TCB MCP. Manage functions, databases, and storage via AI.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Tencent CloudBase TCB lets your AI agent manage your entire serverless backend through natural conversation. It handles functions, NoSQL databases, and cloud storage in one place.
Instead of logging into the Tencent Console and clicking through dashboards, you simply ask your agent to list collections or run a query against active users.
This is for developers who need deep control over their core infrastructure without manual dashboard navigation.
What your AI agents can do
Get environment info
Retrieves essential details about the current TCB environment, including connectivity status and quotas.
Get function metadata
Gets detailed information (like runtime or version) for a specific cloud function.
Invoke cloud function
Executes a specified cloud function using defined inputs to run the core business logic.
Lists all available cloud functions in the environment and retrieves their specific metadata.
Runs a specified cloud function, passing custom data inputs to execute core business logic.
Executes complex search queries against specific database collections and returns the results.
Lists all configured storage buckets and helps audit file resources within your TCB environment.
Retrieves current project details, including active regions and usage quotas for the entire environment.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Tencent CloudBase / 腾讯云开发 TCB: 8 Tools for Backend Orchestration
Use these eight tools to interact with your entire Tencent Cloud infrastructure—from querying NoSQL collections to executing serverless functions and auditing resource quotas.
019d848aget environment info
Retrieves essential details about the current TCB environment, including connectivity status and quotas.
019d848aget function metadata
Gets detailed information (like runtime or version) for a specific cloud function.
019d848ainvoke cloud function
Executes a specified cloud function using defined inputs to run the core business logic.
019d848alist auth users
Retrieves a list of all authenticated user accounts registered in your TCB environment.
019d848alist cloud functions
Lists every cloud function deployed within the current serverless project.
019d848alist collections
Shows all available NoSQL database collections where you store data.
019d848alist tcb buckets
Retrieves a list of all storage buckets configured for your TCB environment.
019d848aquery cloud db
Runs arbitrary search queries against the cloud NoSQL database, returning matching records.
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
Make Your AI Do More
Start with Tencent CloudBase / 腾讯云开发 TCB, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ 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
What you can do with this MCP connector
This server lets your AI agent handle everything related to your TCB backend—functions, databases, and storage—without you having to click through a bunch of dashboards. Instead of logging into the console yourself, you just talk to your agent; it does the heavy lifting.
Checking Your Environment Status: You can start by checking the overall health of your project. The agent uses get_environment_info to pull essential details about the current TCB environment, including connectivity status and usage quotas for the whole thing. It'll also run list_auth_users, giving you a list of every authenticated user account registered in your backend.
Managing Cloud Functions: If you need to audit your serverless code, you can first call list_cloud_functions to get a rundown of every function deployed within the current project. After that, it'll use get_function_metadata to pull detailed specs for any specific function, like its runtime environment or version number. When you need to run actual business logic, you just tell your agent what to do; it executes the code using invoke_cloud_function, passing along custom data inputs so the function runs exactly how you want it to.
Handling NoSQL Data: For database work, the agent first shows you all available collections by running list_collections. Once you know where your data lives, you can run complex searches. The tool query_cloud_db lets you execute arbitrary search queries against the cloud NoSQL database, and it brings back all matching records for you to look at.
Inventorying Storage Assets: To check on your files, you'll use list_tcb_buckets, which pulls a list of every storage bucket configured in your TCB environment. This lets you audit file resources across the entire project without manual navigation.
How TCB MCP Works
- 1 Subscribe to this server on Vinkius.
- 2 Provide your Tencent Cloud credentials: SecretId, SecretKey, Region, and EnvId.
- 3 Call any tool through Claude, Cursor, or your MCP-compatible agent. Your agent handles the connection, authentication, and data retrieval.
The bottom line is that you get a natural language interface to deep cloud infrastructure commands, without ever touching the Tencent console.
Who Is TCB MCP For?
This is for the backend developer who spends too much time in browser consoles. It's for the DevOps engineer who needs to audit resource usage at 2 AM and doesn't want to click through five different dashboards just to check quotas. If your job involves managing serverless backends or NoSQL data, you need this.
Using the agent to audit function metadata (get_function_metadata) before making a deployment, ensuring dependencies are correct.
Running get_environment_info and monitoring quotas in real-time to prevent service outages due to resource limits.
Listing all database collections (list_collections) and executing sample queries (query_cloud_db) for proof-of-concept testing.
What Changes When You Connect
- Audit your entire backend stack instantly. Instead of manually checking the console for function lists or resource quotas, use
list_cloud_functionsandget_environment_infoto get an immediate overview in natural language. - Run complex data queries without writing boilerplate API calls. Use
query_cloud_dbto target specific fields (e.g., 'status=active') across millions of NoSQL records, getting results directly into your chat window. - Test and run functions on demand. Don't wait for a deployment pipeline failure; use
invoke_cloud_functionwith sample data inputs to validate business logic immediately. - Maintain compliance and track users easily. Use
list_auth_usersto pull the current list of active user accounts, which is critical for security audits without navigating user management tabs. - Track your resource usage from one place.
get_environment_infogives you a clear picture of free quota remaining across storage buckets and function invocations, preventing unexpected overages.
Real-World Use Cases
Debugging an intermittent bug.
A user finds that the 'Checkout' feature sometimes fails. Instead of checking logs manually in three different places, they ask their agent to get_function_metadata for the 'CheckoutProcessor' function, then use invoke_cloud_function with test data to replicate and diagnose the failure point immediately.
Onboarding a new team member.
A manager needs to see who has access. They ask their agent to run list_auth_users. The agent executes the tool, provides the list of accounts, and even confirms which roles are associated with those users—all in one conversational step.
Running a nightly data report.
Instead of writing complex SQL scripts or building a dedicated reporting dashboard, the developer asks their agent to list_collections first. Then they use query_cloud_db to pull all 'Order' records from the last 24 hours where 'status' is not 'completed', solving the data retrieval problem immediately.
Checking service health before launch.
A team needs to know if they have enough capacity. They prompt their agent for environment info, triggering get_environment_info. The agent instantly reports on remaining quotas and active regions, ensuring the system won't fail due to resource limits.
The Tradeoffs
Assuming manual API calls are required
Trying to list functions by manually navigating the Tencent Console, remembering specific endpoint paths, and assembling parameters.
→
Just tell your agent: 'List all cloud functions.' It handles list_cloud_functions automatically. You don't need the console.
Over-relying on a single data view
Seeing an error message that says 'Database connection failure,' and then spending an hour checking only the network logs without knowing if the function itself was the issue.
→
First, check environment health with get_environment_info. Then, use list_collections to confirm the database is even visible before trying any queries.
Forgetting resource constraints
Running a large data query using query_cloud_db without checking if the project has enough free storage quota, leading to an unexpected failure and downtime.
→
Always run get_environment_info first. It gives you the necessary visibility into your remaining quotas before any major operation.
When It Fits, When It Doesn't
Use this server when your workflow requires interacting with a complex, structured backend system (like TCB) and you want to avoid manual UI clicks or writing boilerplate API code. Specifically, if you need to list metadata (get_function_metadata), run core logic (invoke_cloud_function), or query specific NoSQL documents (query_cloud_db), this is your tool.
Don't use it if: 1) You only need general documentation lookup (use a standard search engine). 2) Your service is hosted on a completely different platform (e.g., AWS Lambda, which requires a different connector). 3) You just want to read static data that isn't stored in the cloud database. For those cases, you don't need this level of deep integration.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Tencent CloudBase / 腾讯云开发 TCB. 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
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 server provides 8 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Managing backend resources shouldn't require five browser tabs open.
Today, checking your serverless backends means clicking into the Tencent Cloud Console. You switch between 'Functions,' then 'Database,' then 'Storage.' If you need to know what functions exist and how many users are active, you're running a multi-step process that is slow, error-prone, and requires remembering several specific menu paths.
With this MCP server, the task drops back to conversation. You ask your agent to list all cloud functions *and* audit user accounts. The agent handles calling `list_cloud_functions` and `list_auth_users` sequentially, giving you a combined report without you ever leaving your chat window.
The TCB MCP Server gives you full control over backend resources.
Manually querying data means writing specific query strings and hoping the API accepts them. It's a guessing game to find the right collection names or the correct filter syntax for `query_cloud_db`. You waste time debugging schema issues when you should be building features.
Now, your agent handles the complexity of the NoSQL structure. You simply ask: 'What are all active users in the Users collection?' The agent runs the query and returns clean results. It's a massive difference between writing code to read data and just asking for it.
Common Questions About TCB MCP
How do I use the `invoke_cloud_function` tool? +
You ask your agent directly, like: 'Invoke the OrderProcessor function with order ID 123.' The agent handles calling the specific tool and sending the necessary data payload.
Does `query_cloud_db` cover all my database needs? +
It covers standard NoSQL querying. You ask for what you need—like 'all users with status pending'—and it runs the query using your specified collections, letting you retrieve structured data.
What is the difference between `list_cloud_functions` and `get_function_metadata`? +
list_cloud_functions gives you a comprehensive list of all functions deployed. Use get_function_metadata when you already know the name of one function and need specific details about it, like its runtime version.
Can I check my resource quota with TCB MCP Server? +
Yes. You use get_environment_info. This tool pulls your current usage metrics for storage buckets and function invocations, keeping you ahead of potential overages.
When I run `list_auth_users`, what specific security data can my agent pull about our user base? +
The tool returns a list of authenticated users registered in your TCB environment. For each user, you get key identifiers and account metadata, allowing your AI client to audit who has access without needing direct console navigation.
If I use `invoke_cloud_function`, what happens if the function fails or throws an error? +
The agent reports the outcome of the invocation directly. If a function fails, the response includes specific error messages and status codes. This lets you debug failed cloud logic without manually checking logs.
Does `list_tcb_buckets` provide details on file size or how many files are in the bucket? +
Yes, it provides metadata for each listed storage bucket. You get information about the resources contained within those buckets, including counts and overall usage metrics, which is essential for auditing large data sets.
What information does `get_environment_info` provide to verify my connection stability? +
It provides a summary of your TCB instance, confirming the active region (like 'ap-shanghai') and operational status. This helps ensure your AI client is connected to the correct, stable cloud environment.
How do I find my Tencent Cloud SecretId and SecretKey? +
Log in to the Tencent Cloud Console, navigate to [Access Management] -> [API Key Management] to find or generate your unique SecretId and SecretKey.
What is an EnvId? +
An EnvId is the unique identifier for a specific CloudBase environment (e.g., development or production). You can find it in the TCB Environment Overview section of the console.
Does this server handle TC3-HMAC-SHA256 signatures? +
Yes! The server automatically calculates the required Signature V3 (TC3-HMAC-SHA256) for every request using your provided SecretKey, ensuring high security for your serverless backend orchestration.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Platform.ly
Grow your business with marketing automation, CRM, and analytics connected in one platform that shows what drives revenue.
Reportei
Generate marketing performance reports from Google, Facebook, and Instagram data in minutes for client presentations.
Snowflake
Bring your absolute data cloud into your AI editor. Execute queries, list warehouses, and map complex schemas natively.
You might also like
Cheddar
Manage usage-based billing and subscriptions via Cheddar — track usage, monitor invoices, and manage customers directly from any AI agent.
VSPN Esports DB
Automate esports intelligence via VSPN — fetch live tournament brackets, deep player telemetry, and team rosters directly from any AI agent.
Mux
Manage video assets and live streams via Mux — create assets and track performance directly from your AI agent.