Schema | Metaso Search MCP Server

Metaso Search MCP Server

Describes the environment variables required to run the server.

Name	Required	Description	Default
`METASO_API_KEY`	Yes	Metaso API key / 秘塔 API 密钥
`METASO_TIMEOUT`	No	Timeout in milliseconds for API requests	60000
`METASO_BASE_URL`	No	Base URL for Metaso API	https://metaso.cn/api/v1
`METASO_DEFAULT_SEARCH_SIZE`	No	Default number of search results (1-100)	10
`METASO_DEFAULT_SEARCH_SCOPE`	No	Default search scope: webpage, document, paper, image, video, podcast
`METASO_DEFAULT_READER_FORMAT`	No	Reader output format: markdown or json	markdown
`METASO_DEFAULT_CONCISE_SNIPPET`	No	Whether to use concise snippets (true/false)
`METASO_DEFAULT_INCLUDE_SUMMARY`	No	Whether to include summary in results (true/false)
`METASO_DEFAULT_INCLUDE_RAW_CONTENT`	No	Whether to include raw content (true/false)

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{}

Functions exposed to the LLM to take actions

Name	Description
metaso_searchA	使用秘塔AI搜索进行多维度搜索。支持的搜索范围 (scope): webpage: 网页搜索 (默认) document: 文库搜索 paper: 学术论文搜索 image: 图片搜索 video: 视频搜索 podcast: 播客/博客搜索特色功能: includeSummary: 通过网页摘要增强召回 includeRawContent: 抓取来源网页原文 conciseSnippet: 返回精简的原文匹配信息
metaso_readerA	读取指定URL的网页内容并转换为结构化格式。支持的输出格式: markdown: 返回Markdown格式的网页内容 (默认) json: 返回JSON格式，包含标题、URL、内容等结构化信息适用场景: 提取新闻文章内容获取网页正文将网页转换为可读格式

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/SecretRichGarden/metasota-API-MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server