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

Q: How do I get my LangChain agent to run a specific Haystack (deepset Cloud) pipeline?

Give the agent the runpipeline tool. It takes a pipeline ID and input data, then returns the result. Your agent can call it directly as part of a chain.

Q: Can a LangChain agent choose which Haystack (deepset Cloud) pipeline to use?

Yes. Provide the agent with both listpipelines and runpipeline. The agent can first call listpipelines to see what's available, then decide which one to execute based on its goal.

Q: How does LangSmith tracing work with this MCP Server and LangChain?

Every tool call—like searchdocuments or runpipeline—appears as a distinct step in your LangSmith trace. You'll see the exact inputs, outputs, latency, and any errors for each interaction with your Haystack (deepset Cloud) workspace.

Plug your Haystack RAG pipelines directly into your LangChain agents. Let the agent find and run the right pipeline for the job.

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 LangChain

Create your Vinkius account to connect Haystack (deepset Cloud) to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Pipeline Discovery and Execution

Give your agent the ability to find and run your Haystack pipelines. It can use `list_workspaces` to pick the right environment, `list_pipelines` to find the correct tool for the task, and then execute it with `run_pipeline`. This isn't just about running a single pipeline. You build agents that can reason about which pipeline to use based on the user's request. The output from one tool call becomes the input for the next, letting your agent navigate your entire deepset Cloud setup on its own.

Ground Answers in Your Source Documents for LangChain

Your agent can now perform vector search directly against your indexes. The `search_documents` tool lets it query your data and get back the most relevant chunks. This is how you build reliable RAG chains that cite their sources. Combine this with `get_file` to pull the full context for a specific document. Your agent doesn't just get a search snippet; it can retrieve the original source material. This is critical for tasks that require deep validation or summarization.

Inspect and Manage Pipeline Configurations

Let your agent see how your pipelines are built. With `get_pipeline`, it can fetch the full configuration details for any pipeline by its ID. This is useful for debugging or for agents that need to understand the underlying components of a search process. Imagine an agent that can compare two pipelines before running them. Or one that checks if a pipeline uses a specific model before proceeding. This MCP Server gives your chains the situational awareness they need to make smarter decisions.

Setup guide

Set up Haystack (deepset Cloud) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Haystack (deepset Cloud) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "haystack-deepset-cloud-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Haystack (deepset Cloud) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Give the agent the `run_pipeline` tool. It takes a pipeline ID and input data, then returns the result. Your agent can call it directly as part of a chain.

Yes. Provide the agent with both `list_pipelines` and `run_pipeline`. The agent can first call `list_pipelines` to see what's available, then decide which one to execute based on its goal.

Every tool call—like `search_documents` or `run_pipeline`—appears as a distinct step in your LangSmith trace. You'll see the exact inputs, outputs, latency, and any errors for each interaction with your Haystack (deepset Cloud) workspace.

It lets the agent see what source documents are actually in your workspace. This is useful for verification, or for agents that need to confirm a file exists before trying to process it.

Your Vinkius token handles authentication, and your data stays within your deepset Cloud account. This MCP server only processes requests and responses, like pipeline IDs from `list_pipelines` or file metadata from `get_file`. It doesn't store your documents or pipeline definitions.

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