
Connect Myscale SQL Vector Database API 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. Manage high-performance vector data using standard SQL syntax.
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.
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.

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.
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.
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 · 6 capabilities
We ship only the actions that matter.
01-03
3 capabilities in this set.
Part of 6 available through MyScale.
- 01
Ping cluster
Checks if your MyScale cluster is reachable and your credentials work.
- 02
Check index status
Monitors the build status of your vector indices to see if they are Built, InProgress, or in an Error state.
- 03
Create vector index
Adds a new vector index to a specific table using the ADD VECTOR INDEX statement.
04-06
3 capabilities in this set.
Part of 6 available through MyScale.
- 04
Create vector table
Sets up a new table containing a vector column.
- 05
Execute SQL query
Runs any SQL query on your MyScale cluster, with SELECT queries automatically formatted as JSON.
- 06
Vector search
Performs vector similarity searches by automatically constructing the necessary SQL queries.
Real work
What teams actually run
RAG Backend Management
Monitor the health of your vector indices and adjust schemas as your retrieval needs change.
Rapid Prototyping
Quickly create new vector tables with specific dimensions to test new embedding models.
Data Inspection
Run SQL queries to check data distributions and verify the contents of your vector columns.
Database Maintenance
Use natural language to execute ALTER commands or check cluster connectivity.
Automate a task
Put MyScale 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
MyScale 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.
Claude
ChatGPT
Gemini
Perplexity
Grok
Microsoft Copilot
Cursor
VS Code
Windsurf
JetBrains
Cline
LangChain
Vercel AI SDK
Lovable
Z.ai
Raycast
Qwen Code
Kimi Code
Le ChatBuilding your own app? The connector is yours to use.
You don't need a client to put MyScale 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
1033ms average. Fast in production.
MyScale is checked daily against the live service.
- Fastest day
- 772ms
- Slowest day
- 1482ms
- 14-day trend
- Stable-2%
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.
https://edge.vinkius.com/vk_preview_vWeauVyztoYzGBsy6h9azMYGgJ3R8tQDDZfTvuoy/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — MyScale capabilities are ready to use.
{
"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
Guided setup for Claude? Set up MyScale in Claude and other AIs
Who it's for
Built for the work MyScale owners hand off.
This MCP is built for technical users who need to bridge the gap between AI agents and high-performance vector databases.
- 01
AI Engineers
They use the agent to test search parameters and inspect data distributions.
- 02
Data Scientists
They manage RAG backends and monitor index health in real time.
- 03
Backend Developers
They perform database maintenance and schema updates using natural language.
FAQ
Questions MyScale owners ask.
- 01
How do I connect my MyScale cluster to my AI client?
You subscribe to the MCP on Vinkius and enter your MyScale Cluster URL, Username, and Password. Once connected, your client can immediately start using the available capabilities.
- 02
Can I run standard SQL queries through this MCP?
Yes. You can use the execute_sql_query capability to run arbitrary SQL commands, including SELECT, INSERT, and ALTER, directly on your cluster.
- 03
Does the MCP handle vector similarity search logic?
Yes. The vector_search capability automatically handles the construction of the SQL query and the distance functions for you.
- 04
What kind of vector indices can I manage?
You can create and monitor specialized indices such as MSTG, ScaNN, and HNSW using the index management capabilities.
- 05
How can I check if my database connection is working?
You can use the ping_cluster capability to instantly verify your cluster status and credentials.
- 06
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.
- 07
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.
- 08
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.
Explore
More in Databases
ClickHouse (Vector Search) AI Connector
Manage vector embeddings and SQL via ClickHouse — list databases, execute SQL, and perform high-speed vector s
ViewMongoDB Atlas Vector Search AI Connector
Manage vector storage via MongoDB Atlas — perform similarity searches, query MQL documents, and audit collecti
ViewLucidworks Fusion (AI Search & Discovery) AI Connector
Manage AI-powered search via Lucidworks Fusion — execute semantic queries, index documents, and monitor ML tra
ViewMarqo AI (Vector Search & Embeddings) AI Connector
Manage semantic search via Marqo — execute tensor queries, index JSON documents, and audit vector indices.
View
Suggestions
Oracle Vector DB AI Connector
Run vector similarity searches on Oracle 23ai — execute VECTOR_DISTANCE queries, inspect schemas, list vector
ViewTypesense Vector Search AI Connector
Automate vector similarity searches via Typesense — index documents, manage collections, and execute semantic
ViewMilvus (Open-Source Vector Database) AI Connector
Manage vector storage via Milvus — perform ANN searches, query scalar entities, and audit collections.
Viewpgvector (Vector Database) AI Connector
Run vector similarity searches, manage embedding tables, and build AI-powered retrieval pipelines — all direct
View
Connect MyScale to Claude, Cursor, ChatGPT & more
