Schema | deepseek-search-mcp

deepseek-search-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`DEEPSEEK_DEBUG`	No	Set to 1 to output debug logs to stderr	0
`DEEPSEEK_MODEL`	No	Model name	deepseek-v4-flash
`DEEPSEEK_API_KEY`	Yes	DeepSeek API Key (required)
`DEEPSEEK_BASE_URL`	No	API endpoint	https://api.deepseek.com
`DEEPSEEK_TIMEOUT_S`	No	HTTP timeout in seconds	180
`DEEPSEEK_MAX_OUTPUT`	No	Single-turn search synthesis answer max output tokens	8192
`DEEPSEEK_DEEP_QUERIES`	No	Deep search sub-query count (range 1-6)	4

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`	{ "listChanged": false }

Functions exposed to the LLM to take actions

Name	Description
web_searchA	联网搜索（标准模式）。基于 DeepSeek V4-Flash 原生联网搜索：自动规划多次搜索、阅读并核实来源、返回带引用的结构化答案。适合日常查询、新闻、事实确认。
web_search_fastA	联网搜索（快速模式）。使用低推理强度 + 精简指令优先响应速度，通常 1-2 轮搜索后直接给出简洁答案。适合对时效敏感、无需深度核验的查询。
web_search_deepA	深度联网搜索（高准确性模式）。先把问题拆解为多个子查询分别检索，再由 DeepSeek V4-Flash 交叉核验、综合成带引用的最终答案。适合事实核查、研究报告、技术调研、需要多来源验证的场景。耗时更长。
healthA	健康检查：验证 DeepSeek API key 与联网搜索能力是否可用。

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/zouyuanqing/deepseek-search-mcp'

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