About
mcp-golang is an unofficial implementation of the Model Context Protocol (MCP) in Go that enables developers to build MCP servers and clients with minimal boilerplate code. Key capabilities include: - Type-safe tool arguments defined as native Go structs with automatic JSON schema generation, deserialization, and error handling - Multiple built-in transports including stdio for full feature support and HTTP for stateless communication, with the ability to implement custom transports - Modular architecture split into transport, protocol, and server/client components that can be used independently or together - Bi-directional support for both server and client implementations through stdio transport - Automatic generation of MCP endpoints leaving developers to focus only on implementing tools, prompts, and resources
README
[](https://pkg.go.dev/github.com/metoro-io/mcp-golang) [](https://goreportcard.com/report/github.com/metoro-io/mcp-golang)
mcp-golang
mcp-golang is an unofficial implementation of the Model Context Protocol in Go.
Write MCP servers and clients in golang with a few lines of code.
Docs at https://mcpgolang.com
Highlights
Example Usage
Install with go get github.com/metoro-io/mcp-golang
Server Example
package mainimport (
"fmt"
"github.com/metoro-io/mcp-golang"
"github.com/metoro-io/mcp-golang/transport/stdio"
)
// Tool arguments are just structs, annotated with jsonschema tags
// More at https://mcpgolang.com/tools#schema-generation
type Content struct {
Title string json:"title" jsonschema:"required,description=The title to submit"
Description *string json:"description" jsonschema:"description=The description to submit"
}
type MyFunctionsArguments struct {
Submitter string json:"submitter" jsonschema:"required,description=The name of the thing calling this tool (openai, google, claude, etc)"
Content Content json:"content" jsonschema:"required,description=The content of the message"
}
func main() {
done := make(chan struct{})
server := mcp_golang.NewServer(stdio.NewStdioServerTransport())
err := server.RegisterTool("hello", "Say hello to a person", func(arguments MyFunctionsArguments) (*mcp_golang.ToolResponse, error) {
return mcp_golang.NewToolResponse(mcp_golang.NewTextContent(fmt.Sprintf("Hello, %server!", arguments.Submitter))), nil
})
if err != nil {
panic(err)
}
err = server.RegisterPrompt("promt_test", "This is a test prompt", func(arguments Content) (*mcp_golang.PromptResponse, error) {
return mcp_golang.NewPromptResponse("description", mcp_golang.NewPromptMessage(mcp_golang.NewTextContent(fmt.Sprintf("Hello, %server!", arguments.Title)), mcp_golang.RoleUser)), nil
})
if err != nil {
panic(err)
}
err = server.RegisterResource("test://resource", "resource_test", "This is a test resource", "application/json", func() (*mcp_golang.ResourceResponse, error) {
return mcp_golang.NewResourceResponse(mcp_golang.NewTextEmbeddedResource("test://resource", "This is a test resource", "application/json")), nil
})
err = server.Serve()
if err != nil {
panic(err)
}
<-done
}
HTTP Server Example
You can also create an HTTP-based server using either the standard HTTP transport or Gin framework:
// Standard HTTP
transport := http.NewHTTPTransport("/mcp")
transport.WithAddr(":8080")
server := mcp_golang.NewServer(transport)// Or with Gin framework
transport := http.NewGinTransport()
router := gin.Default()
router.POST("/mcp", transport.Handler())
server := mcp_golang.NewServer(transport)
Note: HTTP transports are stateless and don't support bidirectional features like notifications. Use stdio transport if you need those features.
Client Example
Checkout the examples/client directory for a more complete example.
``go
package main
import ( "context" "log" mcp "github.com/metoro-io/mcp-golang" "github.com/metoro-io/mcp-golang/transport/stdio" )
// Define type-safe arguments
type CalculateArgs struct {
Operation string json:"operation"
A int json:"a"`
B
Related MCP Servers
AI Research Assistant
hamid-vakilzadeh
AI Research Assistant provides comprehensive access to millions of academic papers through the Semantic Scholar and arXiv databases. This MCP server enables AI coding assistants to perform intelligent literature searches, citation network analysis, and paper content extraction without requiring an API key. Key features include: - Advanced paper search with multi-filter support by year ranges, citation thresholds, field of study, and publication type - Title matching with confidence scoring for finding specific papers - Batch operations supporting up to 500 papers per request - Citation analysis and network exploration for understanding research relationships - Full-text PDF extraction from arXiv and Wiley open-access content (Wiley TDM token required for institutional access) - Rate limits of 100 requests per 5 minutes with options to request higher limits through Semantic Scholar
Linkup
LinkupPlatform
Linkup is a real-time web search and content extraction service that enables AI assistants to search the web and retrieve information from trusted sources. It provides source-backed answers with citations, making it ideal for fact-checking, news gathering, and research tasks. Key features of Linkup: - Real-time web search using natural language queries to find current information, news, and data - Page fetching to extract and read content from any webpage URL - Search depth modes: Standard for direct-answer queries and Deep for complex research across multiple sources - Source-backed results with citations and context from relevant, trustworthy websites - JavaScript rendering support for accessing dynamic content on JavaScript-heavy pages
context7
huynguyen03dev