Exa Search 扩展
本教程介绍如何将 Exa MCP 服务器 添加为 goose 扩展,以启用 AI 驱动的网页搜索。
快速安装
配置
信息
运行此命令需要在系统上安装 Node.js,因为它使用 npx。
- goose Desktop
- goose CLI
- Launch the installer
- Click
Yesto confirm the installation - Get your Exa API Key and paste it in
- Click
Add Extension - Click the button in the top-left to open the sidebar
- Navigate to the chat
- Run the
configurecommand:
goose configure
- Choose to add a
Command-line Extension.
┌ goose-configure
│
◇ What would you like to configure?
│ Add Extension
│
◆ What type of extension would you like to add?
│ ○ Built-in Extension
│ ● Command-line Extension (Run a local command or script)
│ ○ Remote Extension (Streamable HTTP)
└
- Give your extension a name.
┌ goose-configure
│
◇ What would you like to configure?
│ Add Extension
│
◇ What type of extension would you like to add?
│ Command-line Extension
│
◆ What would you like to call this extension?
│ Exa Search
└
- Enter the command to run when this extension is used.
┌ goose-configure
│
◇ What would you like to configure?
│ Add Extension
│
◇ What type of extension would you like to add?
│ Command-line Extension
│
◇ What would you like to call this extension?
│ Exa Search
│
◆ What command should be run?
│ npx -y exa-mcp-server
└
- Enter the number of seconds goose should wait for actions to complete before timing out. Default is
300seconds.
┌ goose-configure
│
◇ What would you like to configure?
│ Add Extension
│
◇ What type of extension would you like to add?
│ Command-line Extension
│
◇ What would you like to call this extension?
│ Exa Search
│
◇ What command should be run?
│ npx -y exa-mcp-server
│
◆ Please set the timeout for this tool (in secs):
│ 300
└
- Enter a description for this extension.
┌ goose-configure
│
◇ What would you like to configure?
│ Add Extension
│
◇ What type of extension would you like to add?
│ Command-line Extension
│
◇ What would you like to call this extension?
│ Exa Search
│
◇ What command should be run?
│ npx -y exa-mcp-server
│
◇ Please set the timeout for this tool (in secs):
│ 300
│
◆ Enter a description for this extension:
│ AI 驱动的网页搜索
└
- Add an environment variable for this extension.
信息
获取你的 Exa API Key 并粘贴到此处。你可以在 exa.ai 注册,然后在控制台的 API keys 页面获取 API 密钥。
┌ goose-configure
│
◇ What would you like to configure?
│ Add Extension
│
◇ What type of extension would you like to add?
│ Command-line Extension
│
◇ What would you like to call this extension?
│ Exa Search
│
◇ What command should be run?
│ npx -y exa-mcp-server
│
◇ Please set the timeout for this tool (in secs):
│ 300
│
◇ Enter a description for this extension:
│ AI 驱动的网页搜索
│
◆ Would you like to add environment variables?
│ Yes
│
◇ Environment variable name:
│ EXA_API_KEY
│
◇ Environment variable value:
│ ▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪
│
◇ Add another environment variable?
│ No
│
└ Added Exa Search extension
使用示例
Exa MCP 服务器让 goose 的交互具备 AI 驱动的网页搜索能力。Exa 提供的高级搜索能力包括:
- 神经搜索、关键词搜索和自动搜索模式
- 以全文、高亮或摘要形式检索内容
- 按类别筛选(新闻、论文、公司等)
- 按域名和日期范围筛选
goose 提示词
查找关于大语言模型推理能力的近期研究论文,并总结主要发现。
goose 输出
我将使用 Exa 搜索关于 LLM 推理的近期研究论文。
─── web_search_exa | exa ──────────────────────────
query: large language model reasoning capabilities research paper
category: research paper
以下是近期 LLM 推理研究的主要发现:
1. 思维链推理:
- 近期论文表明,显式的思维链提示能显著提升多步推理任务的表现
- 用推理轨迹训练的模型,对新型问题的泛化更好
2. 数学与逻辑推理:
- 新基准显示,LLM 在算术和形式逻辑上有所进步,但在组合推理上仍然困难
- 将神经方法与符号求解器结合的混合方法显示出前景
3. 常识推理:
- 研究表明,扩大模型规模仍能持续提升常识推理基准
- 但在需要物理直觉或日常事件时间推理的任务上,模型仍然会失败
4. 局限与未来方向:
- 多篇论文指出存在“推理捷径”:模型利用数据集模式,而不是进行真正的推断
- 检索增强推理的研究显示,有可能把模型输出锚定在已核实的事实上
需要我针对其中某个主题搜索更多细节吗?
提示
Exa 支持多种搜索类型,包括面向语义查询的神经搜索,以及智能组合多种策略的自动模式。你还可以按类别、域名和日期范围筛选结果,让检索更有针对性。