4,500+ servers built on MCP Fusion
Vinkius

Agora MCP. Manage live video streams and recordings from your agent.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Agora MCP on Cursor AI Code Editor MCP Client Agora MCP on Claude Desktop App MCP Integration Agora MCP on OpenAI Agents SDK MCP Compatible Agora MCP on Visual Studio Code MCP Extension Client Agora MCP on GitHub Copilot AI Agent MCP Integration Agora MCP on Google Gemini AI MCP Integration Agora MCP on Lovable AI Development MCP Client Agora MCP on Mistral AI Agents MCP Compatible Agora MCP on Amazon AWS Bedrock MCP Support

Just plug in your AI agents and start using Vinkius.

Agora MCP Server manages real-time video, voice, and interactive streaming. It lets your AI agent handle channel creation, monitor user usage, and manage cloud recording status programmatically.

You can start, stop, and query recordings, or list current active calls directly from your workflow.

What your AI agents can do

Acquire cloud recording

Requests a unique resource ID needed before you can start any cloud recording session.

Create project

Creates a brand new Agora project within the platform.

Get project details

Retrieves specific configuration details for a known Agora project.

+ 7 more capabilities included
Manage Project Structure

Create new Agora projects, list existing ones, and fetch detailed configuration information for any given project.

Monitor Real-Time Calls

List all currently active communication channels and retrieve the list of users participating in those sessions.

Control Cloud Recordings

Start, stop, and check the status of cloud recordings for any active channel, ensuring reliable archival.

Analyze Usage Data

Query usage metrics for a specific project, retrieving consumption data on minutes, bandwidth, and peak concurrent users.

Inspect Whiteboard Rooms

List and check the status of active Interactive Whiteboard rooms.

Configure Channel Settings

Set and manage specific rules and settings for communication channels to tailor the user experience.

Supported MCP Clients

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients
Free for Subscribers

Waiting for input…

AI Agent

Agora MCP Server: 10 Tools for Video Stream Management

Manage real-time channels, monitor usage metrics, and control the entire lifecycle of cloud recordings using these 10 tools.

acquire019d8413

acquire cloud recording

Requests a unique resource ID needed before you can start any cloud recording session.

create019d8413

create project

Creates a brand new Agora project within the platform.

get019d8413

get project details

Retrieves specific configuration details for a known Agora project.

get019d8413

get usage stats

Queries and returns detailed operational usage data for a specified project.

list019d8413

list active calls

Lists all ongoing communication calls and sessions happening right now.

list019d8413

list projects

Returns a list of all Agora projects configured in your console.

list019d8413

list whiteboard rooms

Lists all active Interactive Whiteboard sessions.

query019d8413

query cloud recording

Checks the current status (running, stopped, pending) of a scheduled cloud recording.

start019d8413

start cloud recording

Initiates a cloud recording for a specific channel and project.

stop019d8413

stop cloud recording

Stops an ongoing cloud recording session immediately.

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 Agora, 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

Agora MCP Server manages real-time video, voice, and interactive streaming. It lets your AI agent handle channel creation, monitor user usage, and manage cloud recording status programmatically. You can start, stop, and query recordings, or list current active calls directly from your workflow.

Manage Project Structure
Your agent can create a brand new Agora project using create_project, list all configured projects with list_projects, and grab specific setup details for any project with get_project_details.

Monitor Real-Time Calls
Your agent can list every ongoing communication call and session using list_active_calls. It also checks all active Interactive Whiteboard sessions via list_whiteboard_rooms.

Control Cloud Recordings
To archive stuff, your agent first needs a unique resource ID by calling acquire_cloud_recording. Then, it can start a recording for a specific channel and project with start_cloud_recording. When you need to stop it, it uses stop_cloud_recording, and to see what's going on, it queries the status with query_cloud_recording.

Analyze Usage Data
Your agent queries detailed usage metrics for a specific project using get_usage_stats, getting consumption data on minutes, bandwidth, and peak concurrent users.

Configure Channel Settings
Your agent can set and manage specific rules and settings for communication channels to tailor the user experience.

How Agora MCP Works

  1. 1 Subscribe to the Agora MCP Server and get your credentials (Customer ID, AppID).
  2. 2 Run a function like list_projects to find the correct project ID.
  3. 3 Pass the project ID and desired action (e.g., 'start recording' or 'get usage stats') to the agent to execute the task.

The bottom line is, you feed your agent your credentials and tell it what operational state you need—it handles the necessary API calls.

Who Is Agora MCP For?

The Ops Engineer who needs to monitor system health across multiple projects without logging into a dashboard. The Product Manager who needs usage reports for billing or roadmapping. Full-Stack Developers automating provisioning tasks. Anyone who treats real-time communication as a background process, not a manual chore.

DevOps Engineer

Automates the setup of communication channels, creates new projects, and runs scripts to manage recording sessions.

Live Operations Team

Monitors peak system usage, checks the status of cloud recordings, and validates the health of multiple active projects in real-time.

Product Manager

Retrieves monthly consumption reports and user engagement data via natural language prompts to inform product decisions.

What Changes When You Connect

  • See who's in a meeting right now with list_active_calls. You get a list of every user UID connected to a room without opening the Agora dashboard.
  • Get instant project status with list_projects and get_project_details. You can check AppIDs and token settings instantly, letting you debug setup issues fast.
  • Manage recordings without manual API calls. Use acquire_cloud_recording before you can run start_cloud_recording or stop_cloud_recording through your agent.
  • Monitor costs and usage. get_usage_stats queries minutes consumed, bandwidth, and peak concurrent users, giving you instant billing data.
  • Orchestrate the entire flow. Your agent can call create_project and then immediately run list_whiteboard_rooms to set up a whole session.
  • Understand the network layer. You can use list_whiteboard_rooms and configure channel rules to ensure the interactive experience stays optimized.

Real-World Use Cases

01

Auditing a Major Webinar

The legal team needs to confirm who was in the 'Q3 Strategy' webinar and ensure the recording was captured. Your agent runs list_active_calls to get the participant list, then calls query_cloud_recording to confirm the status, and finally runs get_usage_stats to calculate the cost.

02

Setting Up a New Client Demo

A developer needs a dedicated, isolated environment for a new client demo. The agent first calls create_project, then uses get_project_details to grab the new AppID, and finally uses list_whiteboard_rooms to prepare the collaboration space.

03

Debugging a Live Stream Failure

A live ops engineer notices calls are failing. They use list_active_calls to see the problematic room, then use get_project_details to check the associated project's rules, and finally use list_whiteboard_rooms to check if the whiteboard connection is the failure point.

04

Billing and Optimization Check

The product manager needs to know if their recent video campaign exceeded budget. The agent runs get_usage_stats for the relevant project, providing minutes consumed and peak concurrency data instantly for reporting.

The Tradeoffs

Manual API Choreography

Logging into the Agora console, manually navigating to 'Usage Metrics', and copying the peak user count into a spreadsheet. This takes 15 minutes of clicking and copy-pasting.

Just ask your agent to run get_usage_stats and specify the time frame. It pulls the data directly, giving you the minutes consumed and peak concurrency number immediately.

Ignoring Setup Requirements

Trying to start a recording (start_cloud_recording) without first checking if the resource ID is acquired. The API call fails, and you waste time debugging the failure reason.

Always run acquire_cloud_recording first. It ensures you have the required resource ID before you attempt to start or stop the recording.

Siloed Project Management

Keeping project configs (AppIDs, secrets) in a separate spreadsheet from your actual usage data. If one changes, you have to manually update both places.

Use list_projects and get_project_details. This keeps your project configuration and your usage metrics linked and current within the MCP Server.

When It Fits, When It Doesn't

Use this if you need to manage the full lifecycle of a real-time streaming session: from initial project setup (create_project) to active monitoring (list_active_calls) and final archival (start_cloud_recording). You need to correlate resource usage with project state.

Don't use this if your only goal is to manage credentials or simple data access—use a dedicated secrets manager or a simple database connection tool instead. If you just need to check a single resource status without needing project context, a dedicated cloud service tool might be cleaner. This server is for orchestration.

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Agora. 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

How we secure 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 server provides 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.

Available Capabilities

acquire_cloud_recording create_project get_project_details get_usage_stats list_active_calls list_projects list_whiteboard_rooms query_cloud_recording start_cloud_recording stop_cloud_recording

Managing real-time video streams means constant dashboard switching.

Today, checking a room's status means logging into the Agora console. You switch tabs to see active calls, then switch again to find the usage dashboard. You copy a list of UIDs here, and then copy a usage metric over there. It's slow, and you lose context.

With the Agora MCP Server, you tell your agent the goal. It runs `list_active_calls` to get the UIDs and simultaneously runs `get_usage_stats` to get the minutes consumed. You get both pieces of data in one conversation thread.

Agora MCP Server: Run video operations from chat.

You no longer have to manually navigate the console to start or stop a recording. Instead, your agent executes `acquire_cloud_recording` and then runs `start_cloud_recording` with a simple command. It handles the multi-step process in the background.

The system treats the whole workflow—from acquiring the resource ID to confirming the recording status—as a single, reliable action. It's about automating the sequence, not just the button press.

Common Questions About Agora MCP

How do I check who is in a room using the list_active_calls tool? +

The list_active_calls tool retrieves a list of all ongoing calls and the UIDs of the users currently connected. It's useful for confirming immediate presence in a session.

What is the difference between `list_projects` and `get_project_details`? +

list_projects gives you a high-level list of all projects. You must run get_project_details with a specific project ID to get the full configuration, like AppIDs and token settings.

Can I use `start_cloud_recording` without first running `acquire_cloud_recording`? +

No. You must run acquire_cloud_recording first. The tool requires a specific resource ID, which this initial call provides, making the recording process reliable.

How do I find out the usage for a specific project using the get_usage_stats tool? +

You provide the target project ID and the time range. The get_usage_stats tool returns detailed metrics on video minutes, audio minutes, and peak concurrency for that period.

What does `query_cloud_recording` actually check? +

It checks the current status of an existing recording job. You use it to confirm if the recording is still running, paused, or if it has finished.

When should I use `create_project` versus `list_projects`? +

Use create_project when you need to establish a completely new Agora workspace. list_projects simply shows you all the existing projects you have access to in the console.

How do I manage channel settings using the `rule_management` tool? +

The rule_management tool lets you configure channel-level rules. You set parameters there to optimize the interactive experience for your users.

What happens if I call `start_cloud_recording` without proper credentials? +

The call fails and returns an authentication error. Always ensure your Customer ID, Secret, and AppID are correctly provided before trying to record anything.

Can I automatically list all active users in an Agora channel? +

Yes! Use the list_channel_users tool with the project AppID and the target Channel Name. Your agent will return a list of UIDs currently connected to that session.

How do I start a cloud recording session via the AI agent? +

Use the start_cloud_recording tool with the necessary parameters (AppID, Channel Name, and recording config). The agent will trigger the Agora cloud recording engine and return the Resource ID and SID.

Can I monitor the total minutes consumed by my project this month? +

Yes! The get_usage_metrics tool retrieves granular consumption data, including audio and video minutes, filtered by date range or project.

More in this category

You might also like

Built & Managed by Vinkius 30s setup 10 tools

We've already built the connector for Agora. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 10 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.