How to Use the Haystack (deepset Cloud) MCP in LlamaIndex

Q: How do I index results from searchdocuments using Haystack (deepset Cloud) and LlamaIndex?

Use the McpToolSpec to load the Haystack tools into your agent. When the agent calls searchdocuments, you take the list of documents it returns and pass them to a LlamaIndex VectorStoreIndex to be indexed.

Q: What's a practical use for listworkspaces with LlamaIndex?

You can have your agent periodically call listworkspaces and listpipelines to keep an index of your Haystack environment up-to-date. This gives you a queryable 'state of the union' for your RAG infrastructure.

Turn Haystack (deepset Cloud) API output into a queryable LlamaIndex knowledge base. Index your pipelines, files, and search results.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Haystack (deepset Cloud) MCP to LlamaIndex

Create your Vinkius account to connect Haystack (deepset 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 Haystack (deepset Cloud) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Live Search Results

Don't just run a search—index the results. Your LlamaIndex agent can use the `search_documents` tool to query Haystack, then automatically ingest the returned documents into a vector index. Now your agent has a memory of past searches. This creates a powerful feedback loop. Your agent can answer questions using its existing knowledge base, and if it can't, it queries Haystack for new information, then adds that information to the index for next time.

Build a Queryable Index of Your Pipelines

Your agent can create a knowledge base about your RAG systems themselves. Use `list_workspaces` and `list_pipelines` to get a full catalog of your Haystack setup. Then, have your LlamaIndex agent index that data. Suddenly, you can ask your agent questions like, "Which pipelines are in the production workspace?" or "Show me pipelines related to document summarization." The agent answers by querying the index it built from the live API data.

Augment Your LlamaIndex Agent with Your MCP Server

This isn't just another data loader. It's a suite of active tools for your agent. While a loader might perform a one-time import, these tools let the agent interact with Haystack continuously. It can `run_pipeline` to get fresh data in response to a user query. Your agent decides when to call Haystack. It combines stored knowledge from its index with live data from your pipelines, giving you answers that are both contextual and up-to-date. This MCP integration makes your agent an active participant, not just a passive reader.

Setup guide

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

Use the `McpToolSpec` to load the Haystack tools into your agent. When the agent calls `search_documents`, you take the list of documents it returns and pass them to a LlamaIndex `VectorStoreIndex` to be indexed.

Not directly, but you can build a log. Each time your agent calls `run_pipeline`, you can log the inputs and outputs, then use LlamaIndex to index that log file. This creates a searchable history of your agent's actions.

A data loader is for one-time ingestion. This MCP server gives your LlamaIndex agent live tools to interact with Haystack (deepset Cloud) in real-time, letting it decide when to `run_pipeline` or `search_documents` based on the conversation.

You can have your agent periodically call `list_workspaces` and `list_pipelines` to keep an index of your Haystack environment up-to-date. This gives you a queryable 'state of the union' for your RAG infrastructure.

Yes. The connection is managed by Vinkius and secured by your token. The server processes tool calls but doesn't retain the content. For example, when you use `search_documents`, the document contents pass from deepset Cloud to your LlamaIndex agent through an encrypted, ephemeral transaction.

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