Deepsearch

io.github.CloudCorpRecords由 GitHub 账号 CloudCorpRecords 发布v0.1.0更新于 Oct 31, 2026

Neural web search, code context, and page crawling through the Exa API.

发布方自己的服务：DeepSearch

已验证STDIO仅桌面网页搜索与抓取开发者工具

概览

AI 生成的概览

本地 MCP 服务器，为助手提供基于 Exa 的神经网页搜索、代码上下文包和整页抓取能力。

可以做什么
  • 用 Exa 搜索网页，返回匹配页面及其正文、标题和出版信息
  • 针对编程问题收集代码示例与文档摘录，并按所选 token 预算裁剪
  • 按 URL 抓取指定页面的完整正文
  • 三个工具都支持 1000 至 50000 的 token 预算，空结果或抓取失败会作为工具错误返回
适用场景
适合需要最新网络资料、编程问题的代码示例与文档，或已知 URL 页面的完整正文时使用，无需自行搭建搜索集成。
运行要求
通过 npx 或 Docker 镜像以本地 stdio 进程运行；需要 Exa API 密钥，放在 EXA_API_KEY 环境变量中，并以 x-api-key 请求头发送；需要访问 Exa API 的网络；仅限桌面端。
安装前请注意
需要 Exa API 密钥，该密钥保存在客户端配置中并发送给 Exa；查询内容和请求的 URL 会发送到第三方 API，避免提交机密材料；用量可能由 Exa 按你的账户计费。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Deepsearch，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

deepsearch

deepsearch asks Exa's neural index questions the way a researcher would. A plain search returns the pages that best match the meaning of a query, with their text already pulled in. A code question gets a context pack instead: examples and documentation excerpts gathered from across the web and sized to a token budget you choose. And when you already know the page you want, a crawl fetches that one page and hands back its words. It runs from the command line or as an MCP server for agents.

An Exa API key is required. Put it in the EXA_API_KEY environment variable; the key is sent to the API as the x-api-key header and never appears in output. When the variable is missing, every operation fails with an error that names it.

Install

bash
npx @reneturcios/deepsearch search "vector index tradeoffs"

Or run the container image:

bash
docker run -i -e EXA_API_KEY ghcr.io/cloudcorprecords/deepsearch

The container defaults to the MCP server (see below). Pass CLI arguments to use it as a CLI instead.

CLI

bash
export EXA_API_KEY="your api key"
# Web search; --num-results defaults to 8deepsearch search "ferry electrification programs"deepsearch search "ferry electrification programs" --num-results 5
# Code context; --tokens sets the budget (1000-50000, default 5000)deepsearch code "React useState hook examples" --tokens 3000
# Fetch one page in fulldeepsearch crawl https://example.com/some/articledeepsearch crawl https://example.com/some/article --tokens 2000
# Machine-readable output for any commanddeepsearch search "ferry electrification programs" --json
deepsearch --version

Exit codes: 0 on success, 1 when an operation fails (including a missing EXA_API_KEY or an API error), 2 for usage errors.

MCP server

One bin serves both faces. The mcp subcommand starts a stdio MCP server:

bash
npx -y @reneturcios/deepsearch mcp

MCP client configuration:

json
{  "mcpServers": {    "deepsearch": {      "command": "npx",      "args": ["-y", "@reneturcios/deepsearch", "mcp"],      "env": { "EXA_API_KEY": "your api key" }    }  }}

Tools

These are the original server's default-enabled tools:

ToolInputWhat it returns
web_search_exaquery (string, required), numResults (number, optional, default 8)Matching pages as a numbered text block: title, URL, publication details when known, and the page text the API supplied.
get_code_context_exaquery (string, required), tokensNum (number, optional, 1000–50000, default 5000)Code examples and documentation excerpts for the question, each headed by its source, trimmed to the token budget.
crawling_exaurl (string, required), tokensNum (number, optional, default 5000)The full text of that one page, titled, trimmed to the token budget.

Token budgets are clamped to the documented 1000–50000 range and are applied at roughly four characters per token. An empty result set is reported as such; a page the API cannot fetch, a missing key, or a failed API call is reported as a tool error.

Development

bash
npm installnpm run build   # tsc -> dist/npm test        # node test runner over test/*.test.ts, no network (fake fetch fixtures)npm run dev     # run the CLI from source via tsx

License

MIT — see LICENSE.

来源：README.md，提交 eb25132

工具

3

web_search_exa

Search the web with Exa and return relevant pages with their text content.

输入参数query必填numResults

get_code_context_exa

Find code examples and documentation for a programming question and return them as context.

输入参数query必填tokensNum

crawling_exa

Fetch the full text content of a specific web page by URL.

输入参数url必填tokensNum

版本历史

1
  1. v0.1.0最新Oct 31, 2026

评分

已满足适用检查项的 90%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分
  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头，或保持端点能够响应探测，以便判定其认证方式。

  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

其他 Deepsearch 集成

DeepSearch

app.deepsearch官方发布者

DeepSearch 是一个远程 MCP 服务器，让助手从公开来源调查个人和公司，返回带来源的档案、答案和查询结果。

Streamable HTTP可网页运行
网页搜索与抓取12 个工具Oct 25, 2026