How to Use the Haystack (deepset Cloud) MCP in Claude Code

Q: How do I use Claude Code to run a Haystack (deepset Cloud) pipeline from a shell script?

You pipe your query to the claude command and specify the tool, like echo '{"query": "My question"}' claude mcp call haystack runpipeline. It executes the request and prints the JSON result to stdout.

Q: Can I pipe a list of queries to Claude Code to search Haystack (deepset Cloud) in a loop?

Yes. You can write a shell script with a while read loop that reads queries from a file and pipes each one to Claude Code. It's an effective way to run batch searches against your Haystack (deepset Cloud) indexes.

Q: What's the best way to get a list of all pipelines from Haystack (deepset Cloud) using Claude Code?

Just run claude mcp call haystack listpipelines. It requires no input and will return a JSON array of all the pipelines available in your configured workspace.

Q: Can I automate file checks in deepset Cloud with a Claude Code script?

Absolutely. A simple bash script can call claude mcp call haystack listfiles and then use jq to check if a specific file exists or check its metadata. You can run this as a cron job.

Automate your Haystack (deepset Cloud) search and RAG tasks. Run headless queries with Claude Code from any shell or CI/CD pipeline.

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 Claude Code

Create your Vinkius account to connect Haystack (deepset Cloud) to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Script Headless Searches and Queries

This MCP server connects your terminal directly to deepset Cloud. You can pipe a query to Claude Code, tell it to use the `run_pipeline` tool, and get structured JSON back. It's built for automation. Chain it with other command-line tools like `jq` to parse the results or trigger other scripts. This is perfect for building custom data processing workflows that run on a schedule or via webhooks.

Automate Document Index Monitoring

Write a simple cron job that uses Claude Code to hit the `search_documents` tool. You can build a shell script to periodically check if new documents are properly indexed or to monitor search latency from different locations. Because Claude Code is headless, you can run these checks from any server or container. It's a straightforward way to build a monitoring system for your search infrastructure.

Integrate RAG into CI/CD Pipelines

Use Claude Code as a step in a GitHub Action to validate your documentation. The workflow can use `run_pipeline` to ask critical questions against your docs repository after every commit. If the answers are wrong or missing, the build fails. This is quality control for your knowledge base, ensuring your RAG system always has the correct information.

Setup guide

Set up Haystack (deepset Cloud) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see haystack-deepset-cloud-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Haystack (deepset Cloud) transactions." It will automatically discover and invoke the available Haystack (deepset Cloud) tools.

Terminal

claude mcp add --transport http haystack-deepset-cloud-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Haystack (deepset Cloud) MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "haystack-deepset-cloud-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Code

You pipe your query to the `claude` command and specify the tool, like `echo '{"query": "My question"}' | claude mcp call haystack run_pipeline`. It executes the request and prints the JSON result to stdout.

Yes. You can write a shell script with a `while read` loop that reads queries from a file and pipes each one to Claude Code. It's an effective way to run batch searches against your Haystack (deepset Cloud) indexes.

Just run `claude mcp call haystack list_pipelines`. It requires no input and will return a JSON array of all the pipelines available in your configured workspace.

Absolutely. A simple bash script can call `claude mcp call haystack list_files` and then use `jq` to check if a specific file exists or check its metadata. You can run this as a cron job.

The server only gets the specific inputs for the tool you call, like a pipeline ID for `run_pipeline` or a query string for `search_documents`. It has no access to your shell history or local files. Each request is handled by a dedicated V8 isolate that's destroyed immediately after.

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