mcp-retriever

io.github.keiranhaaxv0.0.24更新于 Oct 8, 2026

One MCP server for web search, page extraction, and cited research.

已验证STDIO仅桌面Web Search & ScrapingKnowledge & Memory

概览

AI 生成的概览

让助手跨多个提供商进行网络搜索、提取和抓取网页，并返回带引用的研究结果。

功能
通过 web_search_fused 将两三个搜索提供商的结果合并为一个去重后的排名，并在某个提供商失败时返回各提供商状态。可提取页面内容、抓取站点，并在启用存档回退时从 Wayback Machine 快照恢复 404 或 410 页面。可选的支出上限、冷却时间和大型结果分页访问有助于控制用量。
适用场景
当助手需要带引用的网络搜索和网页阅读，或希望同时查询多个搜索提供商并合并排名时使用。适合研究检索类工作流，尤其是希望提供商密钥不写入客户端配置文件的场景。
运行要求
通过 stdio 在本地运行，需要 Node.js 22 或更高版本。至少需要一个提供商密钥（Tavily、Brave、Exa、You.com、GitHub、Linkup、Firecrawl 或 Context.dev），或自建 SearXNG 实例。密钥保存在凭据文件中而非客户端配置；设置后需重启客户端。
安装前请注意
提供商密钥保存在本地凭据文件中，计费密钥检查需要用户同意。支出上限依赖提供商上报的用量而非估算成本，因此未必能限制实际支出。每个服务器实例共享同一信任边界，其结果存储不应供互不信任的客户端使用。搜索和页面抓取会把查询和网址发送给第三方提供商。

安装

在 SourceWeft 中

  1. 打开 控制台中的 mcp-retriever，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

mcp-retriever

One MCP server for web search, page extraction, and cited research. Use your own providers, combine their results, and keep API keys out of client configs.

  • Search together: query two or three providers, deduplicate URLs, and merge rankings with web_search_fused.
  • Read more: extract pages, crawl sites, and recover 404/410 pages from Wayback Machine snapshots when archive fallback is enabled.
  • Control usage: optional spending caps for provider-reported usage, cooldowns, and paged access to large results.

Supports Tavily, Brave, Exa, You.com, SearXNG, GitHub, Linkup, Firecrawl, and Context.dev. Configure only what you use.

Quickstart

Requires Node.js 22+ and a provider key, or your own SearXNG instance.

bash
npx -y mcp-retriever setup

Choose providers, save keys privately, and connect your MCP client. The wizard writes Claude Desktop and Cursor entries, or shows the command/configuration for Claude Code and Codex. Billable key checks require consent.

[Setup wizard and provider selection]

Keys are stored in ~/.config/mcp-retriever/credentials.env, not in client configs. Restart your client after setup.

Client connection and key management

[Connecting MCP clients]

Add, test, or remove keys:

bash
npx mcp-retriever keys

[Key management menu]

Screenshots show a demo session with fixture credentials and a mocked key-check response, not a live provider validation.

Example

Call web_search_fused with two configured search providers:

json
{	"query": "reciprocal rank fusion hybrid search",	"providers": ["brave", "exa"],	"limit": 3}

Results include source providers and merged rankings. If a provider fails, available results are returned with per-provider status.

Documentation

Each server instance shares one trust boundary. Do not use its result store for mutually untrusted clients. Spending caps depend on provider-reported usage, not estimated costs.

License and origins

MIT. Formerly named mcp-omnisearch; a maintained fork of Scott Spence's mcp-omnisearch. When upgrading this fork, rename OMNISEARCH_* settings to RETRIEVER_*, omnisearch:// resources to retriever://, and _meta.omnisearch to _meta.retriever. Preserve the old result store and spending ledger when moving to ~/.cache/mcp-retriever/results; Docker/MCPO clients must also change /omnisearch to /retriever.

来源：README.md，提交 e0fd4d6

工具

0
工具元数据尚未被收录。

版本历史

1
  1. v0.0.24最新Oct 8, 2026