An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Vald to ChatGPT, Claude and Gemini

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. Bring massive, high-speed similarity search to your AI agent.

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 · 6 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-03

3 capabilities in this set.

Part of 6 available through Vald.

  1. 01

    Update vector

    This capability modifies an existing vector in your Vald index. You provide the specific ID and the new vector array to overwrite the old data.

  2. 02

    Delete vector

    This capability permanently removes a vector from the Vald index. Use this when you need to purge specific items from the cluster.

  3. 03

    Get engine info

    This capability pulls operational data and health status from the Vald engine. It's how you check if your cluster is running correctly.

Capability set02 / 02

04-06

3 capabilities in this set.

Part of 6 available through Vald.

  1. 04

    Get vector details

    This capability retrieves the raw vector data for a specific ID. Use it to inspect the exact float values of an embedding.

  2. 05

    Insert vector

    This capability adds a new vector to the Vald index. You'll need to provide a unique ID and the vector as a JSON array.

  3. 06

    Search vectors

    This capability performs a nearest neighbor similarity search. You provide a query vector to find the most relevant matches in the index.

Real work

What teams actually run

01

RAG Pipeline Management

Keep your vector index updated with new data by having your agent insert vectors directly.

02

Rapid Prototyping

Test how different embedding models affect search results by updating vectors through the agent.

03

System Troubleshooting

Quickly diagnose cluster issues by asking for engine health and node details.

04

Data Cleaning

Remove outdated or incorrect embeddings from your distributed index using simple commands.

Automate a task

Put Vald 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

Vald 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 Vald 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

868ms average. Fast in production.

Vald is checked daily against the live service.

Daily averagePeak 1195ms
Oct 3Today
Fastest day
667ms
Slowest day
1195ms
14-day trend
Slowing+41%

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 Vald, so you can see the experience inside your AI.

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

Vald Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_LwabvjFRxR6SLDMyq0Lg8wB1fanBWcNw0aRuqiDM/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 — Vald capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "vald-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_LwabvjFRxR6SLDMyq0Lg8wB1fanBWcNw0aRuqiDM/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 Vald in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Vald owners hand off.

This MCP is built for engineers working with large-scale embeddings and distributed systems.

  • 01

    Machine Learning Engineers

    They use the agent to test and visualize embedding changes against live Vald instances.

  • 02

    Data Scientists

    They run top-k semantic queries from their IDE to validate search recall.

  • 03

    DevOps Engineers

    They check engine health and cluster info to respond to anomalies.

  • 04

    Backend Developers

    They purge corrupted vectors or update records without using database terminals.

FAQ

Questions Vald owners ask.

  • 01

    How do I connect my AI client to Vald?

    You subscribe to the MCP on Vinkius and enter your Vald Gateway Host address. Once connected, your client can immediately start using the available capabilities.

  • 02

    Can I use this with Cursor or VS Code?

    Yes. This MCP works with any compatible client, including Cursor, Windsurf, and VS Code.

  • 03

    What kind of searches can I perform?

    You can perform approximate nearest neighbor (ANN) similarity searches using query vectors provided to the agent.

  • 04

    Is it possible to delete data?

    Yes, you can use the delete capability to permanently remove a vector from the index, but this action cannot be undone.

  • 05

    Can I monitor my cluster health?

    Yes. You can ask your agent to retrieve operational information and health status for your Vald deployment.

  • 06

    Can my AI agent do a semantic search across my vector database?

    Yes! Provided you supply the embedded query vector, your agent can issue a vector search command to the Vald Engine. It will rapidly scan millions of indexes natively using its ANN algorithms and return the top-K closest neighbors associated with your data.

  • 07

    How do I ensure my Vald cluster is healthy right from my CLI?

    Skip complex diagnostics loops. Instruct your agent to get Vald internal engine info. It will interface directly via gRPC/REST and pull down cluster metrics including operational status, agent versions, and basic diagnostic health. This is vital for MLOps managing production RAG pipelines needing constant reassurance.

  • 08

    Can I permanently purge a corrupted vector embedding?

    When a document becomes stale in your knowledge base, you must remove its embedding. Ask the AI agent: permanently delete vector ID 'doc-xyz'. Using the removeVector capability, it targets your cluster and ensures the outdated semantic representation is fully expunged without risking other node data.

Explore

More in Databases

Suggestions

Connect Vald to Claude, Cursor, ChatGPT & more