ClaudeChatGPTPerplexityGeminiMicrosoft CopilotRaycastMeta AIGrokZ.aiQwenKimi
DeepSeekMistralCursorVS CodeWindsurfJetBrainsClineLovableVercel AI SDKLangChain

Use MyScale with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Manage MyScale vector databases via SQL. execute queries, perform vector searches, and manage indices 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 · 6 capabilities

The complete MyScale capability set.

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

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 6 available through MyScale.

  1. 01

    Ping cluster

    Check MyScale cluster connectivity

  2. 02

    Check index status

    Vector_indices table to monitor the build status of vector indices (Built, InProgress, Error). Check the status of vector indices

  3. 03

    Create vector index

    ADD VECTOR INDEX statement. Create a vector index on a table

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through MyScale.

  1. 04

    Create vector table

    Create a new table with a vector column

  2. 05

    Execute SQL query

    For SELECT queries, FORMAT JSON is automatically appended. Execute an arbitrary SQL query on MyScale

  3. 06

    Vector search

    Automatically constructs the SQL query. Perform a vector similarity search

Observed, not estimated

885ms average. Fast in production.

MyScale is checked daily against the live service.

Daily averagePeak 1084ms
Aug 20Today
Fastest day
667ms
Slowest day
1084ms
14-day trend
Slowing+27%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 6 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 MyScale, so you can see the experience inside your AI.

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

MyScale Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_vWeauVyztoYzGBsy6h9azMYGgJ3R8tQDDZfTvuoy/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 — MyScale capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "myscale-sql-vector-database-api-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_vWeauVyztoYzGBsy6h9azMYGgJ3R8tQDDZfTvuoy/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 MyScale owners ask.

  • 01

    How can I check if my vector index has finished building?

    Use the check_index_status capability. It queries the system tables to show you the current status (Built, InProgress, or Error) for all vector indices in your cluster.

  • 02

    Can I perform a vector search with metadata filtering?

    Yes! The vector_search capability includes an optional filter parameter where you can provide a SQL WHERE clause (e.g., "category = 'science'") to restrict your search results.

  • 03

    What SQL commands are supported by the execute capability?

    The execute_sql_query capability supports standard MyScale/ClickHouse SQL, including SELECT, CREATE, ALTER, and INSERT. For SELECT queries, it automatically formats the output as JSON for the agent.