MCP Tools

MCP (Model Context Protocol) tools allow your agent to connect to external MCP servers and use their tools. This enables your agent to interact with various services and resources through standardized MCP tool interfaces.

Connecting to an MCP Server

To use MCP tools, you first need to create an MCP client using the mcpclient.NewSSEClient function. The server should expose an SSE (Server-Sent Events) endpoint:

import (
    "context"
    "github.com/curaious/uno/pkg/agent-framework/tools"
)

mcpClient, err := mcpclient.NewSSEClient(context.Background(), "http://localhost:9001/sse")
if err != nil {
    log.Fatal(err)
}

Parameters

• ctx: The context for the connection
• endpoint: The SSE endpoint URL of the MCP server (e.g., "http://localhost:9001/sse")

Custom Headers

You can also configure the MCP Client to send custom HTTP headers while interacting with the MCP server.

mcpClient, err := mcpclient.NewSSEClient(context.Background(), "http://localhost:9001/sse",
	mcpclient.WithHeaders(map[string]string{
        "token": "your-token",
    }),
)

Filtering Tools

You can optionally filter which tools to use by passing tool names to GetTools():

// Only use specific tools
mcpClient, err := mcpclient.NewSSEClient(context.Background(), "http://localhost:9001/sse",
		mcpclient.WithToolFilter("list_users"),
	)

Complete Example

Here’s a complete example of an agent using MCP tools:

package main

import (
    "context"
    "fmt"
    "log"

	"github.com/bytedance/sonic"
	"github.com/curaious/uno/pkg/agent-framework/agents"
	"github.com/curaious/uno/pkg/agent-framework/mcpclient"
	"github.com/curaious/uno/pkg/gateway"
	"github.com/curaious/uno/pkg/llm"
	"github.com/curaious/uno/pkg/llm/responses"
	"github.com/curaious/uno/pkg/sdk"
)

func main() {
    // Initialize SDK client
    client, err := sdk.New(&sdk.ClientOptions{
		LLMConfigs: sdk.NewInMemoryConfigStore([]*gateway.ProviderConfig{
			{
				ProviderName:  llm.ProviderNameOpenAI,
				BaseURL:       "",
				CustomHeaders: nil,
				ApiKeys: []*gateway.APIKeyConfig{
					{
						Name:   "Key 1",
						APIKey: "",
					},
				},
			},
		}),
	})
    if err != nil {
        log.Fatal(err)
    }

    // Create LLM model
    model := client.NewLLM(sdk.LLMOptions{
        Provider: llm.ProviderNameOpenAI,
        Model:    "gpt-4o-mini",
    })

    // Create conversation history
    history := client.NewConversationManager("default", uuid.NewString(), "")

    // Connect to MCP server
    mcpClient, err := mcpclient.NewSSEClient(context.Background(), "http://localhost:9001/sse",
		mcpclient.WithHeaders(map[string]string{
			"token": "your-token",
		}),
		mcpclient.WithToolFilter("list_users"),
	)

    // Create agent with MCP tools
    agent := client.NewAgent(&sdk.AgentOptions{
        Name:        "Hello world agent",
        Instruction: client.Prompt("You are helpful assistant."),
        LLM:         model,
        History:     history,
        McpServers:  []*mcpclient.MCPClient{mcpClient},
    })

    // Execute agent
	out, err := agent.Execute(context.Background(), &agents.AgentInput{
        Messages: []responses.InputMessageUnion{
            responses.UserMessage("Hello!"),
        },
    })
    if err != nil {
        log.Fatal(err)
    }

    b, _ := sonic.Marshal(out)
    fmt.Println(string(b))
}