How do I search for specific information within my VectorShift knowledge base?

Use the `query_knowledge_base` tool with your Knowledge Base ID and the search query. The agent will perform a semantic search and return the most relevant data chunks.

Can I trigger a specific AI workflow with custom parameters?

Yes! Use the `run_pipeline` tool. Provide the Pipeline ID and a JSON object mapping your input names to their respective values to start the execution.

Is it possible to add new documents to a knowledge base through the agent?

Absolutely. Use the `index_knowledge_base` tool to add data (such as URLs or file content) to an existing knowledge base for real-time RAG updates.

VectorShift (AI Workflow & RAG Automation) MCP Connector for Claude

A+

Automate AI workflows and RAG via VectorShift — manage pipelines, query knowledge bases, and deploy chatbots directly from any AI agent.

29 tools Official Updated Oct 1, 2026 Official Vinkius Partner

More Details Connect to Claude

Connect your VectorShift account to any AI agent and take full control of your AI automation and RAG (Retrieval-Augmented Generation) workflows through natural conversation.

What you can do

AI Pipelines — List, create, and run complex multi-step workflows. Manage execution with pause, resume, and terminate controls.
Knowledge Management — Create vector-based knowledge bases, index documents (files/URLs), and perform semantic searches to ground your AI.
Chatbot Orchestration — Deploy chatbots, upload context files, and run conversational instances directly.
Data Transformations — Execute custom data transformations and logic as part of your automated processes.

How it works

Subscribe to this server
Enter your VectorShift API Key
Start building and running AI automations from Claude, Cursor, or any MCP-compatible client

Who is this for?

AI Developers — trigger and test RAG pipelines or knowledge base indexing straight from your coding environment
Operations Teams — automate repetitive data processing tasks using pre-built AI pipelines
Product Teams — quickly query internal knowledge bases to retrieve technical or product documentation via AI

ragai-workflowsautomationknowledge-basellm-ops

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

list_knowledge_bases

Use this tool to view the system’s knowledge base structure. List all available knowledge bases

create_chatbot

Supply the required configuration payload for the new chatbot. Create a new chatbot

create_knowledge_base

The payload must contain all required settings. Create a new knowledge base

create_pipeline

The payload must contain all required settings. Create a new pipeline

create_transformation

Ensure the payload contains valid Python or JavaScript code. Create a new transformation (Python/JS)

delete_chatbot

Ensure the chatbot is not currently in use before calling this tool. Delete a chatbot

get_knowledge_base

Provide at least one identifier. Fetch a knowledge base by id or name

get_pipeline

Fetch a pipeline by id or name

terminate_pipeline

The ID must belong to an active pipeline run. Stop a currently running pipeline instance

upload_chatbot_files

Specify the Chatbot ID and the file upload payload. Upload files to a chatbot session

list_pipelines

Use this tool to view the system’s pipeline structure. List all available pipelines

bulk_run_pipeline

The ID must correspond to an existing pipeline definition. Execute multiple instances of a pipeline in parallel

delete_knowledge_base

Ensure the ID belongs to an existing knowledge base. Delete a knowledge base

delete_knowledge_base_documents

Supply the knowledge base ID and the document IDs in the payload. Delete specific documents by ID from a knowledge base

delete_pipeline

Ensure the ID belongs to an existing pipeline. Delete a pipeline by ID

delete_transformation

The ID must correspond to an existing transformation. Delete a transformation

get_chatbot

Use either the ID or the name parameter, but not both. Fetch a chatbot by id or name

get_transformation

Use either the ID or the name parameter, but not both. Fetch a transformation by id or name

index_knowledge_base

) to a knowledge base. Provide the target knowledge base ID and the data payload. Add data (files, URLs, etc.) to a knowledge base

list_chatbots

Use this tool to view the system’s chatbot structure. List all available chatbots

list_knowledge_base_documents

Provide the ID of the knowledge base to search. Find documents within a knowledge base

list_transformations

List all available transformations

pause_pipeline

The ID must belong to an active pipeline run. Pause a currently running pipeline instance

query_knowledge_base

Specify the knowledge base ID and the search queries. Query a knowledge base with semantic search

resume_pipeline

The IDs must belong to paused pipeline runs. Resume one or more paused pipeline instances

run_chatbot

Provide a conversation ID if state must be maintained. Send a message to a chatbot and get a response

run_pipeline

The ID must correspond to an existing pipeline definition. Execute a pipeline with specified inputs

run_transformation

The transformation must be active to run successfully. Execute a transformation with inputs

terminate_chatbot

Provide the Chatbot ID to end the session. Terminate an active chatbot session

Connect to Claude

Subscribe on Vinkius, then add this connector to Claude.ai or Claude Code.

① Claude.ai (web app)

Go to Settings → Connectors → Add custom connector
Paste the MCP endpoint URL below

https://edge.vinkius.com/vk_preview_EmQ0ykbVFnJJJOx8Wrsr9PBOJ4yiohOhm84Pa96G/mcp

② Claude Code (terminal)

claude mcp add --transport http vectorshift-ai-workflow-rag-automation https://edge.vinkius.com/vk_preview_EmQ0ykbVFnJJJOx8Wrsr9PBOJ4yiohOhm84Pa96G/mcp

③ Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "vectorshift-ai-workflow-rag-automation": {
      "url": "https://edge.vinkius.com/vk_preview_EmQ0ykbVFnJJJOx8Wrsr9PBOJ4yiohOhm84Pa96G/mcp"
    }
  }
}

Get full access on Vinkius

The preview token above works for testing. Powered by Vinkius.