SenseCore Platform MCP Server
Orchestrate SenseCore AI services — manage models, trigger chat completions, and handle compute resources directly from any AI agent.
Ask AI about this MCP Server
Vinkius AI Gateway supports streamable HTTP and SSE.
Works with every AI agent you already use
…and any MCP-compatible client
What is the SenseCore Platform MCP Server?
The SenseCore Platform MCP Server gives AI agents like Claude, ChatGPT, and Cursor direct access to SenseCore Platform. Orchestrate SenseCore AI services — manage models, trigger chat completions, and handle compute resources directly from any AI agent. Powered by the Vinkius AI Gateway — no API keys, no infrastructure, connect in under 2 minutes.
SenseCore Platform MCP Server: see your AI Agent in action
Built-in capabilities (11)
chat_completions
Send a message to a SenseCore large language model
create_assistant
Define a new AI assistant
create_message
Add a message to a thread
create_run
Execute an assistant on a thread
create_thread
Initialize a new conversation thread
get_assistant_details
Get complete configuration for an assistant
get_run_status
Check the status of an active assistant run
list_assistants
List all configured assistants
list_files
List uploaded files
list_messages
Retrieve the message history of a thread
list_models
List all available SenseNova models
What this connector unlocks
Connect your AI agents to the SenseCore Platform, the industrial-grade AI infrastructure by SenseTime. This MCP provides 10 tools to manage advanced foundation models, orchestrate large-scale chat completions, and monitor high-performance compute resources programmatically.
What you can do
- SenseChat Interaction — Trigger chat completions with SenseTime's foundation models using persistent context and history
- Model Intelligence — List all available foundation models and retrieve granular technical specifications for each version
- Resource Management — Monitor compute node availability and track quota consumption across your organizational projects
- Service Monitoring — Check real-time health and latency metrics for deployed model services
- Async Operations — List and track the status of long-running training or inference tasks on the SenseCore infrastructure
How it works
1. Subscribe to this server
2. Log in to the [SenseCore Console](https://platform.sensecore.cn/)
3. Navigate to API Management to obtain your API Key and Secret Key
4. Identify your Organization ID and the target Project ID
5. Insert your credentials into the fields below to start managing your SenseTime AI infrastructure.
Who is this for?
- Enterprise AI Developers — automate the integration of SenseTime's industrial models into custom applications
- Infrastructure Engineers — monitor GPU cluster utilization and model service health programmatically
- Machine Learning Ops — orchestrate and track large-scale inference tasks on the SenseCore platform
Frequently asked questions
Give your AI agents the power of SenseCore Platform
Access SenseCore Platform and 2,500+ MCP servers — ready for your agents to use, right now. No glue code. No custom integrations. Just plug Vinkius AI Gateway and let your agents work.