An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Vectorshift AI Workflow RAG Automation to your AI

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Control your RAG pipelines and chatbots through natural conversation.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 29 capabilities

We ship only the actions that matter.

Capability set01 / 08

01-04

4 capabilities in this set.

Part of 29 available through VectorShift.

  1. 01

    List knowledge bases

    This capability shows you all the knowledge bases currently in your system.

  2. 02

    Create chatbot

    This capability sets up a new chatbot using your provided configuration.

  3. 03

    Create knowledge base

    Use this to build a new knowledge base with your required settings.

  4. 04

    Create pipeline

    This capability creates a new multi-step workflow pipeline.

Capability set02 / 08

05-08

4 capabilities in this set.

Part of 29 available through VectorShift.

  1. 05

    Create transformation

    This capability builds a new data transformation using Python or JavaScript code.

  2. 06

    Delete chatbot

    This capability removes a chatbot from your account.

  3. 07

    Get knowledge base

    Use this to fetch information about a knowledge base via its ID or name.

  4. 08

    Get pipeline

    This capability pulls up the configuration for a specific pipeline.

Capability set03 / 08

09-12

4 capabilities in this set.

Part of 29 available through VectorShift.

  1. 09

    Terminate pipeline

    This capability stops a running pipeline instance immediately.

  2. 10

    Upload chatbot files

    This capability uploads files directly to a chatbot session.

  3. 11

    List pipelines

    This capability provides a list of all your available pipelines.

  4. 12

    Bulk run pipeline

    This capability runs multiple instances of a specific pipeline at the same time.

Capability set04 / 08

13-16

4 capabilities in this set.

Part of 29 available through VectorShift.

  1. 13

    Delete knowledge base

    This capability deletes an entire knowledge base.

  2. 14

    Delete knowledge base documents

    Use this to remove specific documents from a knowledge base by their ID.

  3. 15

    Delete pipeline

    This capability removes a pipeline from your system using its ID.

  4. 16

    Delete transformation

    This capability deletes a specific data transformation.

Capability set05 / 08

17-20

4 capabilities in this set.

Part of 29 available through VectorShift.

  1. 17

    Get chatbot

    This capability retrieves the details of a specific chatbot by its name or ID.

  2. 18

    Get transformation

    This capability fetches the details of a transformation using its name or ID.

  3. 19

    Index knowledge base

    This capability adds new data like files or URLs to a specific knowledge base.

  4. 20

    List chatbots

    Use this to see a list of all your configured chatbots.

Capability set06 / 08

21-23

3 capabilities in this set.

Part of 29 available through VectorShift.

  1. 21

    List knowledge base documents

    Use this to see all the documents stored inside a knowledge base.

  2. 22

    List transformations

    This capability shows you all the transformations you have created.

  3. 23

    Pause pipeline

    This capability stops a running pipeline instance temporarily.

Capability set07 / 08

24-26

3 capabilities in this set.

Part of 29 available through VectorShift.

  1. 24

    Query knowledge base

    Use this to perform a semantic search against a specific knowledge base.

  2. 25

    Resume pipeline

    This capability restarts one or more paused pipeline instances.

  3. 26

    Run chatbot

    This capability sends a message to a chatbot and returns its response.

Capability set08 / 08

27-29

3 capabilities in this set.

Part of 29 available through VectorShift.

  1. 27

    Run pipeline

    This capability starts a specific pipeline with the inputs you provide.

  2. 28

    Run transformation

    This capability executes a specific data transformation with your inputs.

  3. 29

    Terminate chatbot

    This capability ends an active chatbot session.

Real work

What teams actually run

01

Automated Data Extraction

Trigger a pipeline to scrape a URL and transform the data using custom JavaScript.

02

Internal Knowledge Retrieval

Ask your agent to find specific policy details within a company wiki knowledge base.

03

Chatbot Deployment

Create and configure a new chatbot instance to handle specific user queries.

04

Workflow Monitoring

Pause or terminate long-running pipelines if the output doesn't meet requirements.

Automate a task

Put VectorShift to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

VectorShift works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put VectorShift to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

994ms average. Fast in production.

VectorShift is checked daily against the live service.

Daily averagePeak 1250ms
Oct 3Today
Fastest day
807ms
Slowest day
1250ms
14-day trend
Improving-6%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 29 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of VectorShift, so you can see the experience inside your AI.

It does not authenticate your account with VectorShift. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

VectorShift Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_EmQ0ykbVFnJJJOx8Wrsr9PBOJ4yiohOhm84Pa96G/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — VectorShift capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "vectorshift-ai-workflow-rag-automation-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_EmQ0ykbVFnJJJOx8Wrsr9PBOJ4yiohOhm84Pa96G/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up VectorShift in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work VectorShift owners hand off.

This MCP is built for technical teams who need to bridge the gap between AI reasoning and automated execution.

  • 01

    AI Developers

    They use it to trigger and test RAG pipelines or index knowledge bases directly from their IDE.

  • 02

    Operations Teams

    They use it to automate repetitive data processing through pre-built pipelines.

  • 03

    Product Teams

    They use it to query internal technical documentation via AI agents.

FAQ

Questions VectorShift owners ask.

  • 01

    How do I connect my VectorShift account?

    You subscribe to the MCP on Vinkius and enter your VectorShift API Key. Once connected, your AI client can immediately start using the capabilities.

  • 02

    Which AI clients can I use with this MCP?

    You can use this MCP with any compatible client, including Claude, Cursor, and Windsurf.

  • 03

    Can I run custom code in my workflows?

    Yes, you can create and run custom transformations using Python or JavaScript as part of your pipelines.

  • 04

    Can I manage my existing VectorShift chatbots?

    Yes, you can list, get, create, and delete chatbots, as well as run or terminate active sessions.

  • 05

    Is it possible to search through my uploaded documents?

    Yes, you can use the query_knowledge_base capability to perform semantic searches on your indexed data.

  • 06

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

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

  • 07

    Can I trigger a specific AI workflow with custom parameters?

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

  • 08

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

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

Explore

More in Knowledge Management

Suggestions

Connect VectorShift to Claude, Cursor, ChatGPT & more