Sylex Search

io.github.MastadoonPrime由 GitHub 账号 MastadoonPrime 发布v0.1.2更新于 Oct 25, 2026

Universal search engine for AI agents. Discover products, services, and businesses via MCP.

已验证SSE可网页运行网页搜索与抓取商业与电商

概览

AI 生成的概览

Sylex Search 是一个远程 MCP 搜索索引，让助手发现、比较和评估产品、服务与企业，并注册或管理其自身的条目。

可以做什么
按自然语言查询搜索索引，返回带匹配分数的排序结果，并可浏览分类和查找相似条目作为替代方案。
适用场景
当助手需要查找、比较或推荐产品、服务或企业（例如软件包、SaaS 工具或供应商），并希望获得结构化结果而非抓取网页时使用。
运行要求
需要远程 SSE 端点，或通过 npx 在本地运行 npm 包（本地方式需要 Node.js）。托管端点未声明需要账号、API 密钥或配置。自托管需要 Supabase URL 和密钥，以及传输方式和端口设置。
安装前请注意
列表管理工具会写入共享的公开索引：注册会新增条目并返回所有者令牌，认领会通过 URL 证明验证所有权，更新会修改条目详情，因此更改对其他智能体可见。所有者令牌应保密。查询和条目数据会发送给托管第三方。README 的自托管部分要求提供 Supabase 凭据。README 中关于索引规模、延迟和成本的说明来自提供方，未经核实。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Sylex Search，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。

Web executable，通过 SSE。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.MastadoonPrime%2Fsylex-search/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "sylex-search": {
      "type": "sse",
      "url": "https://mcp-server-production-38c9.up.railway.app/sse"
    }
  }
}

README

Sylex Search — Universal Search for AI Agents

[Smithery]

Sylex Search is an MCP server that lets AI agents discover, evaluate, and compare products, services, and businesses across every category.

Think of it as Google, but for agents — returns structured JSON instead of web pages, zero latency, zero cost per query.

Connect

SSE (recommended)

Add to your MCP client config (Claude Desktop, Claude Code, Cursor, etc.):

json
{  "mcpServers": {    "sylex-search": {      "url": "https://search.sylex.ai/sse"    }  }}

Via Smithery

bash
smithery mcp add mastadoonprime/sylex-search

Via npm (local stdio proxy)

bash
npx sylex-search

Why this exists

McKinsey projects $1 trillion in sales will flow through AI agents. When agents handle purchasing, booking, hiring, and sourcing, they need a way to find the right business for the job — whether that's a contractor, a restaurant, a SaaS platform, or a parts supplier. If a business isn't in the index, it's invisible to agents.

Sylex Search is the discovery layer for agent commerce.

What's in the index

14,000+ entries and growing:

SourceCountWhat
npm~3,000JavaScript/TypeScript packages
crates.io~3,000Rust crates
Wikidata~2,800Products, companies, protocols
MCP servers~2,100MCP tools from awesome-mcp-servers
GitHub~1,900Popular repositories
PyPI~1,000Python packages
SaaS~100SaaS products

The index started with software packages as seed data, but Sylex Search is not software-specific. The schema and tools support any product, service, or business.

Tools

Search & Discovery

ToolDescription
search.discoverSearch the index by natural language query. Returns ranked results with fit scores.
search.detailsGet full product data by ID — pricing, features, integrations, reviews.
search.compareSide-by-side comparison of 2-5 products.
search.categoriesBrowse all categories and subcategories with counts.
search.alternativesFind similar products scored by relevance.
search.feedbackReport issues or suggest improvements.

Listing Management

ToolDescription
manage.registerAdd a new product or business to the index. Returns an owner token.
manage.claimVerify ownership of an existing listing via URL proof.
manage.updateUpdate listing details (description, pricing, category, etc.).
manage.list_mcpAdd MCP connection config so other agents can discover and connect.

Prompts

PromptDescription
search-workflowStep-by-step guide: discover → details → compare → recommend.
product-evaluationThorough evaluation: find product → get details → find alternatives → verdict.

Example queries

  • "react state management" → zustand, redux, mobx, jotai
  • "python web framework" → Django, Flask, FastAPI, Sanic
  • "project management tool for small teams" → Notion, Linear, Asana
  • "CRM with Slack integration" → HubSpot, Salesforce, Pipedrive

Use with agent frameworks

LangChain

python
from langchain_mcp_adapters.client import MultiServerMCPClient
async with MultiServerMCPClient({    "sylex": {"url": "https://search.sylex.ai/sse", "transport": "sse"}}) as client:    tools = client.get_tools()

OpenAI Agents SDK

python
from agents import Agentfrom agents.mcp import MCPServerSse
server = MCPServerSse(url="https://search.sylex.ai/sse")agent = Agent(name="shopper", mcp_servers=[server])

Microsoft AutoGen

python
from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
params = SseServerParams(url="https://search.sylex.ai/sse")async with McpWorkbench(server_params=params) as bench:    tools = await bench.list_tools()

CrewAI

python
from crewai import Agentfrom crewai_tools import MCPTool
sylex_tools = MCPTool.from_sse(url="https://search.sylex.ai/sse")agent = Agent(role="researcher", tools=sylex_tools)

Architecture

  • Zero LLM calls — deterministic search (SQLite FTS + custom ranking)
  • Millisecond responses — no API calls, no model inference
  • $0 per query — no token costs
  • Structured JSON — agents parse directly, no scraping needed
  • Agents-first — no dashboards, no accounts, no human UI
  • MCP native — built on the Model Context Protocol standard
  • Self-service — any business can register, claim, and manage its listing through tool calls

Server metadata

PropertyValue
TransportSSE
Quality score100/100 (Smithery)
Version0.1.2
Tools11
Prompts2
Auth requiredNo
Config requiredNo

For agents

Server card available at:

GET https://search.sylex.ai/.well-known/mcp/server-card.json

This returns full server metadata including all tools, prompts, and connection details — no MCP session required.

Self-hosting

bash
pip install -r requirements.txtexport AC_SUPABASE_URL=your-supabase-urlexport AC_SUPABASE_KEY=your-supabase-keyexport TRANSPORT=sseexport PORT=8080cd src && python server.py

License

AGPL-3.0 — see LICENSE for details.

来源：README.md，提交 6786178

工具

0
SourceWeft 尚未读取此服务器的工具。

版本历史

1
  1. v0.1.2最新Sep 16, 2026

评分

已满足适用检查项的 85%

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 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分

    请让服务器在无凭据时响应 tools/list，或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分