Skip to main content
Glama
Sign In
deepseek-search-mcp

deepseek-search-mcp

by Taosheng777
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

deepseek_search

Read-only

Search the web through DeepSeek's own engine with site, language, and date filters, and optionally return page content as Markdown for AI coding clients.

Instructions

Search the web with DeepSeek's own search engine. 用 DeepSeek 自研搜索引擎搜索网页。按次计费（每次 0.005 元，与 count 无关）。

query 支持语法：site:github.com（多个用 OR 连接）、-site:x.com、"精确短语"（弱约束）、
  -关键词、lang:zh 或 lang:en、after:2026-01-01、before:2026。
  实用写法：中文检索加 lang:zh 防混入外文；找轮子加 site:github.com；找经验可加 -site:edu.cn 避开高校新闻稿。
include_content：同时返回正文，比逐条 fetch 省钱省时；总输出约 2 万字，条数越多每条正文越短，建议 count≤10。
exclude_doc_farms：默认过滤 book118/人人文库/豆丁/道客巴巴/百度文库等转卖文档站。
结果顺序沿用 DeepSeek 排序；score 与 authority 只作参考，不代表内容可靠。缺日期的结果标为"日期未知"。

Input Schema

NameRequiredDescriptionDefault
countNo返回条数
queryYes搜索词，1-128 字符，可含 site:/lang:/after: 等语法
include_contentNo是否附带每条结果的正文（按输出上限截断）
exclude_doc_farmsNo是否过滤转卖文档站

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the readOnly/openWorld annotations: per-call pricing (0.005 yuan, independent of count), approximate total output size (~20k chars), the shrinkage of per-result content as count grows, default doc-farm filtering with named sites, DeepSeek-native result ordering, and the caveat that score/authority are only advisory. These are exactly the operational facts an agent needs before calling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose and dense with useful detail, but the opening sentence is duplicated bilingually and the syntax list is a little sprawling. Almost every line earns its place, with minor redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly takes on return-value semantics: result ordering, the meaning of score/authority, and the 'date unknown' labeling for undated results. Combined with the pricing and size notes, nothing needed to invoke it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Even though schema coverage is 100%, the description substantially enriches every parameter: it enumerates query syntax (site: with OR, -site:, quotes as a weak constraint, lang:, after:/before:), explains the cost/size tradeoff of include_content, and names what exclude_doc_farms actually removes. This is real meaning beyond the terse schema strings.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Search the web'), and implicitly distinguishes itself from the sibling deepseek_fetch by noting that include_content is 'cheaper and faster than fetching each result individually'. An agent can tell what this tool does without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete practical guidance with conditions: add lang:zh for Chinese searches, use site:github.com to find libraries, add -site:edu.cn to avoid university press releases, and recommends count<=10 when include_content is on. It names the fetch alternative, though it never states an explicit when-not-to-use condition.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools