How do I connect this MCP to my AI client?

You subscribe to the MCP on Vinkius and then connect your preferred client like Claude, Cursor, or Windsurf. Vinkius handles the hosting and credential management for you.

What credentials do I need?

You will need your API Key and Secret Key from the SenseCore Console, along with your Organization ID and Project ID.

Can I monitor GPU usage?

Yes, the MCP allows you to monitor compute node availability and track quota consumption across your projects.

Which models are supported?

The MCP provides access to the SenseNova model family, including SenseChat, SenseVision, and SenseAudio.

Is this for managing individual chats or large tasks?

It handles both. You can manage individual conversation threads or track the status of large-scale, long-running inference and training tasks.

Can I automatically list all available models in my SenseCore project?

Yes! Use the list_models capability. Your agent will retrieve a complete list of all SenseTime foundation models and specialized variants currently active in your account.

How do I check the health status of my deployed model services?

Use the get_service_health capability with the specific Service ID. The agent will return real-time metrics on availability, throughput, and average latency.

Can I monitor GPU resource utilization via the AI agent?

Yes! The get_resource_usage capability retrieves granular metrics on compute node utilization and remaining quota for your specific project environment.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect SenseCore Platform 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. Control industrial AI infrastructure from your AI client.

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.

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.

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 · 11 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 11 available through SenseCore Platform.

01
Create run
This capability executes an assistant on a specific thread.
02
Create thread
Use this to initialize a new conversation thread.
03
Get run status
This capability checks the current status of an active assistant run.
04
Create assistant
This capability defines a new AI assistant.

Capability set02 / 03

05-08

4 capabilities in this set.

Part of 11 available through SenseCore Platform.

05
Get assistant details
Use this to get the full configuration for a specific assistant.
06
List assistants
This capability lists all your configured assistants.
07
List messages
This capability retrieves the message history from a thread.
08
List models
This capability lists all available SenseNova models.

Capability set03 / 03

09-11

3 capabilities in this set.

Part of 11 available through SenseCore Platform.

09
List files
Use this to see a list of your uploaded files.
10
Create message
This capability adds a new message to an existing thread.
11
Chat completions
This capability sends a message to a SenseCore large language model.

Real work

What teams actually run

Automated Model Testing

Your agent can quickly cycle through different SenseNova models to compare outputs.

Infrastructure Monitoring

An engineer can ask their agent for the health status of specific GPU services.

Conversational AI Management

Developers can programmatically manage assistant threads and message histories.

Resource Quota Tracking

Teams can monitor how much compute quota their projects are consuming.

Automate a task

Put SenseCore Platform 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

SenseCore Platform 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.

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

You don't need a client to put SenseCore Platform 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

866ms average. Fast in production.

SenseCore Platform is checked daily against the live service.

Daily averagePeak 4419ms

Oct 3Today

Fastest day: 709ms
Slowest day: 4419ms
14-day trend: Slowing+382%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 11 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 SenseCore Platform, so you can see the experience inside your AI.

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

SenseCore Platform Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_WGerX5EoMF3cLaPImYP34A8UFoRYYgmvQyPkRFRu/mcp

Claude 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 — SenseCore Platform capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "sensecore-platform-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_WGerX5EoMF3cLaPImYP34A8UFoRYYgmvQyPkRFRu/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 SenseCore Platform in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work SenseCore Platform owners hand off.

This MCP is built for technical teams managing large-scale AI deployments on SenseTime infrastructure.

01
Enterprise AI Developers
They automate the integration of SenseTime models into their own applications.
02
Infrastructure Engineers
They use the agent to monitor GPU cluster utilization and service health.
03
MLOps Engineers
They orchestrate and track large-scale inference tasks on SenseCore.

FAQ

Questions SenseCore Platform owners ask.

01
How do I connect this MCP to my AI client?
You subscribe to the MCP on Vinkius and then connect your preferred client like Claude, Cursor, or Windsurf. Vinkius handles the hosting and credential management for you.
02
What credentials do I need?
You will need your API Key and Secret Key from the SenseCore Console, along with your Organization ID and Project ID.
03
Can I monitor GPU usage?
Yes, the MCP allows you to monitor compute node availability and track quota consumption across your projects.
04
Which models are supported?
The MCP provides access to the SenseNova model family, including SenseChat, SenseVision, and SenseAudio.
05
Is this for managing individual chats or large tasks?
It handles both. You can manage individual conversation threads or track the status of large-scale, long-running inference and training tasks.
06
Can I automatically list all available models in my SenseCore project?
Yes! Use the list_models capability. Your agent will retrieve a complete list of all SenseTime foundation models and specialized variants currently active in your account.
07
How do I check the health status of my deployed model services?
Use the get_service_health capability with the specific Service ID. The agent will return real-time metrics on availability, throughput, and average latency.
08
Can I monitor GPU resource utilization via the AI agent?
Yes! The get_resource_usage capability retrieves granular metrics on compute node utilization and remaining quota for your specific project environment.

Explore

More in Industry Titans

Connect SenseCore Platform to Claude, Cursor, ChatGPT & more

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

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Create run

Create thread

Get run status

Create assistant

05-08

Get assistant details

List assistants

List messages

List models

09-11

List files

Create message

Chat completions

What teams actually run

Automated Model Testing

Infrastructure Monitoring

Conversational AI Management

Resource Quota Tracking

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

SenseCore Platform Connector

Claude Desktop

Enterprise AI Developers

Infrastructure Engineers

MLOps Engineers

How do I connect this MCP to my AI client?

What credentials do I need?

Can I monitor GPU usage?

Which models are supported?

Is this for managing individual chats or large tasks?

Can I automatically list all available models in my SenseCore project?

How do I check the health status of my deployed model services?

Can I monitor GPU resource utilization via the AI agent?

CrewAI Platform AI Connector

Kubernetes Architecture Prover AI Connector

LiteLLM (LLM Proxy & Spend Tracking) AI Connector

LangSmith (LLM Observability & Hub) AI Connector

Suggestions

Langfuse (LLM Tracing & Evals) AI Connector

Akash Network (Decentralized GPU & Cloud API) AI Connector

Vast.ai (GPU Rental Cloud API) AI Connector

Shunwang Tech AI Connector