小遥搜索 MCP 工具 - 本地文件智能搜索(语义/全文/图像/语音/混合搜索)
npx skills add https://github.com/dtsola/xiaoyaosearch --skill xiaoyao-search
当需要搜索本地文件时使用此 Skill:
小遥搜索 MCP 服务器提供以下 5 个搜索工具:
query: string - 搜索关键词(1-500字符)limit: int - 返回结果数(1-100,默认20)threshold: float - 相似度阈值(0.0-1.0,默认0.5)file_types: string[] - 文件类型过滤(可选)query: string - 搜索关键词(1-500字符)limit: int - 返回结果数(1-100,默认20)file_types: string[] - 文件类型过滤(可选)query: string - 搜索关键词(1-500字符)limit: int - 返回结果数(1-100,默认20)threshold: float - 相似度阈值(0.0-1.0,默认0.5)file_types: string[] - 文件类型过滤(可选)image_path: string - 图片绝对路径limit: int - 返回结果数(1-100,默认20)threshold: float - 相似度阈值(0.0-1.0,默认0.5)audio_path: string - 音频绝对路径search_type: string - 搜索类型(semantic/fulltext/hybrid,默认semantic)limit: int - 返回结果数(1-100,默认20)threshold: float - 相似度阈值(0.0-1.0,默认0.5)Claude Code 通过 MCP 协议自动发现和调用工具:
用户:帮我找一下关于 Python 异步编程的文档
→ Claude Code 调用 semantic_search(query="Python 异步编程")
→ 返回搜索结果
→ Claude 基于结果回答用户
搜索结果返回 JSON 格式:
{
"total": 10,
"search_time": 0.523,
"results": [
{
"file_name": "async_guide.md",
"file_path": "D:/docs/async_guide.md",
"file_type": "markdown",
"relevance_score": 0.95,
"preview_text": "Python异步编程指南..."
}
]
}
用户:查找关于机器学习算法优化的文档
调用:semantic_search(
query="机器学习算法优化",
limit=10,
threshold=0.5
)
用户:查找包含 async def 的 Python 文件
调用:fulltext_search(
query="async def",
limit=20,
file_types=["python"]
)
用户:找一下跟这张图片相似的设计稿
调用:image_search(
image_path="C:/Users/test/reference.png",
limit=10
)
用户:(语音输入)帮我找一下上周的会议记录
调用:voice_search(
audio_path="C:/Users/test/voice.mp3",
search_type="semantic"
)
用户:全面搜索关于 Vue3 组件开发的资料
调用:hybrid_search(
query="Vue3 组件开发",
limit=20,
threshold=0.6
)
| 变量名 | 默认值 | 说明 |
|-------|--------|------|
| MCP_SSE_ENABLED | true | 启用 MCP SSE |
| MCP_SERVER_NAME | xiaoyao-search | 服务器名称 |
| MCP_DEFAULT_LIMIT | 20 | 默认结果数 |
| MCP_DEFAULT_THRESHOLD | 0.5 | 默认相似度阈值 |
| MCP_VOICE_ENABLED | true | 启用语音搜索 |
# 测试 MCP SSE 端点
curl http://127.0.0.1:8000/mcp
# 检查后端健康状态
curl http://127.0.0.1:8000/api/system/health
Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
Take dtsola/xiaoyao-search from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.