deepseek-web-search

Overview Schema Source Related Servers Discussions Admin

DeepSeek Web Search

search

Read-only

Run structured web queries through DeepSeek and return raw JSON results with titles, URLs, snippets, dates, and optional full page content. Filter by site, language, and date range.

Instructions

Search the web with DeepSeek's search API and return the raw JSON response exactly as received.

The response is a JSON object with a results array; fields include rerank_score, title, url, snippet, summary, content, site_name, site_icon, date, and authority. Set need_content=true to include full page content (can be very large). Prefer the fetch tool for a specific URL.

query supports DeepSeek search syntax: site:github.com, -site:example.com, -term, "exact phrase", lang:zh,en, after:2025-01-01, before:2026. Structured filters are appended to query. Results are not filtered or truncated by this server. Billing: 5 CNY per 1,000 successful requests that produce results. Rate limit: 100 QPS.

Input Schema

TableJSON Schema

Name	Required	Description
`lang`	No	Preferred languages, for example ["zh", "en"].
`site`	No	Only include these sites. Multiple sites are joined with OR.
`after`	No	Only results published after this date: YYYY, YYYY-MM, or YYYY-MM-DD.
`count`	No	Number of results to return, 1-50. Default: 10.
`query`	Yes	Search text, 1-128 Unicode characters. Supports DeepSeek syntax: site:github.com, -site:example.com, -term, "exact phrase", lang:zh,en, after:2025-01-01, before:2026.
`before`	No	Only results published before this date: YYYY, YYYY-MM, or YYYY-MM-DD.
`exact_phrase`	No	Require this exact phrase.
`need_content`	No	Include full page content in each result. Default: false. Responses can be very large.
`ori_question`	No	The user's original question, 1-128 characters. Helps the search service understand intent.
`exclude_sites`	No	Exclude these sites.
`exclude_terms`	No	Exclude pages containing these terms.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 23, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only cover readOnly/openWorld; the description adds real operational context the agent cannot otherwise know: billing (5 CNY/1,000 requests producing results), a 100 QPS rate limit, and the fact that results are neither filtered nor truncated server-side. It also warns that need_content output can be very large.

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?

Well front-loaded — what it is, what comes back, the key flag, then syntax and billing. Dense with no filler, though the response-field list and syntax list make it longer than strictly necessary since the schema already repeats the query syntax.

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?

For an 11-parameter, no-output-schema search tool, the description covers return shape (results array with named fields), size risk, cost, rate limits, and syntax. Nothing an agent needs to call this correctly is missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3. The description still adds value by documenting DeepSeek query-syntax support and by clarifying a cross-parameter behavior not visible in the schema: structured filters are appended to the query string.

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 with DeepSeek's search API') and specifies the return contract ('raw JSON response exactly as received'). It also distinguishes itself from the sibling by naming 'fetch' for single-URL retrieval.

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?

Explicitly routes single-URL needs to the 'fetch' tool and gives a condition for need_content ('can be very large'). It stops short of describing when *not* to use search at all, but the alternative framing is clear enough to guide selection.

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

fetchA
searchA