MCP For Claude Marketplace
Haystack (deepset Cloud)

Haystack (deepset Cloud) MCP Connector for Claude

A+

Build and manage AI-powered search and RAG pipelines via deepset Cloud — search documents, run pipelines, and manage workspaces.

7 tools Official Updated Jun 28, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect your deepset Cloud account to any AI agent and manage your Haystack-powered RAG pipelines through natural conversation.

What you can do

  • Workspaces — List and manage isolated environments for different search contexts
  • Pipelines — Visualize NLP topologies, including embedding nodes and retriever logic
  • Run Search — Dispatch immediate LLM or Retriever invocations to test RAG pipelines
  • Document Management — List files and inspect metadata attached to source document embeddings
  • Vector Search — Trigger dense or sparse vector searches over indexed enterprise knowledge

How it works

  1. Subscribe to this server
  2. Enter your deepset Cloud API URL and API Key
  3. Start managing your AI pipelines from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • AI/ML Teams — quickly audit pipeline configurations and test search results
  • RAG Developers — integrate enterprise knowledge bases with AI agents for contextual answers
  • Product Managers — monitor search performance and verify document indexing status
rag-pipelinesllm-frameworkenterprise-searchnlp-topologiesembedding-modelsdocument-retrieval

7 tools expose this connector's capabilities to your AI agent.

list_workspaces

List workspaces

list_pipelines

List pipelines

get_pipeline

Get pipeline details

run_pipeline

Run a pipeline search

list_files

List uploaded files

get_file

Get file metadata

search_documents

Search documents in index

See how to talk to your AI agent using Haystack (deepset Cloud).

List all pipelines in my 'production' workspace

I found 3 pipelines in your production workspace: 'default-rag', 'semantic-search', and 'hybrid-retriever'. Which one would you like to inspect?

Run a search for 'AI security compliance' using the default-rag pipeline

Running search… Based on your indexed documents, I found 5 relevant snippets. The main compliance requirements are… [results summary]. Would you like to see the source file IDs?

List the files in my 'knowledge-base' workspace

You have 12 files in the 'knowledge-base' workspace. Recent uploads include 'q4_report.pdf', 'security_guidelines.md', and 'api_docs.txt'. I can fetch metadata for any of these files.

Yes. Use the `run_pipeline` tool to dispatch a query to any registered pipeline in your workspace. Your agent will return the response from the NLP topology, allowing you to verify retriever performance and LLM grounding without leaving your workspace.

Related Connectors

JP

Jamf Pro MCP

10 tools Official

Manage Apple devices, computers, and inventory via Jamf Pro API.

A+ View details →
UE

USGS Earthquakes MCP

3 tools Official

Tap into the USGS real-time seismic network. Monitor global earthquakes, filter by magnitudes, and run historical analyses instantly.

A+ View details →
CE

Celoxis MCP

12 tools Official

Empower your AI agents to manage complex portfolios, track project milestones, and analyze resource timesheets on Celoxis.

F View details →
DS

Data Sorting & Filtering Engine MCP

2 tools Official

Perfect array manipulation. Sort and deduplicate massive JSON lists with native Vinkius Edge JavaScript instead of relying on token-limited LLMs.

A+ View details →