Tencent START MCP for AI. Automate game session and worker management.

Q: How do I check if a user can play right now using Tencent START MCP Server?

Run getconcurrentuserinfo to see how many users are active. If that number is close to the limit, run getcapacitylimit first. This tells you your current operational boundaries.

Q: Is there a tool in Tencent START MCP Server to handle scaling?

Yes, use modifycapacitylimit. This tool updates the maximum user count for a game ID when demand requires it. It's how you prevent service slowdowns.

Q: What's the difference between listworkers and getworkerinfo?

listworkers gives you an inventory—a broad overview of all worker instances and their general status. getworkerinfo is specific; it drills down to get detailed metrics for one single, known user's worker.

Q: How do I start a game session programmatically?

You use the createsession tool. This initializes the cloud gaming instance and makes it ready for the user to connect to.

Q: When should I use stopgame versus stoppublishstream?

stopgame fully terminates a game instance, releasing all associated resources and workers. Use stoppublishstream, however, if you only need to cut the video feed for a specific user while keeping the underlying worker active.

Q: What does the listgames tool provide about the Tencent GS platform?

The listgames tool returns a catalog of all available game IDs on the platform. This is essential for determining which titles you can target before attempting to monitor or create sessions.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

Tencent START MCP Server connects your AI agent directly to cloud gaming operations. It lets you manage game server sessions, check worker availability, and adjust user capacity limits for Tencent START Cloud Gaming.

Use it to orchestrate complex scaling tasks without writing boilerplate API calls.

What your AI can do

Create session

Starts a new cloud gaming instance for a user.

Get capacity limit

Checks the maximum allowed concurrent users for any given game ID.

Get concurrent user info

Retrieves the current number of active, connected users for a specific game.

+ 8 more capabilities included

Start and Stop Game Sessions

Initialize a cloud gaming session using create_session or release an instance completely with stop_game.

Monitor Worker Status

Get detailed worker information for specific users (get_worker_info) and list the status of all available workers (list_workers).

Check Concurrency Limits

Verify current user capacity using get_capacity_limit or check active concurrent usage with get_concurrent_user_info.

Scale Capacity On Demand

Adjust the maximum number of simultaneous users for a game ID by calling modify_capacity_limit.

Lock Resources

Reserve a cloud gaming instance for a user before they need it, preventing race conditions using try_lock_worker.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

Tencent START: 11 Tools for Game Session & Worker Control

Use these 11 tools to manage the full lifecycle of cloud gaming instances—from listing games to modifying concurrency limits.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using Tencent START on Vinkius

Create Session

Starts a new cloud gaming instance for a user.

Get Capacity Limit

Checks the maximum allowed concurrent users for any given game ID.

Get Concurrent User Info

Retrieves the current number of active, connected users for a specific game.

Get Worker Info

Fetches detailed status information for a worker associated with a particular user...

List Games

Lists all available game titles running on the Tencent GS platform.

List Workers

Gathers a list of all operational cloud gaming worker instances and their status.

Modify Capacity Limit

Updates the maximum concurrent user limit for a specific game title when scaling is needed.

Stop Game

Ends an active game session and releases the underlying worker resource back to the...

Stop Publish Stream By Action

Stops the video stream using an explicit action code to ensure clean termination.

Stop Publish Stream

Stops the video stream feed for a specified user.

Try Lock Worker

Attempts to reserve a worker instance for a user, preventing it from being allocated...

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The Tencent START integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "tencent-start": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the Tencent START tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"tencent-start": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with Tencent START, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,100+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Tencent START. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 11 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Managing game resources used to mean logging into three different dashboards.

Today, managing cloud gaming capacity is a mess. You have to check the main dashboard for active workers, then jump to the resource allocation tab to see if you're hitting your concurrency limits. Finally, you might open a third window just to confirm who exactly is assigned which worker ID. It takes ten minutes and three different logins.

With this MCP Server, all that information collapses into one API call. You run `list_workers` or `get_concurrent_user_info`, and your agent gives you the full status in a single response. That's everything you need to know right there.

Tencent START MCP Server: Control sessions with simple commands.

The biggest headaches are scaling and cleanup. Before, if traffic spiked, you were stuck until an admin manually increased the concurrency limit via a console GUI. If users logged out, sometimes the worker was left hanging—a 'ghost' resource consuming capacity.

Now, your agent handles it automatically. Need more room? Call `modify_capacity_limit`. A session ends? Run `stop_game` and consider it done. The system adjusts instantly.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

Tencent START MCP Server gives your AI agent direct command over cloud gaming operations for Tencent START Cloud Gaming. You'll manage entire game server sessions and orchestrate resource scaling without writing a single line of boilerplate API code. It handles everything from initial user connection to shutting down resources when the action is done.

Managing Game Sessions

You can initiate a new gaming session for any user using create_session. When a player is done, call stop_game to end the active instance and release its worker resource back into the pool. If you only need to cut the video feed without killing the whole game process, use stop_publish_stream or stop_publish_stream_by_action to stop the stream by specific action code.

Monitoring Infrastructure Status

To understand what's running, start with list_games, which gives you a rundown of every game title currently available on the Tencent GS platform. You can then check usage metrics: call get_concurrent_user_info to retrieve the current number of active users connected to a specific game ID. To see how close you are to hitting your limits, use get_capacity_limit, which checks the maximum allowed concurrent users for that same game ID.

For deeper status checks, list_workers gives you a full inventory and operational status of every cloud gaming worker instance out there. If you need details on one specific user's machine, get_worker_info fetches detailed status information using the associated user ID.

Scaling and Resource Control

When player demand spikes, you don't want your service to crash. You can adjust the maximum number of simultaneous users for any game title by calling modify_capacity_limit, which updates that hard cap when scaling is necessary. Before a user connects, it’s smart to reserve their spot; use try_lock_worker to attempt reserving a worker instance for a specific user, keeping it locked down so no other process allocates it elsewhere.

If you need to know what games are even available before running any checks, start with list_games.

Operational Flow

You can execute complex operational sequences through this single server connection. You'll first use list_games to identify the target title, then check current usage via get_concurrent_user_info, and verify the hard limit with get_capacity_limit. If you determine scaling is required, call modify_capacity_limit. Once capacity is set and workers are available (which you monitor using list_workers), you can execute a session start with create_session or pre-reserve resources by calling try_lock_worker for mission-critical users.

When the user connects, their dedicated worker status comes through via get_worker_info. To ensure clean shutdown, you'll use stop_game, and if needed, follow up with a stream stop using either stop_publish_stream or stop_publish_stream_by_action to guarantee the video feed terminates cleanly. You won't need to write custom logic for these transitions; this server handles it all.

Built · Hosted · Managed by Vinkius Tencent START MCP Server - Cloud Gaming Orchestration

Server ID 019d848a-6403-723f-91ce-1245809a610d

Vinkius Inspector

Compliance Grade A+

Score 98.33/100

Report View Report ↗

Here's how it actually works

The bottom line is: you provide the credentials once, and then your agent handles all the complex API calls needed to run game operations.

First, subscribe to the server and log in via your preferred AI client. Then, navigate to the Tencent Cloud Console to generate a SecretId and SecretKey for access management.

Next, you'll enable the Cloud Gaming (GS) service and input your credentials and desired region into the MCP fields. This authenticates your agent with the gaming platform.

Finally, your AI client uses the tools—like list_games or get_worker_info—to read the current state of the system and execute commands to manage sessions.

Who is this actually for?

This tool is for platform operators, infrastructure engineers, and backend developers who handle live cloud gaming environments. If you're tired of manually checking dashboards every five minutes just to see if a server pool is running low, this is built for you.

Platform Operations Engineer

Uses list_workers and get_concurrent_user_info to monitor resource utilization across multiple game titles in real-time.

Game Backend Developer

Integrates session management by calling create_session when a user signs up, and stop_game when they log out.

SRE (Site Reliability Engineer)

Manages scaling events by running modify_capacity_limit immediately after analyzing traffic spikes using get_capacity_limit.

What Changes When You Connect

Stop manually checking capacity. Use get_capacity_limit to instantly see if you're hitting user limits, preventing unexpected service outages before they happen.

Manage player flow with precision. You can lock a resource using try_lock_worker, ensuring that when a user connects, the worker is ready and won't be assigned elsewhere.

Scale without downtime. When traffic spikes, run modify_capacity_limit to raise the concurrency ceiling immediately, accommodating sudden bursts of players.

Keep costs down by cleaning up. Use stop_game after a session ends; it reliably releases the worker instance back into the pool for reuse.

Gain full visibility. Running list_workers gives you an immediate inventory count and status (Occupied, Idle, Maintenance) across your entire fleet.

See it in action

01 01

Handling a Peak Load Event

A major game launch causes traffic to spike past the default capacity. Instead of waiting for manual alerts, the agent runs get_concurrent_user_info and sees the limit is breached. It immediately calls modify_capacity_limit to raise the ceiling, stabilizing service before users complain.

02 02

User Login Flow Orchestration

A user hits 'Play'. The agent first runs try_lock_worker for that specific user ID. If successful, it calls create_session. This sequence ensures the worker is reserved before resources are consumed.

03 03

Debugging a Disconnected Client

A client suddenly drops connection but isn't showing up in usage metrics. The agent checks get_worker_info for that user ID, confirming the last known status and whether the worker was properly released using stop_game.

04 04

Pre-Launch Readiness Check

The ops team needs to know if the platform is ready. They run list_games to confirm all titles are listed, then use get_worker_info and list_workers to verify that a sufficient number of workers are in 'Idle' status.

The honest tradeoffs

Guessing Capacity

Anti-pattern

Writing code that just assumes there's enough capacity because the last check was fine, leading to connection failures during unexpected traffic spikes.

The Fix

Always run get_capacity_limit before attempting large-scale operations. If the limit is too low, use modify_capacity_limit first.

Forgetting Cleanup

Anti-pattern

Calling create_session for a temporary test and then just abandoning the process, leaving the worker instance locked and unavailable.

The Fix

When you're done testing or when the user logs out, always use stop_game to guarantee the resource is released back into the pool.

Race Conditions

Anti-pattern

Multiple background services trying to assign a worker to different users at the same time, leading to unpredictable assignment errors.

The Fix

Use try_lock_worker first. This atomic operation reserves the resource for your user before any other service can touch it.

When It Fits, When It Doesn't

Use this MCP Server if your core problem is operational control over live cloud gaming resources (e.g., 'Is there a worker available? Can I increase the limit right now?'). The tools are designed to manage resource state: locking, starting, stopping, and measuring capacity.

Don't use it if you need pure analytics or business logic that doesn't touch infrastructure. If your goal is, 'What was the average player spending last month?' or 'How many users registered yesterday?', then this tool is overkill; you need a dedicated database query endpoint instead of list_games.

If you only need to list available games, run list_games. But if you need to act on that data—like creating a session for one of those listed games—you'll need the full suite.

Questions you might have

How do I check if a user can play right now using Tencent START MCP Server? +

Run get_concurrent_user_info to see how many users are active. If that number is close to the limit, run get_capacity_limit first. This tells you your current operational boundaries.

Is there a tool in Tencent START MCP Server to handle scaling? +

Yes, use modify_capacity_limit. This tool updates the maximum user count for a game ID when demand requires it. It's how you prevent service slowdowns.

What's the difference between list_workers and get_worker_info? +

list_workers gives you an inventory—a broad overview of all worker instances and their general status. get_worker_info is specific; it drills down to get detailed metrics for one single, known user's worker.

How do I start a game session programmatically? +

You use the create_session tool. This initializes the cloud gaming instance and makes it ready for the user to connect to.

What credentials do I need to use the `try_lock_worker` tool? +

You must provide a valid SecretId, SecretKey, and Region for authentication. These are generated in your Tencent Cloud Console after enabling the Cloud Gaming (GS) service. Your AI client uses these keys to authorize session locking requests.

When should I use `stop_game` versus `stop_publish_stream`? +

stop_game fully terminates a game instance, releasing all associated resources and workers. Use stop_publish_stream, however, if you only need to cut the video feed for a specific user while keeping the underlying worker active.

What does the `list_games` tool provide about the Tencent GS platform? +

The list_games tool returns a catalog of all available game IDs on the platform. This is essential for determining which titles you can target before attempting to monitor or create sessions.

How do I ensure I have the right parameters for `modify_capacity_limit`? +

The tool requires two main inputs: a specific game ID and the new maximum concurrency limit. You must know both values to successfully update the capacity ceiling for that particular title.

Can I automatically list all available games on the platform? +

Yes! Use the list_games tool. It will retrieve metadata for all configured cloud games, including their names and unique identifiers.

How do I check the status of my cloud gaming workers? +

Use the list_workers tool. It returns the availability and current operational state of all server instances allocated to your account.

Can I dynamically modify the concurrency limit for a game? +

Yes! Use the modify_capacity_limit tool with the target Game ID and the new maximum concurrent user count to scale your capacity.

Connect to your AI in seconds.

Create session

Get capacity limit

Get concurrent user info

Tencent START: 11 Tools for Game Session & Worker Control

Make your AI actually useful.

Create Session

Get Capacity Limit

Get Concurrent User Info

Get Worker Info

List Games

List Workers

Modify Capacity Limit

Stop Game

Stop Publish Stream By Action

Stop Publish Stream

Try Lock Worker

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

Managing game resources used to mean logging into three different dashboards.

Tencent START MCP Server: Control sessions with simple commands.

What your AI can actually do with this

Managing Game Sessions

Monitoring Infrastructure Status

Scaling and Resource Control

Operational Flow

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

Handling a Peak Load Event

User Login Flow Orchestration

Debugging a Disconnected Client

Pre-Launch Readiness Check

The honest tradeoffs

Guessing Capacity

Forgetting Cleanup

Race Conditions

When It Fits, When It Doesn't

Questions you might have