Tencent Yuanqi MCP for AI. Manage Agents, Documents, and Usage Tracking.

Q: How do I check if my uploaded file is ready for use with chat?

You must call getfilestatus first. This tool checks the document's processing state, letting you know exactly when it moves from 'uploaded' to 'ready,' which prevents your agent from failing.

Q: What should I use if I need a list of all available assistants?

Use listassistants. It gives you an immediate, machine-readable inventory of every assistant ID in your workspace. This is better than manually navigating the UI.

Q: Does the chat tool handle file context automatically?

No, it doesn't. You must use uploadfile and confirm readiness with getfilestatus before calling the chat tool to ensure the agent uses your desired documents.

Q: How can I track my token usage programmatically?

Call getusage. This returns a direct report on your current API quota and consumption, letting you build limits into your application logic before they hit zero.

Q: What command should I use to list every document uploaded using listfiles?

listfiles returns the IDs and names of every document linked to your account. You can run this tool for an audit of all knowledge bases available.

Q: If a document is obsolete, how do I permanently remove it with deletefile?

The deletefile tool removes the file ID you provide from your knowledge base. Note that this action is irreversible; double-check the file ID first.

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 Yuanqi MCP Server manages specialized AI agents and knowledge bases. Use this server to chat with published assistants, upload documents for RAG context, monitor API usage, or check file processing status directly from your agent framework.

What your AI can do

Chat

Sends a message to a specific Tencent Yuanqi assistant ID and receives the conversational response.

Get file status

Checks the current processing status of an uploaded file to see if it's ready for use in RAG.

List files

Outputs a list of all documents currently stored and managed within your knowledge base.

+ 4 more capabilities included

Interact with AI Assistants

You can send messages to published agents and track the conversation context using the chat tool.

Control Document Lifecycle

The server lets you upload files (upload_file), list them (list_files), or delete them (delete_file) from your knowledge base.

Track File Processing Status

Use get_file_status to monitor if a document is finished being indexed and ready for agent use.

Manage Agent Metadata

Retrieve detailed configuration or basic information about any existing assistant with get_assistant_info.

Monitor API Usage

Check your current token consumption and remaining quota using the get_usage tool, which is critical for billing and planning.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

Tencent Yuanqi MCP Server: 9 Tools for Agent & File Management

Use these nine tools to automate agent interactions, handle document lifecycles, and monitor system performance within your AI client.

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 Yuanqi on Vinkius

Chat

Sends a message to a specific Tencent Yuanqi assistant ID and receives the conversational response.

Get File Status

Checks the current processing status of an uploaded file to see if it's ready for...

List Files

Outputs a list of all documents currently stored and managed within your knowledge...

Upload File

Sends a document to the Yuanqi platform so it can be processed and used by agents...

Delete File

Removes an uploaded file from your account's knowledge base documents.

Get Assistant Info

Retrieves detailed metadata and configuration settings for a specified assistant ID.

Get File Info

Fetches general metadata, like file name or size, for a specific uploaded document.

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 Yuanqi 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-yuanqi": {
    "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 Yuanqi 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-yuanqi": {
  "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 Yuanqi, 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 Yuanqi. 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 7 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Managing documents for agents shouldn't require five different tabs and three manual checks.

Today, if you want an agent to answer based on a new report, the workflow is messy. You upload the document in one place; then, you have to switch tabs to check its status—is it indexed? If not, you wait and manually refresh until it says 'ready.' Finally, you copy the ID over to your chat script.

With this MCP server, that whole dance disappears. You call `upload_file` once. Your agent then calls `get_file_status`. It waits programmatically until the status is confirmed. When it's ready, *then* your agent executes `chat`, guaranteeing the response uses fresh, indexed data.

Tencent Yuanqi MCP Server: Control assistant interactions and file access.

Before this server, getting a full picture of an AI agent meant guessing which ID to use or manually looking up its configuration parameters. If you wanted to know if the bot supported external context, you'd be stuck clicking through documentation pages.

Now, you just call `get_assistant_info`. The API returns all the metadata you need—the name, the creator, and the specific capabilities. It makes building reliable, automated agent pipelines straightforward.

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

This MCP connects your AI client directly to Tencent Yuanqi, giving you nine specific tools to manage specialized agents and handle knowledge documents. You're talking to an intelligent agent platform powered by the Hunyuan model, and these tools let you control everything from conversation context to raw data lifecycle.

To interact with published assistants, you use chat; this sends a message to a specific Tencent Yuanqi assistant ID and immediately returns the conversational response. If you're building complex flows that require tracking history, it handles those persistent context sessions for you.

When you need to manage your knowledge base—the stuff your agents read from—you first use upload_file to send a document to the Yuanqi platform; this gets the file processed and ready for agent consumption. Once uploaded, you can list all stored documents using list_files, which outputs an inventory of everything currently in your knowledge base.

If that document needs to be removed later, you use delete_file to take it out.

Since agents need context before they're useful, you often have to wait for the uploaded files to get indexed. That's where get_file_status comes in; it checks if a document is finished being processed and ready for actual RAG use. You also can check basic file details—like its name or size—by calling get_file_info.

To manage the agents themselves, you first get an overview of what's available by running list_assistants, which retrieves a full list of every assistant you've created in your account. For deeper technical dives, get_assistant_info pulls detailed metadata and configuration settings for any specific assistant ID. This gives you granular control over how those agents function.

Lastly, when you're running these tools frequently, you gotta watch the billing. The get_usage tool returns a clear report showing your API token consumption and what quota limits you still have remaining. You can also check the system status by retrieving detailed metadata about any specific assistant ID using get_assistant_info.

These tools let you control the entire document lifecycle—uploading, listing, deleting, checking status, and getting basic file info—while also letting you chat with agents, list all available agents, and track your usage right from your agent framework. You're running a tight operation here; this server makes sure every step of the way is accounted for.

Built · Hosted · Managed by Vinkius Tencent Yuanqi MCP Server - Manage AI Agents & RAG

Server ID 019d848b-9f16-71c0-9a78-eb05cd74a0e1

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

Who is this actually for?

This tool is for the developer who needs to integrate specialized, high-performance Chinese-native AI agents into a larger application. If you're tired of building manual workflows just to check if a document has finished indexing or to manually list every available assistant, this is for you.

AI Developer

You use the server to programmatically automate document ingestion and reliably test agent responses within your custom application.

Knowledge Manager

You maintain dynamic, complex knowledge bases across multiple specialized agents by systematically uploading, listing, and tracking documents.

Product Architect

You integrate high-performance, production-ready AI components into a product while ensuring you can programmatically track usage quotas (get_usage) and manage agent lifecycles.

What Changes When You Connect

Stop guessing if a document is indexed. Use get_file_status to confirm real-time processing status before an agent attempts to read it.

Never lose track of your agents. With list_assistants, you get a clear inventory, letting you quickly select the right assistant ID for chat or development calls.

Keep costs predictable. The get_usage tool lets you monitor API token consumption programmatically, so you don't hit an unexpected quota wall mid-run.

Build full knowledge graphs. You can use upload_file to ingest source materials and then call chat using those files as context for deep agent responses.

Clean up old data. Need to remove a document from the system? Use delete_file instead of relying on manual dashboard deletion.

Get full control over your environment. The get_assistant_info tool lets you pull metadata, ensuring your application knows exactly what parameters an assistant requires.

See it in action

01 01

The Agent needs context before answering.

A user asks a question that requires company specs. Instead of just calling chat, your agent first calls upload_file with the 'specs.pdf'. Then, it waits for the document to process (checking via get_file_status) and finally executes chat using the newly indexed context. This ensures accurate answers every time.

02 02

Auditing a production agent's behavior.

A product team needs to know if they are close to hitting their usage limit. They run an API call that executes get_usage first, checking the quota. This prevents service interruption and allows them to scale up before users even notice a slowdown.

03 03

Debugging agent configuration.

A developer is debugging why one specialized bot isn't responding correctly. They use list_assistants to verify the correct ID, then call get_assistant_info for that ID. This confirms all parameters are set up right before they attempt a test chat.

04 04

Maintaining data hygiene.

A knowledge manager finds old, irrelevant documents in the system. They use list_files to see everything stored, then systematically call delete_file on every document that shouldn't be indexed anymore.

The honest tradeoffs

Assuming file readiness.

Anti-pattern

An agent tries to run a query or chat immediately after calling upload_file, assuming the data is instantly available for retrieval. This results in vague, incorrect answers because the document hasn't finished indexing.

The Fix

Always check the status first. After calling upload_file with a new document, your agent must call get_file_status. Wait until the server confirms the file is 'processed' or 'ready' before attempting to use it in any chat function.

Ignoring API limits.

Anti-pattern

Running a large-scale test suite of agent interactions without checking usage. This rapidly consumes tokens, leading to an unexpected quota failure and halting the entire test run midway through.

The Fix

Build checks into your workflow. Before running any batch of calls (like multiple chat calls), start by calling get_usage. This gives you a clear picture of available resources.

Relying on UI for management.

Anti-pattern

The developer manually goes through the web dashboard to list assistants or check metadata. This is slow, non-repeatable, and impossible to integrate into an automated workflow.

The Fix

Use the tools directly. Instead of clicking buttons, call list_assistants to get a machine-readable ID list, then use get_assistant_info for detailed parameters.

When It Fits, When It Doesn't

Use this MCP Server if your primary need is orchestrating agent workflows that depend on managed knowledge bases and real-time usage tracking. You're building an application where the input data (files) or the agents themselves are complex, specialized components.

Don't use it if:
1. You just need simple chat access without file management; a basic messaging API might suffice.
2. Your files don't require indexing/RAG and you only need to store them in buckets (a general cloud storage SDK is better).
3. All your agents are simple, non-persistent scripts that never change. This server provides the necessary governance for dynamic, multi-agent systems.

If you need to manage the lifecycle of AI assets—from document ingestion (upload_file) to usage auditing (get_usage) and final interaction (chat)—this is your go-to tool.

Questions you might have

How do I check if my uploaded file is ready for use with chat? +

You must call get_file_status first. This tool checks the document's processing state, letting you know exactly when it moves from 'uploaded' to 'ready,' which prevents your agent from failing.

What should I use if I need a list of all available assistants? +

Use list_assistants. It gives you an immediate, machine-readable inventory of every assistant ID in your workspace. This is better than manually navigating the UI.

Does the chat tool handle file context automatically? +

No, it doesn't. You must use upload_file and confirm readiness with get_file_status before calling the chat tool to ensure the agent uses your desired documents.

How can I track my token usage programmatically? +

Call get_usage. This returns a direct report on your current API quota and consumption, letting you build limits into your application logic before they hit zero.

How do I check the full configuration of an agent using `get_assistant_info`? +

It retrieves all metadata and setup details for any specific assistant ID. This lets you verify parameters or see if an agent needs updates before calling it.

What command should I use to list every document uploaded using `list_files`? +

list_files returns the IDs and names of every document linked to your account. You can run this tool for an audit of all knowledge bases available.

If a document is obsolete, how do I permanently remove it with `delete_file`? +

The delete_file tool removes the file ID you provide from your knowledge base. Note that this action is irreversible; double-check the file ID first.

Before using a document, how can I inspect its details with `get_file_info`? +

This tool pulls the complete metadata for any given file ID. You get details like size and upload date without having to process or read the content.

Can my AI automatically find the details of an assistant just by providing its ID? +

Yes! Use the get_assistant_info tool with the Assistant ID. Your agent will respond with complete metadata, configuration, and capabilities connected to that specific agent in seconds.

How do I check the remaining token quota for my account? +

Simply ask the agent to run the get_usage action. It will retrieve the current token consumption statistics and the remaining quota provided by the Yuanqi platform.

Can I upload multiple files for my assistant's knowledge base? +

Yes! Use the upload_file tool for each document you want to add. After uploading, use the list_files tool to verify they are processed and available for RAG operations.

Connect to your AI in seconds.

Chat

Get file status

List files

Tencent Yuanqi MCP Server: 9 Tools for Agent & File Management

Make your AI actually useful.

Chat

Get File Status

List Files

Upload File

Delete File

Get Assistant Info

Get File Info

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 documents for agents shouldn't require five different tabs and three manual checks.

Tencent Yuanqi MCP Server: Control assistant interactions and file access.

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

The Agent needs context before answering.

Auditing a production agent's behavior.

Debugging agent configuration.

Maintaining data hygiene.

The honest tradeoffs

Assuming file readiness.

Ignoring API limits.

Relying on UI for management.

When It Fits, When It Doesn't

Questions you might have