How to Use the Nimbleway MCP in LlamaIndex

Q: How do I connect Nimbleway to LlamaIndex?

Install llama-index-tools-mcp. Set up a BasicMCPClient pointing to the server URL. Convert the tools with McpToolSpec and pass them to your FunctionAgent.

Q: Can LlamaIndex query live web search results using Nimbleway?

Yes. The searchweb tool returns structured search engine results. Your agent can read those snippets directly or decide to scrape the full links.

Q: Is it better to extract HTML or Markdown for Nimbleway RAG in LlamaIndex?

Always use extractmarkdown for vector indexing. It strips out the CSS and JavaScript, leaving only the semantic text your embedding model actually cares about.

Q: How do I track my active scraping jobs?

Call listjobs through the MCP Server to see everything currently running. If you need details on a specific target, pass the ID to getjob.

Feed live web data directly into LlamaIndex. Turn unstructured public websites into a searchable index.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nimbleway MCP to LlamaIndex

Create your Vinkius account to connect Nimbleway 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 Nimbleway with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index the web with this MCP Server

Static documents go out of date. You need a RAG pipeline that pulls fresh context on demand. By connecting LlamaIndex to `search_web`, your application actively hunts for new information before answering a user query. When the agent finds a relevant source, it uses `extract_markdown` to strip out the noise. That clean text gets chunked and indexed immediately. Your vector store stays completely up to date with live internet data.

Monitor scraping infrastructure

High-volume data ingestion requires serious proxy management. Your application can query `list_proxies` to ensure it routes traffic through the right geographic regions before hitting target sites. If a site throws a captcha, you don't want your indexer to crash. The agent monitors `get_account_usage` and `get_job` to verify the scrape succeeded. If a job fails, the system logs it and moves to the next URL.

Automate your data pipelines

You don't have to trigger every scrape manually. Use `list_pipelines` to review your active automated workflows. Your LlamaIndex MCP integration can check `get_pipeline` to confirm when fresh batches of data finish processing. It then automatically pulls the results and updates the semantic index.

Setup guide

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

Install `llama-index-tools-mcp`. Set up a `BasicMCPClient` pointing to the server URL. Convert the tools with `McpToolSpec` and pass them to your `FunctionAgent`.

Yes. The `search_web` tool returns structured search engine results. Your agent can read those snippets directly or decide to scrape the full links.

Always use `extract_markdown` for vector indexing. It strips out the CSS and JavaScript, leaving only the semantic text your embedding model actually cares about.

Call `list_jobs` through the MCP Server to see everything currently running. If you need details on a specific target, pass the ID to `get_job`.

No. The queries and URLs you send to the API are transient. Vinkius operates a zero-trust architecture, so your scraped HTML and pipeline configurations never persist on our infrastructure after the request completes.

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