Build with AI

Use AI coding assistants to build with Agora faster. With access to Agora's full documentation, your AI assistant can generate working code examples, suggest API implementations, and answer platform-specific questions in real-time.

Agora skills

Agora skills is a set of structured reference files that give AI coding assistants deep knowledge of Agora's platform. When you ask your assistant to build something with Agora, it loads the relevant skill files covering products, APIs, and platform-specific code examples, so it can generate working code without guessing.

Skills includes integration with the Agora MCP server, which gives your assistant access to live Agora documentation. For installation instructions and supported tools, see the Agora Skills repository.

Installation

Install Agora Skills using one of the following methods:

Skills CLI (recommended)

Run the following command:

npx skills add github:AgoraIO/skills

Skills activate automatically when your agent detects relevant tasks, for example, "build a voice agent", "integrate Agora RTC", or "generate a token".

Manual installation

Clone the repository once and point your AI coding assistant to the skill files directly.

Clone the Agora Skills repo:

_1git clone https://github.com/AgoraIO/skills.git ~/agora-skills
Point your AI assistant to skills/agora/.

Follow the instructions for your AI coding assistant:
- Claude Code
- Cursor
- Windsurf
- GitHub Copilot
- Other tools
Run the following commands inside Claude Code:
- User-level (available across all your projects)
  
  _2/plugin marketplace add AgoraIO/skills _2/plugin install agora
- Project-level (shared with your team via version control)
  
  _2/plugin marketplace add AgoraIO/skills _2/plugin install agora --scope project
Copy or symlink skills/agora/ into .cursor/rules/. For more information, see Cursor skill directories.
Add skills/agora/ to your Cascade context. For more information, see Windsurf skills.
Reference via @workspace or add to .github/copilot-instructions.md. For more information, see Create skills for Copilot in the CLI or Create skills for the Copilot coding agent.
The skill files are plain markdown. Point your tool to skills/agora/ or load individual files directly. Use SKILL.md as the entry point.

Agora MCP server

The Agora MCP server gives your AI assistant direct access to Agora's documentation, so it can look up APIs, SDK methods, and platform-specific details in real time. The Agora MCP server is included when you install Agora Skills. If you prefer to install only the MCP server, it is available at:

https://mcp.agora.io

Installation

Refer to the installation instructions for your coding assistant.

Cursor
Claude
Codex
Gemini CLI
Manual installation

Click the button below to install the MCP server in Cursor

or add it manually with the following JSON:

{
  "mcpServers": {
    "agora-docs": {
      "url": "https://mcp.agora.io"
    }
  }
}

Claude Code

Run the following command in your terminal to install the MCP server in Claude Code:

_1claude mcp add --transport http agora-docs https://mcp.agora.io
Claude Desktop

In Settings, select Connectors and then choose Add custom connector. Enter the following values and click Add:
- Name: agora-docs
- Remote MCP server URL: https://mcp.agora.io

Run the following command in your terminal to install the server in OpenAI Codex:

codex mcp add --url https://mcp.agora.io agora-docs

Run the following command in your terminal to install the server in Gemini CLI:

gemini mcp add --transport http agora-docs https://mcp.agora.io

Add the server URL https://mcp.agora.io to your MCP client of choice. If prompted, set the transport to http or "Streamable HTTP".

Getting started

Once installed, your coding assistant has access to Agora's documentation through the MCP server. The assistant will intelligently use this resource when relevant to your questions. For more targeted results, mention Agora along with your target product and platform, such as 'iOS', 'Web', 'Conversational AI', 'Video Calling' in your prompts.

System prompt

This MCP works with all LLMs that support MCP, but performs best when the assistant understands facet-based exploration. Add the following prompt to your LLMs custom instructions:

System prompt for LLMs

# Agora MCP Markdown - System Prompt
You have access to Agora's documentation search via three tools:
- `algolia_search_index_docs_platform_aware_markdown` - Full-text search with facets
- `algolia_search_for_facet_values` - Browse products/platforms
- `algolia_recommendations` - Find related documentation
## Key Behaviors
**1. Use facets for discovery**
- When users ask about "what's available", explore facets first
- Example: User asks "what video products exist?" 
  → Use `algolia_search_for_facet_values(facetName: "product", facetQuery: "video")`
  → Shows video-calling is the main product
**2. Platform-aware searching**
- Include target platform in search queries (iOS, Android, Web, etc.)
- Results are intelligently ranked by platform relevance
**3. Interpret facet results for refinement**
- Search results include facet breakdowns by product and platform
- Use these to suggest filtering: "15 results are for video-calling, 8 for voice-calling"
**4. Maintain session continuity**
- Use same sessionId (UUID) across related searches in a conversation
- Improves ranking for follow-up queries
## Available Products & Platforms
**Key Products:** conversational-ai, video-calling, broadcast-streaming, interactive-live-streaming, agora-chat, voice-calling, signaling, extensions-marketplace, interactive-whiteboard
**Key Platforms:** android, web, ios, windows, macos, unity, flutter, react-native, electron, unreal
## Workflow Example
User: "I'm building an iOS app with Video Calling. Where do I start?"
1. Search: "iOS video calling quickstart"
2. Results show facets indicating video-calling is the best match
3. Suggest: "Most results are for Video Calling, here's the quickstart"
4. Follow-up searches: Keep same sessionId for context

What This Enables

Intelligent facet exploration before deep searches
Platform-aware result refinement suggestions
Cross-search session continuity for better context

Without the prompt, searches still work but won't leverage faceted browsing patterns.

AGENTS.md

To get the most out of Agora Skills and the MCP server, Agora recommends that you include an AGENTS.md or similar file in your repository. This file ensures that your agent always consults Agora docs to produce reliable, working code.

Add the following instructions to your own AGENTS.md file:

## Agora Documentation
Agora documentation is updated frequently. You should always refer to the latest documentation when working with Agora products. Agora offers an MCP server that you can use to browse and search its documentation. If the developer has not yet installed this server, recommend that they install it at https://mcp.agora.io.
If the Agora Skills files are available in your context, use them for platform-specific API guidance and code examples.

LLMs.txt

A Markdown-based index of the docs site is available at https://docs.agora.io/llms.txt. This file includes links to all product overview pages along with brief page descriptions. It also provides instruction on how to access LLM-friendly markdown versions of all documentation pages.

For more about how to use LLMs.txt files, see llmstxt.org.

Markdown docs

Each page on the Agora docs site is available in Markdown format, optimized for pasting into AI assistants when you can't use MCP.

To access the Markdown version, modify the HTML page URL as follows:

Change docs.agora.io to docs-md.agora.io
Replace any platform query parameter such as ?platform=web with underscore suffixes like _web.md
Add .md extension to the end of the path. For example:
- HTML: https://docs.agora.io/en/video-calling/get-started/get-started-sdk?platform=web
- Markdown:https://docs-md.agora.io/en/video-calling/get-started/get-started-sdk_web.md

You can also use the Markdown dropdown on the HTML page to copy, download or view the .md file. Choose Open in ChatGPT or Open in Claude to directly start a chat with the page context.