records secure and compliant with enterprise standards.

Index unified SaaS records into LlamaIndex vector stores to ground your agents in live Nango integration data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nango (Unified API & Integration Platform) MCP to LlamaIndex

Create your Vinkius account to connect Nango (Unified API & Integration Platform) 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 Nango (Unified API & Integration Platform) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build RAG Pipelines with Live SaaS Data

LlamaIndex excels at turning external data into searchable knowledge bases, and this MCP Server feeds it perfectly. By calling `list_records`, your pipeline pulls unified data from external integrations and indexes them directly into your vector database. Your retrieval-augmented generation apps no longer rely on stale file exports. The agent queries live, synchronized records, ensuring its answers are grounded in actual, up-to-date business data instead of model hallucinations.

Index Integration Metadata for Semantic Search

Feed your system configuration details directly into your index using `list_integrations` and `get_environment`. This lets your agent answer complex questions about your active integrations, including which external APIs are currently connected. If a developer asks which CRM tools are active, the agent queries the indexed output of `list_connections` to give a precise response. You get a self-documenting integration setup that anyone on your team can query using natural language.

Track Sync Health directly from LlamaIndex

Keep tabs on your background data ingestion by running diagnostics over your sync histories. Your agent can call `list_syncs` to check if recent data loads succeeded before running a vector query. If the agent detects a failed sync, it uses `get_integration` to inspect the configuration boundaries. This step ensures your RAG pipeline only queries healthy, complete data sources.

Setup guide

Set up Nango (Unified API & Integration Platform) 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 Nango (Unified API & Integration Platform) 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 Nango (Unified API & Integration Platform) tools.",
)
response = await agent.run("List recent Nango (Unified API & Integration Platform) 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 Nango. 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 Nango (Unified API & Integration Platform) 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 Nango (Unified API & Integration Platform) MCP in LlamaIndex

You use the MCP tool spec to call `list_records` directly from your ingestion pipeline. LlamaIndex takes those standardized JSON records, parses them into document nodes, and writes them to your chosen vector store.

Yes, your agent can call `list_connections` or `get_connection` to retrieve connection metadata. This allows the agent to verify if a user's account is linked before attempting to index their data.

Yes, using to_tool_list_async() allows LlamaIndex to fetch integration parameters via `list_integrations` asynchronously. This keeps your data loading fast even when querying multiple integrations at once.

You can use the MCP server's allowed_tools filter during initialization to limit the agent's scope. For example, you can restrict it to `list_records` and `list_syncs` if you only want it reading synced data.

Synced records retrieved via `list_records` pass straight to your local LlamaIndex instance for indexing. No raw data is cached or stored inside the Vinkius sandbox, keeping your customer records secure and compliant with enterprise standards.

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