About DeepSeek Web Search
DeepSeek Web Search is an MCP server for clients that need web research through DeepSeek. It combines scored search results with Markdown extraction from individual pages.
Key features
- 01DeepSeek web search
- 02Relevance and authority scores
- 03Markdown page fetching
- 04Search operators and date filters
- 05Throttling and automatic retries
- 06Summary-first responses
Use cases
- 01Find relevant, authoritative web sources
- 02Fetch a page for model analysis
MCP support
Exposes `deepseek_search` and `deepseek_fetch` tools to MCP clients. Search uses DeepSeek's search engine and returns results as tool output for the connected model.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y mcp-deepseek-searchDEEPSEEK_API_KEYSecretDeepSeek API key from https://platform.deepseek.comLocal servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
2Saved tool list · updated 4d ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| count | integer | No | Number of results to return, 1-50. Default 10. |
| query | string | Yes | Search query, 1-128 Unicode chars. Supports site:, lang:, after:/before:, "phrases" and -exclusions. |
| localization | string | No | User IP address used to localize results. Only pass it when appropriate and with consent. |
| need_content | boolean | No | Include full page content per result (truncated at 8000 chars each). Default false. |
| ori_question | string | No | The user's original question, if the query was rewritten. Improves intent understanding. |
Details
From the project READMEmcp-deepseek-search
An Model Context Protocol server that exposes DeepSeek's web Search and Fetch tools to any MCP client — Claude Desktop, Claude Code, Cursor, Cline, ZCode, and more.
Works with any LLM: the search runs on DeepSeek's own search engine, but the results are returned to your existing model as ordinary tool output.
Features
deepseek_search— web search backed by DeepSeek's search engine, with two quality signals per result:rerank_score(0–3): relevance; ≥ 1.5 = highly relevantauthority(0–4,-1unknown): source authority; ≥ 3 = highly authoritative
deepseek_fetch— fetch a single page and get its main content as Markdown- Powerful query syntax:
site:,-site:,-term,"exact phrase",-"phrase",lang:zh,en,after:YYYY-MM-DD,before:YYYY-MM-DD - Built-in throttling (stays under the 5 QPS account limit) and automatic retry on 408/429/5xx
- Response-size friendly: summaries by default, full page text only on request
Setup
- Get an API key at platform.deepseek.com (web tools are billed at ¥5 per 1,000 successful calls, charged to your DeepSeek account — failed calls and empty results are not billed).
- Add the server to your MCP client config:
Claude Desktop / Cursor / Cline / most clients
{
"mcpServers": {
"deepseek-web": {
"command": "npx",
"args": ["-y", "mcp-deepseek-search"],
"env": {
"DEEPSEEK_API_KEY": "sk-your-key-here"
}
}
}
}
ZCode
Add the same mcpServers block to your ZCode MCP settings (Settings → MCP → Add server).
From source
git clone https://github.com/Matthewyin/deepseek-mcp
cd deepseek-mcp && npm install && npm run build
node dist/index.js # stdio MCP server
Tools
deepseek_search
| Parameter | Type | Required | Description |
|---|---|---|---|
query | string | yes | 1–128 chars; supports the search syntax above |
count | integer | no | 1–50 results, default 10 (does not affect billing) |
ori_question | string | no | The user's original question — improves intent matching when the query was rewritten |
localization | string | no | User IP to localize results (pass only with consent) |
need_content | boolean | no | Include full page text per result (each truncated at 8,000 chars). Default false |
Each result includes title, url, snippet (short, for display), summary (long, for feeding to a model), rerank_score, authority, site_name, date, and optionally content.
deepseek_fetch
| Parameter | Type | Required | Description |
|---|---|---|---|
url | string | yes | Plain http(s) URL, max 8,192 chars, no embedded credentials |
Returns title + Markdown content (truncated at 30,000 chars).
Example
Ask your agent: "用 deepseek_search 搜一下最近一周关于 MCP 的大新闻,挑权威来源,再用 deepseek_fetch 读全文总结" — or in English: "Search for recent DeepSeek news, keep only results with authority ≥ 3, fetch the top one and summarize."
Notes & limits
- Rate limit is 5 QPS per DeepSeek account (shared across all your API keys); the server throttles automatically.
- HTTP 402 means your DeepSeek balance ran out; 401 means the key is invalid.
- Page content depends on the target site's availability and access policy.
- This is an unofficial community wrapper; not affiliated with DeepSeek.
Development
npm install
npm run build
DEEPSEEK_API_KEY=sk-... npm test # end-to-end test against the real API
Releases are automated via GitHub Actions: pushing a v* tag publishes to npm and the official MCP Registry.
License
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.