Download PDFMarkdown Version
ClaudeChatGPTPerplexityGeminiMicrosoft CopilotRaycastMeta AIGrokZ.aiQwenKimi
DeepSeekMistralCursorVS CodeWindsurfJetBrainsClineLovableVercel AI SDKLangChain

Use VectorShift with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Automate AI workflows and RAG via VectorShift. manage pipelines, query knowledge bases, and deploy chatbots directly from any AI agent.

Included with plan

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

Complete set · 29 capabilities

The complete VectorShift capability set.

These are the exact actions your AI can choose when you ask it to work with VectorShift.

Capability set01 / 08

01-04

4 capabilities in this set.

Part of 29 available through VectorShift.

  1. 01

    Delete knowledge base documents

    Delete specific documents by ID from a knowledge base

  2. 02

    List knowledge bases

    List all available knowledge bases

  3. 03

    Create chatbot

    Create a new chatbot

  4. 04

    Create knowledge base

    Create a new knowledge base

Capability set02 / 08

05-08

4 capabilities in this set.

Part of 29 available through VectorShift.

  1. 05

    Create pipeline

    Create a new pipeline

  2. 06

    Create transformation

    Create a new transformation (Python/JS)

  3. 07

    Delete pipeline

    Delete a pipeline by ID

  4. 08

    Delete transformation

    Delete a transformation

Capability set03 / 08

09-12

4 capabilities in this set.

Part of 29 available through VectorShift.

  1. 09

    Get chatbot

    Fetch a chatbot by id or name

  2. 10

    Get pipeline

    Fetch a pipeline by id or name

  3. 11

    Get transformation

    Fetch a transformation by id or name

  4. 12

    Index knowledge base

    Add data (files, URLs, etc.) to a knowledge base

Capability set04 / 08

13-16

4 capabilities in this set.

Part of 29 available through VectorShift.

  1. 13

    List pipelines

    List all available pipelines

  2. 14

    List transformations

    List all available transformations

  3. 15

    Pause pipeline

    Pause a currently running pipeline instance

  4. 16

    Run pipeline

    Execute a pipeline with specified inputs

Capability set05 / 08

17-20

4 capabilities in this set.

Part of 29 available through VectorShift.

  1. 17

    Run transformation

    Execute a transformation with inputs

  2. 18

    Terminate chatbot

    Terminate an active chatbot session

  3. 19

    Terminate pipeline

    Stop a currently running pipeline instance

  4. 20

    Bulk run pipeline

    Execute multiple instances of a pipeline in parallel

Capability set06 / 08

21-23

3 capabilities in this set.

Part of 29 available through VectorShift.

  1. 21

    Delete chatbot

    Delete a chatbot

  2. 22

    Delete knowledge base

    Delete a knowledge base

  3. 23

    Get knowledge base

    Fetch a knowledge base by id or name

Capability set07 / 08

24-26

3 capabilities in this set.

Part of 29 available through VectorShift.

  1. 24

    List chatbots

    List all available chatbots

  2. 25

    List knowledge base documents

    Find documents within a knowledge base

  3. 26

    Query knowledge base

    Query a knowledge base with semantic search

Capability set08 / 08

27-29

3 capabilities in this set.

Part of 29 available through VectorShift.

  1. 27

    Resume pipeline

    Resume one or more paused pipeline instances

  2. 28

    Run chatbot

    Send a message to a chatbot and get a response

  3. 29

    Upload chatbot files

    Upload files to a chatbot session

Observed, not estimated

985ms average. Fast in production.

VectorShift is checked daily against the live service.

Daily averagePeak 1234ms
Aug 20Today
Fastest day
873ms
Slowest day
1234ms
14-day trend
Slowing+11%

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

FAQ

Questions VectorShift owners ask.

  • 01

    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.

  • 02

    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.

  • 03

    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