quickstart-resources/mcp-client-go/main.go
Alex Akimov 470d1ba328
Some checks failed
Smoke Tests / test (push) Has been cancelled
Fix the tool-use loop in the Go, Rust, and Ruby clients and add a tool-loop smoke test (#200)
* Fix the tool-use loop in the Go, Rust, and Ruby clients and add a tool-loop smoke test

## Motivation and Context

Only the Python and TypeScript clients implemented a correct tool-use loop. The other three
had bugs that break ordinary multi-step requests:

- **Go, Rust, Ruby** did a single tool round and then called Claude once more *without*
  `tools`, so any request that needs a second tool call stalled. Go silently dropped
  `tool_use` blocks from that final response.
- **Ruby** called Claude once per `tool_use` block, each time with a single `tool_result`.
  Parallel tool calls produced a malformed message sequence and an API 400.
- **max_tokens** was 1000 in TypeScript and Ruby, 1024 in Go, and unset in Rust. Sonnet 5
  thinks adaptively, so 1000 tokens is regularly exhausted mid-thought. Python already used
  10000 with a comment explaining why.
- **Ruby** never forwarded MCP `isError` as `is_error`, so the model could not tell a failed
  tool call from a successful one. Rust cannot set the flag either (see below).
- **TypeScript** forwarded raw MCP content blocks to Anthropic. The two block shapes differ,
  so a non-text result would have failed.

The existing smoke test never noticed because it only checks that each client calls
`tools/list`. None of these bugs was reachable without an API key.

### What changed

All five clients now run the same loop: call tools until Claude answers without one, send
every `tool_result` of a turn in one user message, pass `tools` on every call, and stop
after `MAX_TOOL_TURNS = 10`. `max_tokens` is 10000 everywhere, with the same comment.
Python and TypeScript also keep the last response's text when the turn cap is hit; it used
to be dropped.

Rust keeps the `genai` crate. Its tool-response type has no `is_error` field, so an error
result is marked with an `Error:` prefix in the text and the limitation is commented.

### New smoke test

`tests/helpers/tool-loop-test.ts` starts a fake Anthropic Messages API on a loopback port,
points a client at it through `ANTHROPIC_BASE_URL`, pipes in one query, and checks every
request the client sends. It scripts two parallel tool calls, then a call to a tool the mock
server lacks (an `isError` result), then a final answer, and asserts that tools are passed
each time, `max_tokens` is 10000, all `tool_result`s arrive in one message with matching
ids, and the error is forwarded. `smoke-test.sh` runs it for Python, TypeScript, Go, and
Ruby.

The Rust client is excluded for now: `genai` reads no endpoint variable, and the client
negotiates protocol `2025-11-25`, under which the mock's array-rooted tool is refused at call
time. Both will be addressed in a follow-up that brings all examples to current SDK versions.

## How Has This Been Tested?

- `./tests/smoke-test.sh` passes for every example.
- The new tool-loop test passes all 19 checks for Python, TypeScript, Go, and Ruby.
- The Rust client was driven through the same scripted conversation with a temporary
  endpoint resolver (not committed) and passes.
- As a negative check, the Ruby client from `main` was run through the new test. It fails 10
  of 19 checks, on exactly the bugs listed above.
- Go and Ruby were built and run in `golang:1.25` and `ruby:3.4` containers.

## Breaking Changes

None. The clients' command lines, output format, and no-key behavior are unchanged.

## Types of changes

- [x] Bug fix (non-breaking change which fixes an issue)
- [ ] New feature (non-breaking change which adds functionality)
- [ ] Breaking change (fix or feature that would cause existing functionality to change)
- [x] Documentation update

## Checklist

- [x] I have read the [MCP Documentation](https://modelcontextprotocol.io)
- [x] My code follows the repository's style guidelines
- [x] New and existing tests pass locally
- [x] I have added appropriate error handling
- [x] I have added or updated documentation as needed

## Additional context

Two pre-existing issues surfaced while testing and are left for a follow-up:

- The Rust client (rmcp 3.1.2) negotiates `2025-11-25`. The TypeScript mock server and the
  Python weather server both reject its calls to array-rooted tools under that revision.
  Even current rmcp defaults to `2025-11-25`, so the client must request `2026-07-28`
  explicitly.
- The Go SDK's tool-result helper sends content as a list of text blocks rather than a
  string. The API accepts both, so it is unchanged.

AI assistance: the analysis, code changes, test helper, and this description were prepared
partially manually, partially with Claude Code and reviewed by me.

* Improvements

* Address comments
2026-09-19 18:25:02 -07:00

359 lines
10 KiB
Go

package main
import (
"bufio"
"context"
"encoding/json"
"fmt"
"log"
"os"
"os/exec"
"strings"
"github.com/anthropics/anthropic-sdk-go"
"github.com/anthropics/anthropic-sdk-go/option"
"github.com/google/jsonschema-go/jsonschema"
"github.com/joho/godotenv"
"github.com/modelcontextprotocol/go-sdk/mcp"
)
var model anthropic.Model = "claude-sonnet-5"
// Sonnet 5 thinks adaptively unless told otherwise, and max_tokens caps thinking
// plus the reply, so leave room for both.
const maxTokens = 10000
const maxToolTurns = 10
type MCPClient struct {
anthropic *anthropic.Client
session *mcp.ClientSession
tools []anthropic.ToolUnionParam
// Compiled outputSchema per tool name, for validating results.
outputSchemas map[string]*jsonschema.Resolved
}
func NewMCPClient() (*MCPClient, error) {
// .env is optional; the key may come from the environment instead.
_ = godotenv.Load()
client := anthropic.NewClient(option.WithAPIKey(os.Getenv("ANTHROPIC_API_KEY")))
return &MCPClient{
anthropic: &client,
}, nil
}
func (c *MCPClient) ConnectToServer(ctx context.Context, serverArgs []string) error {
if len(serverArgs) == 0 {
return fmt.Errorf("no server command provided")
}
// Create command to spawn server process
cmd := exec.CommandContext(ctx, serverArgs[0], serverArgs[1:]...)
// Create MCP client
client := mcp.NewClient(
&mcp.Implementation{
Name: "mcp-client-go",
Version: "0.1.0",
},
nil,
)
// Connect using CommandTransport
transport := &mcp.CommandTransport{
Command: cmd,
}
session, err := client.Connect(ctx, transport, nil)
if err != nil {
return fmt.Errorf("failed to connect to server: %w", err)
}
c.session = session
// List available tools
toolsResult, err := session.ListTools(ctx, &mcp.ListToolsParams{})
if err != nil {
return fmt.Errorf("failed to list tools: %w", err)
}
var toolNames []string
// Convert MCP tools to Anthropic tool format
c.outputSchemas = make(map[string]*jsonschema.Resolved)
for _, tool := range toolsResult.Tools {
toolNames = append(toolNames, tool.Name)
anthropicTool, err := mcpToolToAnthropicTool(tool)
if err != nil {
return fmt.Errorf("failed to convert mcp tool to anthropic tool: %w", err)
}
c.tools = append(c.tools, anthropicTool)
resolved, err := resolveOutputSchema(tool)
if err != nil {
return fmt.Errorf("failed to compile output schema of tool %s: %w", tool.Name, err)
}
if resolved != nil {
c.outputSchemas[tool.Name] = resolved
}
}
fmt.Printf("Connected to server with tools: %v\n", toolNames)
return nil
}
func mcpToolToAnthropicTool(tool *mcp.Tool) (anthropic.ToolUnionParam, error) {
var zeroTool anthropic.ToolUnionParam
schemaJSON, err := json.Marshal(tool.InputSchema)
if err != nil {
return zeroTool, fmt.Errorf("failed to marshal input schema of mcp tool: %w", err)
}
var schema anthropic.ToolInputSchemaParam
err = json.Unmarshal(schemaJSON, &schema)
if err != nil {
return zeroTool, fmt.Errorf("failed to unmarshal to anthropic input schema: %w", err)
}
toolParam := anthropic.ToolParam{
Name: tool.Name,
Description: anthropic.String(tool.Description),
InputSchema: schema,
}
return anthropic.ToolUnionParam{
OfTool: &toolParam,
}, nil
}
// resolveOutputSchema compiles a tool's declared outputSchema, or returns
// (nil, nil) when it declares none. OutputSchema is `any` because the root may
// be any JSON Schema, so round-trip through JSON to accept every form.
func resolveOutputSchema(tool *mcp.Tool) (*jsonschema.Resolved, error) {
if tool.OutputSchema == nil {
return nil, nil
}
raw, err := json.Marshal(tool.OutputSchema)
if err != nil {
return nil, fmt.Errorf("failed to marshal output schema: %w", err)
}
var schema jsonschema.Schema
if err := json.Unmarshal(raw, &schema); err != nil {
return nil, fmt.Errorf("failed to unmarshal output schema: %w", err)
}
return schema.Resolve(nil)
}
// validateToolOutput checks a result against its tool's declared outputSchema.
// Error results are exempt: they carry a message, not data.
func (c *MCPClient) validateToolOutput(name string, result *mcp.CallToolResult) error {
resolved, ok := c.outputSchemas[name]
if !ok || result.IsError {
return nil
}
if result.StructuredContent == nil {
return fmt.Errorf("tool %s declares an output schema but returned no structured content", name)
}
if err := resolved.Validate(result.StructuredContent); err != nil {
return fmt.Errorf("structured content from tool %s does not match its output schema: %w", name, err)
}
return nil
}
func (c *MCPClient) ProcessQuery(ctx context.Context, query string) (string, error) {
if c.session == nil {
return "", fmt.Errorf("client is not connected to any server")
}
messages := []anthropic.MessageParam{
anthropic.NewUserMessage(anthropic.NewTextBlock(query)),
}
var finalText []string
// Initial Claude API call with tools
response, err := c.createMessage(ctx, messages)
if err != nil {
return "", err
}
// Keep calling tools until Claude answers without one, up to a cap.
for turn := 0; turn < maxToolTurns; turn++ {
var toolUseBlocks []anthropic.ToolUseBlock
for _, block := range response.Content {
switch b := block.AsAny().(type) {
case anthropic.TextBlock:
finalText = append(finalText, b.Text)
case anthropic.ToolUseBlock:
toolUseBlocks = append(toolUseBlocks, b)
}
}
if len(toolUseBlocks) == 0 {
return strings.Join(finalText, "\n"), nil
}
// Execute every tool call in this response and collect the results
var anthropicToolResults []anthropic.ContentBlockParamUnion
for _, toolUseBlock := range toolUseBlocks {
// Add information about the tool call to final text
finalText = append(finalText, fmt.Sprintf("[Calling tool %s with args %s]", toolUseBlock.Name, string(toolUseBlock.Input)))
// Call the MCP server tool
mcpToolResult, err := c.session.CallTool(ctx, &mcp.CallToolParams{
Name: toolUseBlock.Name,
Arguments: toolUseBlock.Input,
})
if err != nil {
return "", fmt.Errorf("tool call %s failed: %w", toolUseBlock.Name, err)
}
if err := c.validateToolOutput(toolUseBlock.Name, mcpToolResult); err != nil {
return "", err
}
// StructuredContent is data the application can use directly.
if items, ok := mcpToolResult.StructuredContent.([]any); ok {
finalText = append(finalText, fmt.Sprintf("[%s returned %d items]", toolUseBlock.Name, len(items)))
}
// Content is a list of block types; forward only the text ones.
var texts []string
for _, block := range mcpToolResult.Content {
if text, ok := block.(*mcp.TextContent); ok {
texts = append(texts, text.Text)
}
}
anthropicToolResults = append(anthropicToolResults, anthropic.NewToolResultBlock(
toolUseBlock.ID,
strings.Join(texts, "\n"),
mcpToolResult.IsError,
))
}
// Append the assistant's response and all tool results, in one user
// message, to the history. Every tool_use needs a matching tool_result.
messages = append(messages, response.ToParam())
messages = append(messages, anthropic.NewUserMessage(anthropicToolResults...))
response, err = c.createMessage(ctx, messages)
if err != nil {
return "", err
}
}
// The turn cap was hit. Keep the last response's text. If it asked for
// more tools, say they were not run.
wantsTools := false
for _, block := range response.Content {
switch b := block.AsAny().(type) {
case anthropic.TextBlock:
finalText = append(finalText, b.Text)
case anthropic.ToolUseBlock:
wantsTools = true
}
}
if wantsTools {
finalText = append(finalText, fmt.Sprintf("[Stopped after %d tool-use turns]", maxToolTurns))
}
return strings.Join(finalText, "\n"), nil
}
// createMessage calls Claude with the current history. Tools are passed on
// every call so Claude can keep calling them across turns.
func (c *MCPClient) createMessage(ctx context.Context, messages []anthropic.MessageParam) (*anthropic.Message, error) {
response, err := c.anthropic.Messages.New(ctx, anthropic.MessageNewParams{
Model: model,
MaxTokens: maxTokens,
Messages: messages,
Tools: c.tools,
})
if err != nil {
return nil, fmt.Errorf("anthropic API request failed: %w", err)
}
return response, nil
}
func (c *MCPClient) ChatLoop(ctx context.Context) error {
fmt.Println("\nMCP Client Started!")
fmt.Println("Type your queries or 'quit' to exit.")
scanner := bufio.NewScanner(os.Stdin)
for {
fmt.Print("\nQuery: ")
if !scanner.Scan() {
break // EOF
}
query := strings.TrimSpace(scanner.Text())
if strings.EqualFold(query, "quit") {
break
}
if query == "" {
continue
}
response, err := c.ProcessQuery(ctx, query)
if err != nil {
fmt.Printf("\nError: %v\n", err)
continue
}
fmt.Printf("\n%s\n", response)
}
return scanner.Err()
}
func (c *MCPClient) Cleanup() error {
if c.session != nil {
if err := c.session.Close(); err != nil {
return fmt.Errorf("failed to close session: %w", err)
}
c.session = nil
}
return nil
}
func main() {
if len(os.Args) < 2 {
fmt.Fprintln(os.Stderr, "Usage: go run main.go <server_script_or_binary> [args...]")
os.Exit(1)
}
serverArgs := os.Args[1:]
client, err := NewMCPClient()
if err != nil {
log.Fatalf("Failed to create MCP client: %v", err)
}
ctx := context.Background()
if err := client.ConnectToServer(ctx, serverArgs); err != nil {
log.Fatalf("Failed to connect to MCP server: %v", err)
}
// Connecting and listing tools needs no credentials; querying them does.
// Matching the Python and TypeScript clients, report and exit rather than
// failing, so the connection itself can be exercised without a key.
if os.Getenv("ANTHROPIC_API_KEY") == "" {
fmt.Println("\nNo ANTHROPIC_API_KEY found. To query these tools with Claude, set your API key:")
fmt.Println(" export ANTHROPIC_API_KEY=your-api-key-here")
if err := client.Cleanup(); err != nil {
log.Printf("Cleanup error: %v", err)
}
return
}
if err := client.ChatLoop(ctx); err != nil {
log.Printf("ChatLoop error: %v", err)
}
if err := client.Cleanup(); err != nil {
log.Printf("Cleanup error: %v", err)
}
}