Enables AI agents to perform web searches and convert web pages into Markdown using the DeepSeek Search & Fetch API.
Also known as esticklack/seekfetch
- Stars
- 2
- Tools
- 3
- Downloads, 30 days
- —
- Latest version
- 0.1.0
- Last commit
- Oct 18, 2026
- License
- MIT
What is seekfetch MCP?
seekfetch enables AI agents to perform web searches and convert web pages into Markdown using the DeepSeek Search & Fetch API. It exposes 3 tools, such as deepseek_search, deepseek_fetch, deepseek_research.
Summary generated from the project's README
About seekfetch MCP server
seekfetch provides AI agents with the ability to perform web searches and convert web pages into Markdown format. It functions as a client for the DeepSeek Search and Fetch API, requiring a personal API key from the DeepSeek platform to operate. The server runs locally via stdio and is compatible with various MCP clients including Claude Desktop, Cursor, VS Code, and Claude Code.
Users can access three primary tools: deepseek_search for ranked results with summaries, deepseek_fetch for retrieving specific URLs as Markdown, and deepseek_research for comprehensive queries that return top-scoring pages with their full content. The system is designed for efficiency by calling dedicated endpoints directly rather than using a chat model, which helps manage token usage. It also includes production-ready features like request pacing to respect the 5 QPS account limit and automatic retries for specific error codes.
Written from the project's README. Every use case is checked against a quote from it.
How to install seekfetch MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall seekfetch MCP in Claude Code
$ claude mcp add --env 'DEEPSEEK_API_KEY=<YOUR_DEEPSEEK_API_KEY>' seekfetch -- npx -y seekfetch mcpInstall seekfetch MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"seekfetch": {
"command": "npx",
"args": [
"-y",
"seekfetch",
"mcp"
],
"env": {
"DEEPSEEK_API_KEY": "<YOUR_DEEPSEEK_API_KEY>"
}
}
}
}Install seekfetch MCP in VS Code
.vscode/mcp.json
{
"servers": {
"seekfetch": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"seekfetch",
"mcp"
],
"env": {
"DEEPSEEK_API_KEY": "<YOUR_DEEPSEEK_API_KEY>"
}
}
}
}Install seekfetch MCP in VS Code CLI
$ code --add-mcp '{"name":"seekfetch","type":"stdio","command":"npx","args":["-y","seekfetch","mcp"],"env":{"DEEPSEEK_API_KEY":"<YOUR_DEEPSEEK_API_KEY>"}}'Install seekfetch MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"seekfetch": {
"command": "npx",
"args": [
"-y",
"seekfetch",
"mcp"
],
"env": {
"DEEPSEEK_API_KEY": "<YOUR_DEEPSEEK_API_KEY>"
}
}
}
}Install seekfetch MCP in Codex
$ codex mcp add seekfetch --env 'DEEPSEEK_API_KEY=<YOUR_DEEPSEEK_API_KEY>' -- npx -y seekfetch mcpInstall seekfetch MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.seekfetch] command = "npx" args = ["-y", "seekfetch", "mcp"] [mcp_servers.seekfetch.env] DEEPSEEK_API_KEY = "<YOUR_DEEPSEEK_API_KEY>"
Install seekfetch MCP in Gemini CLI
$ gemini mcp add -s user -e 'DEEPSEEK_API_KEY=<YOUR_DEEPSEEK_API_KEY>' seekfetch npx -- -y seekfetch mcpInstall seekfetch MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"seekfetch": {
"command": "npx",
"args": [
"-y",
"seekfetch",
"mcp"
],
"env": {
"DEEPSEEK_API_KEY": "<YOUR_DEEPSEEK_API_KEY>"
}
}
}
}Started by HostedMCP on 16 Nov 2026
We ran this command for seekfetch 0.1.0 in an isolated container with no network and no keys. It answered and listed 3 tools.
seekfetch MCP tools 3
Read from the server with tools/listdeepseek_searchRead-onlySearch the live web with DeepSeek's search engine. Returns ranked results with a model-ready summary per result (capped at 800 chars by default). rerank_score ranges 0-3; >= 1.5 is high quality. Use this to discover sources; then call deepseek_fetch on a URL for the full page, or use deepseek_research to do both in one step. The query is limited to 128 characters including filters and supports operators: "exact phrase", -term, -"phrase".
deepseek_fetchRead-onlyFetch a web page through DeepSeek and return its content as Markdown. Long pages are returned in chunks: when the output says to call again with an offset, do so to read further.
deepseek_researchRead-onlyAnswer-oriented web research in one call: searches, keeps the best-scoring results and returns their full page content with numbered sources for citation. Prefer this over search+fetch when you need to read sources, not just find them.
| deepseek_search | Search the live web with DeepSeek's search engine. Returns ranked results with a model-ready summary per result (capped at 800 chars by default). rerank_score ranges 0-3; >= 1.5 is high quality. Use this to discover sources; then call deepseek_fetch on a URL for the full page, or use deepseek_research to do both in one step. The query is limited to 128 characters including filters and supports operators: "exact phrase", -term, -"phrase". | Read-only |
| deepseek_fetch | Fetch a web page through DeepSeek and return its content as Markdown. Long pages are returned in chunks: when the output says to call again with an offset, do so to read further. | Read-only |
| deepseek_research | Answer-oriented web research in one call: searches, keeps the best-scoring results and returns their full page content with numbered sources for citation. Prefer this over search+fetch when you need to read sources, not just find them. | Read-only |
Configuration
DEEPSEEK_API_KEYRequiredSecretYour DeepSeek API key (platform.deepseek.com)
| Name | Description | |
|---|---|---|
| DEEPSEEK_API_KEY | Your DeepSeek API key (platform.deepseek.com) | RequiredSecret |
Automated checks
Ran Nov 12, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packagePass
- Remote endpoint uses HTTPSNot checked
- Destructive tools are labelledPass
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesPass
README
View on GitHubseekfetch
Web search and page-to-Markdown for AI agents, powered by the DeepSeek Search & Fetch API. One package, three ways to use it: an MCP server, a CLI, and a TypeScript library.
Unofficial community project. seekfetch is not affiliated with, endorsed by, or sponsored by DeepSeek. It is a client for DeepSeek's public API and needs your own API key.
Why
- Calls the dedicated endpoints (
/v1/tools/search,/v1/tools/fetch). No chat model sits in between, so a search costs one API request and no model tokens. - Search, fetch and research.
researchreturns the best pages with their content from a single search request, and only fetches the pages that came back empty. - Built for context windows. It returns DeepSeek's model-ready summaries by default, filters by relevance score, and pages through long documents with an offset.
- Production behavior. It retries 408/429/5xx with backoff and honors
Retry-After. It paces requests to the 5 QPS account limit and validates inputs locally so bad requests never cost a call. It parses responses tolerantly, so new or missing fields don't break it.
Quick start
- Get an API key at platform.deepseek.com.
- Add seekfetch to your MCP client (below), or run it from the shell:
export DEEPSEEK_API_KEY=sk-...
npx -y seekfetch search "model context protocol registry"
Requires Node.js 22.12 or later.
MCP setup
The server runs over stdio with npx -y seekfetch mcp.
claude mcp add seekfetch -e DEEPSEEK_API_KEY=sk-... -- npx -y seekfetch mcp
{
"mcpServers": {
"seekfetch": {
"command": "npx",
"args": ["-y", "seekfetch", "mcp"],
"env": { "DEEPSEEK_API_KEY": "sk-..." }
}
}
}
{
"mcpServers": {
"seekfetch": {
"command": "npx",
"args": ["-y", "seekfetch", "mcp"],
"env": { "DEEPSEEK_API_KEY": "sk-..." }
}
}
}
{
"inputs": [
{ "type": "promptString", "id": "deepseek-key", "description": "DeepSeek API key", "password": true }
],
"servers": {
"seekfetch": {
"type": "stdio",
"command": "npx",
"args": ["-y", "seekfetch", "mcp"],
"env": { "DEEPSEEK_API_KEY": "${input:deepseek-key}" }
}
}
}
[mcp_servers.seekfetch]
command = "npx"
args = ["-y", "seekfetch", "mcp"]
env = { DEEPSEEK_API_KEY = "sk-..." }
On Windows, if your client can't find npx, use "command": "cmd" with "args": ["/c", "npx", "-y", "seekfetch", "mcp"].
Tools
| Tool | What it does |
|---|---|
deepseek_search |
Ranked web results with a summary each (capped at 800 chars; summary_chars to change). Optional filters: sites, exclude_sites, lang, after, before, min_score; include_content adds page text. |
deepseek_fetch |
A URL as Markdown. Long pages come in chunks of max_chars; continue with offset. |
deepseek_research |
Question → top-scoring pages with content and numbered sources, in one call. |
All tools are read-only.
CLI
npm i -g seekfetch # or prefix each command with npx -y
seekfetch search "rust async runtimes" -n 5 --min-score 1.5
seekfetch search "mcp server" --site github.com --lang en --after 2026-01-01
seekfetch research "how is the DeepSeek search API priced?" -o notes.md
seekfetch fetch https://example.com --max-chars 20000
seekfetch search "query" --json | jq '.results[].url'
Run seekfetch <command> --help for every flag.
Agent skill
skills/seekfetch/SKILL.md teaches agents with a shell (Claude Code, Codex and others that read SKILL.md) when and how to use the CLI. Copy the folder into your agent's skills directory, for example ~/.claude/skills/seekfetch/.
Library
import { DeepSeekWebClient, buildQuery, research } from "seekfetch";
const client = new DeepSeekWebClient({ apiKey: process.env.DEEPSEEK_API_KEY! });
const { results } = await client.search({
query: buildQuery("vector databases", { sites: ["github.com"], after: "2026" }),
count: 10,
});
const page = await client.fetch("https://example.com"); // { title, content (Markdown) }
const report = await research(client, { question: "What changed in MCP this year?", maxPages: 3 });
Configuration
| Variable | Default | |
|---|---|---|
DEEPSEEK_API_KEY |
— | Required. |
DEEPSEEK_BASE_URL |
https://api.deepseek.com |
Override for proxies. |
DEEPSEEK_TIMEOUT_MS |
60000 |
Per attempt. |
DEEPSEEK_MAX_RETRIES |
3 |
For 408, 429, 5xx and network errors. |
API limits and pricing
As documented by DeepSeek on 2026-10-18; check the Search & Fetch guide for current terms.
- Queries are limited to 128 characters, filters included.
countis 1–50. - Observed in practice: summaries run 1,000–3,500 characters (the docs say 600–800), page content from search is capped around 20,000 characters, and
site:is a strong preference rather than a strict filter. - 5 QPS per account for search, and separately for fetch. Fetch also has a per-domain limit.
- Billing is per successful request, published at $0.75 per 1,000 for each API. Empty results and errors are not billed.
Development
npm install
npm test # unit + MCP tests against a fake API
npm run build
Issues and PRs are welcome.
License
MIT. "DeepSeek" is a trademark of its owner and is used here only to describe the API this client calls.
seekfetch MCP questions
How do I add seekfetch MCP to Claude Code?
Run claude mcp add --env 'DEEPSEEK_API_KEY=<YOUR_DEEPSEEK_API_KEY>' seekfetch -- npx -y seekfetch mcp in your terminal. Add --scope user to make it available in every project.
How do I add seekfetch MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does seekfetch MCP provide?
It exposes 3 tools, including deepseek_search, deepseek_fetch, deepseek_research.
Does seekfetch require a DeepSeek API key?
Yes, it is a client for DeepSeek's public API and requires your own API key.
How much does using the DeepSeek Search & Fetch API cost?
Billing is per successful request, priced at approximately $0.75 per 1,000 requests for each API.