Provides AI assistants with direct access to Mastra.ai's complete knowledge base.
A Model Context Protocol (MCP) server that provides AI assistants with direct access to Mastra.ai's complete knowledge base. This includes comprehensive documentation with MDX support, a collection of production-ready code examples, technical blog posts, and detailed package changelogs. The server integrates with popular AI development environments like Cursor and Windsurf, as well as Mastra agents, making it easy to build documentation-aware AI assistants that can provide accurate, up-to-date information about Mastra.ai's ecosystem.
Create or update .cursor/mcp.json
in your project root:
MacOS/Linux
{
"mcpServers": {
"mastra": {
"command": "npx",
"args": ["-y", "@mastra/mcp-docs-server"]
}
}
}
Windows
{
"mcpServers": {
"mastra": {
"command": "cmd",
"args": ["/c", "npx", "-y", "@mastra/mcp-docs-server"]
}
}
}
This will make all Mastra documentation tools available in your Cursor workspace. Note that the MCP server wont be enabled by default. You'll need to go to Cursor settings -> MCP settings and click "enable" on the Mastra MCP server.
Create or update ~/.codeium/windsurf/mcp_config.json
:
MacOS/Linux
{
"mcpServers": {
"mastra": {
"command": "npx",
"args": ["-y", "@mastra/mcp-docs-server"]
}
}
}
Windows
{
"mcpServers": {
"mastra": {
"command": "cmd",
"args": ["/c", "npx", "-y", "@mastra/mcp-docs-server"]
}
}
}
This will make all Mastra documentation tools available in your Windsurf workspace. Note that Windsurf MCP tool calling doesn't work very well. You will need to fully quit and re-open Windsurf after adding this. If a tool call fails you will need to go into Windsurf MCP settings and re-start the MCP server.
import { MCPClient } from '@mastra/mcp';
import { Agent } from '@mastra/core/agent';
import { openai } from '@ai-sdk/openai';
// Configure MCP with the docs server
const mcp = new MCPClient({
servers: {
mastra: {
command: 'npx',
args: ['-y', '@mastra/mcp-docs-server'],
},
},
});
// Create an agent with access to all documentation tools
const agent = new Agent({
name: 'Documentation Assistant',
instructions: 'You help users find and understand Mastra.ai documentation.',
model: openai('gpt-4'),
tools: await mcp.getTools(),
});
// Or use toolsets dynamically in generate/stream
const response = await agent.stream('Show me the quick start example', {
toolsets: await mcp.getToolsets(),
});
mastraDocs
)mastraExamples
)mastraBlog
)mastraChanges
)Interact with the Eventbrite API to search for events, get event details, and retrieve venue information.
Performs web searches using the Gemini Web Search Tool via the local gemini-cli.
Performs deep web searches for information using the Tavily API.
Web search and webpage content extraction using the Google Custom Search API.
Provides full-text and semantic search over structured and unstructured data using Azure Cognitive Search.
Search Engine made for AIs by Exa
Search across multiple email accounts using mxHERO's vector search service.
Search for IP addresses using Chaitin's IP Intelligence API.
A full-text search server for Jewish texts and literature.
Search for news articles using the Naver News API. Requires Naver News API credentials.