能力标签

🔌 MCP 🤖 Agent 🔄 工作流 🐳 Docker 💻 CLI 🔗 REST API 📚 RAG 🧠 Claude ✨ GPT

🔌

MCP工具

Go代理SDK

基于 Go · 让 AI 助手直接操作你的系统与工具

英文名：agent-sdk-go

⭐ 19 Stars 🍴 1 Forks 💻 Go 📄 Apache-2.0 🏷 AI 8.0分

8.0AI 综合评分

mcpa2aag-uiagent-sdkagent-sdk-goagenticgo

⬇ 下载源码 ZIP ⚙️ 配置说明

✦ AI Skill Hub 推荐

Go代理SDK 是 AI Skill Hub 本期精选MCP工具之一。综合评分 8.0 分，整体质量较高。我们强烈推荐将其纳入你的 AI 工具库，帮助提升工作效率。

📚 深度解析

Go代理SDK 是一款基于 MCP（Model Context Protocol）标准协议的 AI 工具扩展。MCP 协议由 Anthropic 开发并开源，旨在建立 AI 模型与外部工具之间的标准化通信接口，目前已被 Claude Desktop、Claude Code、Cursor 等主流 AI 工具采纳。

通过安装 Go代理SDK，你的 AI 助手将获得额外的工具调用能力，可以用自然语言直接操控该工具的功能，无需学习复杂的命令行语法。MCP 工具的核心价值在于"一次配置，永久增强"——配置完成后，每次与 AI 对话时都可以无缝调用这些工具。

在技术实现上，MCP 工具通过标准的 JSON-RPC 协议与 AI 客户端通信，工具的功能以"工具列表"的形式暴露给 AI 模型，AI 可以按需调用。Go代理SDK 提供了结构化的工具调用接口，使 AI 模型能够精确地理解和使用每个功能点，显著降低 AI 在工具使用上的错误率。

与传统的 API 集成相比，MCP 工具的优势在于无需编写代码——用户只需在配置文件中添加几行 JSON，即可让 AI 获得全新能力。AI Skill Hub 将 Go代理SDK 评为 AI 评分 8.0 分，属于同类工具中的优质选择。

📋 工具概览

Go代理SDK 是一款遵循 MCP（Model Context Protocol）标准协议的 AI 工具扩展。通过 MCP 协议，它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务，实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用，都可以通过自然语言在 AI 对话中直接触发，极大提升生产效率。

GitHub Stars

⭐ 19

开发语言

支持平台

Windows / macOS / Linux（跨平台）

维护状态

轻量级项目，按需更新

开源协议

Apache-2.0

AI 综合评分

8.0 分

工具类型

MCP工具

Forks

📖 中文文档

以下内容由 AI Skill Hub 根据项目信息自动整理，如需查看完整原始文档请访问底部「原始来源」。

📌 核心特色

通过标准 MCP 协议与 Claude、Cursor 等主流 AI 客户端深度集成
提供结构化工具调用接口，显著降低 AI 集成复杂度
支持 Claude Desktop 和 Claude Code 无缝接入，开箱即用
可与其他 MCP 工具组合叠加，构建完整 AI 工作站
轻量无侵入设计，不影响现有系统架构

🎯 主要使用场景

在 Claude Desktop 对话中直接调用本地工具，实现 AI 与系统的深度联动
通过自然语言驱动复杂的多步骤自动化任务，代替繁琐手动操作
将多个 MCP 工具组合使用，构建个人专属 AI 工作站

以下安装命令基于项目开发语言和类型自动生成，实际以官方 README 为准。

安装命令

# 方式一：通过 Claude Code CLI 一键安装
claude skill install https://github.com/agenticenv/agent-sdk-go

# 方式二：手动配置 claude_desktop_config.json
{
  "mcpServers": {
    "go--sdk": {
      "command": "npx",
      "args": ["-y", "agent-sdk-go"]
    }
  }
}

# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json

📋 安装步骤说明

确认已安装 Node.js（v18 或以上版本）
打开 Claude Desktop 或 Claude Code 的 MCP 配置文件
按「交给 Agent 安装 → Claude Desktop」标签中的 JSON 配置填入 mcpServers 字段
保存配置文件并重启 Claude 客户端
重启后，在对话中即可使用本工具

以下用法示例由 AI Skill Hub 整理，涵盖最常见的使用场景。

常用命令 / 代码示例

# 安装后在 Claude 对话中直接使用
# 示例：
用户: 请帮我用 Go代理SDK 执行以下任务...
Claude: [自动调用 Go代理SDK MCP 工具处理请求]

# 查看可用工具列表
# 在 Claude 中输入："列出所有可用的 MCP 工具"

以下配置示例基于典型使用场景生成，具体参数请参照官方文档调整。

配置示例

// claude_desktop_config.json 配置示例
{
  "mcpServers": {
    "go__sdk": {
      "command": "npx",
      "args": ["-y", "agent-sdk-go"],
      "env": {
        // "API_KEY": "your-api-key-here"
      }
    }
  }
}

// 保存后重启 Claude Desktop 生效

📑 README 深度解析真实文档完整度 74/100 含工作流图查看 GitHub 原文 →

以下内容由系统直接从 GitHub README 解析整理，保留代码块、表格与列表结构。

Overview

agent-sdk-go is a Go SDK for production AI agents — tools, MCP, A2A, human-in-the-loop approvals, and multi-agent delegation.

Every agent run on the Temporal runtime is a durable workflow: it survives process crashes and deploys, supports horizontal scaling, and is observable as a real service operation. This is the recommended runtime for production workloads where run durability matters. A running Temporal server is required.

The in-process runtime runs the agent loop directly in your process with no external dependencies — ideal for development, testing, and deployments where Temporal is not available. It has full feature parity: tools, MCP, A2A, sub-agents, streaming, AG-UI, approvals, conversation, and observability.

pkg/agent exposes three entry points — Run, Stream, and RunAsync. Add WithTemporalConfig or WithTemporalClient for the Temporal runtime; omit it for in-process. See Getting Started or Runtimes.

Capabilities

LLM providers — OpenAI, Anthropic, and Gemini out of the box; bring your own via interfaces.LLMClient.
Tools — Register built-in or custom tools via interfaces.Tool; optional parallel vs sequential execution for multiple tool calls in one LLM round (WithAgentToolExecutionMode).
Human-in-the-loop — Approval gates on tool calls and delegation across Run, RunAsync, and Stream.
Conversation — Persist multi-turn message history via WithConversation; in-memory store for in-process; in-memory and Redis for Temporal. Bring your own via interfaces.Conversation.
Sub-agents — Delegate to specialist agents via WithSubAgents; recursive delegation with depth limiting; all sub-agent events fan in to the parent stream on both runtimes.
MCP — Extend agent capabilities by connecting any MCP server as a tool source via WithMCPConfig or WithMCPClients.
A2A — Connect remote Agent-to-Agent agents as tool providers via WithA2AConfig or WithA2AClients; or expose the agent itself as an A2A server via WithA2ADefaultServer / WithA2AServer and RunA2A.
Retrieval (RAG) — Ground agent responses in external knowledge bases via a pluggable Retriever interface with built-in Weaviate and pgvector support; extend with your own implementation.
Streaming — Partial tokens and events via Stream and WithStream.
AG-UI — Stream events conform to the AG-UI protocol; agents work out of the box with any AG-UI compatible frontend such as CopilotKit.
Reasoning — Extended thinking / chain-of-thought where supported (Anthropic, Gemini).
Token usage — Track input, output, and reasoning token counts per run.
Observability — OpenTelemetry traces, metrics, and structured logs; export to any OTLP-compatible backend.
Durable execution ★ — Runs survive process crashes and restarts; Temporal workflow history ensures no step is lost.
Scale ★ — Add Temporal workers to scale agent execution horizontally; split agent and worker across separate processes.

★ Temporal runtime only.

Prerequisites

Go 1.26+ (see go.mod) and credentials for your LLM provider are always required.

In-process runtime (default): no additional setup — just go get and an LLM API key.
Temporal runtime: a running Temporal server is required. See Temporal setup.

Module: github.com/agenticenv/agent-sdk-go

go get github.com/agenticenv/agent-sdk-go@latest

Durable agents: survive crashes, restarts, and deploys

Because every agent run is a Temporal workflow, the process can crash and restart without losing a single step — tool calls already made are not replayed, approvals already given are not re-requested, and the agent resumes exactly where it left off. DisableLocalWorker and NewAgentWorker let you split the client and execution across OS processes or machines while the cluster holds all state.

examples/durable_agent walks through this split across two terminals, including crash and retry scenarios. Step-by-step exercises: examples/durable_agent/README.md.

Getting Started

How to use the SDK—agents, LLMs, Temporal connection, examples.

Token usage (`LLMUsage`)

Each LLM completion can report token counts via [interfaces.LLMUsage](pkg/interfaces/llm.go) on [interfaces.LLMResponse.Usage](pkg/interfaces/llm.go). OpenAI, Anthropic, and Gemini clients populate **PromptTokens**, **CompletionTokens**, **TotalTokens**, and optional **CachedPromptTokens** / **ReasoningTokens** when the provider returns them.

**Agent.Run / RunAsync: **Usage on *AgentRunResult is the sum across all LLM calls in that run (including tool rounds). Use it for cost estimates, quotas, and logging.
**Stream:** the same aggregate appears as **Usage** on **RUN_FINISHED**: assert **[*AgentRunFinishedEvent](pkg/agent/agent.go)**, then **Result** as **[*AgentRunResult](pkg/agent/agent.go)**. OpenAI streaming **include_usage** surfaces totals there. Helpers: examples/shared/utils.go (UsageFooter, RunResultFromFinishedEvent).

Examples: examples/simple_agent (prints usage after Run), examples/agent_with_stream (prints usage on **RUN_FINISHED**).

Default: no-op, zero config

No WithObservabilityConfig, no WithTracer, no WithMetrics — the agent uses built-in no-op implementations. No extra imports or init code required.

Configuration

A Temporal connection (WithTemporalConfig or WithTemporalClient) is optional — omit it to use the local runtime (in-process, no Temporal). Set it to use the Temporal runtime (durable execution). All other options work the same on both runtimes.

WithTemporalConfig: Temporal connection (Host, Port, Namespace, TaskQueue). Use for simple setups. See Temporal connection.
WithTemporalClient: Pre-configured Temporal client. Use for TLS, API key auth, Temporal Cloud. Requires WithTaskQueue. Agent does not close the client.
WithTaskQueue: Task queue name. Required when using WithTemporalClient. Ignored when using WithTemporalConfig.
WithResponseFormat: LLM response format. Omit for text-only. Use &interfaces.ResponseFormat{Type, Name, Schema} for JSON with schema. See Response format.
WithConversation: Message history store. Use inmem for single process; redis for remote workers. Pass same conversationID to Run and Stream for a session. See Conversation.
WithConversationSize: Max messages to fetch for LLM context (default 20). Only applies when WithConversation is set.
EnableRemoteWorkers: Pass EnableRemoteWorkers() when using DisableLocalWorker with approval or streaming (starts the event worker/workflow path).
WithSubAgents: Attach specialist agents the main agent can delegate to. Each needs its own task queue and worker. See Sub-agents.
WithMaxSubAgentDepth: Maximum delegation hops from this agent (default 2). See Sub-agents.
WithMaxIterations: Max LLM rounds (default 5).
WithStream: Enable Stream partial content streaming.
Token usage: Not a separate option. On **Run**, read **Usage** on **[*AgentRunResult](pkg/agent/agent.go)** when set. On **Stream**, assert **[*AgentRunFinishedEvent](pkg/agent/agent.go)** with **[*AgentRunResult](pkg/agent/agent.go)** in **Result** (aggregate across LLM/tool rounds when the provider reports it). See Token usage.
WithLLMSampling: Pass &agent.LLMSampling{...}; nil or zero fields leave that knob to the provider default. Which fields apply where:
**Temperature** — OpenAI, Anthropic, Gemini.
**MaxTokens** — OpenAI, Anthropic, Gemini (max output / completion tokens).
**TopP** — OpenAI, Gemini only (not sent to Anthropic).
**TopK** — Anthropic only (not sent to OpenAI or Gemini).
**Reasoning** (*interfaces.LLMReasoning) — optional generic controls; each LLM client maps them:
**Enabled** — requests reasoning/thinking on providers that support it (see below).
**Effort** — "none" … "xhigh"; OpenAI → reasoning_effort when non-empty; Gemini → ThinkingLevel when low / medium / high / minimal; Anthropic ignores (use `**Bud

Agent SDK for Go

Build production-grade AI agents in Go — backed by Temporal for durable, crash-resilient execution, or run in-process with zero setup. See Capabilities for the full feature set.

Versioning: Semantic versioning; published lines are git tags (e.g. v0.1.2). See the latest release — the README does not pin a patch number so it stays accurate after each tag. Note: Independent community library — not affiliated with Temporal Technologies.