Skip to main content
Glama
RedrockerLi

deepseek-web-search

by RedrockerLi
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DEEPSEEK_API_KEYYesDeepSeek API key. Required; if missing, the server can still start but tool calls return a configuration error.
DEEPSEEK_BASE_URLNoOptional DeepSeek base URL. Default is https://api.deepseek.com. Must not include /v1 or credentials.https://api.deepseek.com

Instructions

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.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
searchA

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.

fetchA

Fetch a URL through DeepSeek and return the raw JSON response exactly as received.

The response is a JSON object with title (string) and content (Markdown). The content is not truncated by this server. The URL must be an absolute HTTP/HTTPS URL of at most 8192 characters and must not contain credentials. Billing: 5 CNY per 1,000 successful fetches. Rate limit: 25 QPS.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
Let your AI agent see the webWeb-to-screenshot MCP for Claude, Cursor and Codex. No cookie banners. Free to start.snap-render.comAd

TDQS

A4.1/5.0

Scored across 2 tools

Disambiguation5/5

search and fetch have clearly distinct purposes: discovery via query vs. retrieval of a specific known URL. The search description even explicitly redirects agents to fetch for a specific URL, eliminating any overlap.

Naming Consistency5/5

Both tools use a single lowercase verb with no mixed conventions (no camelCase, no noun-only names). The pattern is fully predictable across the two-tool surface.

Tool Count4/5

Two tools is on the thin side, but for a narrowly scoped search-and-retrieve proxy it is exactly the right surface — no tool feels extraneous and none is missing. Slightly below 5 only because the count leaves no room for filter/parameter discovery aids.

Completeness4/5

Search plus fetch covers the full web-retrieval lifecycle with no dead ends, and both tools return raw upstream JSON. Minor gap: structured filters are mentioned as being 'appended to query' without explicit parameters, so agents must guess the syntax.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources