Opensearch MCP Server
Zero-config web search and page fetch MCP backed by @minpeter/opensearch
context tax
queued
security
queued
cold start
queued
freshness
Maintained36d ago
Install Opensearch MCP server
Install in Claude Code
claude mcp add opensearch-minpeter -- npx -y opensearch-mcpInstall in Cursor
{
"mcpServers": {
"opensearch-minpeter": {
"command": "npx",
"args": [
"-y",
"opensearch-mcp"
]
}
}
}Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).
Install in Claude Desktop
{
"mcpServers": {
"opensearch-minpeter": {
"command": "npx",
"args": [
"-y",
"opensearch-mcp"
]
}
}
}Settings → Developer → Edit Config (claude_desktop_config.json), then restart.
Install in VS Code
{
"servers": {
"opensearch-minpeter": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"opensearch-mcp"
]
}
}
}Add to .vscode/mcp.json in your workspace.
Install in Windsurf
{
"mcpServers": {
"opensearch-minpeter": {
"command": "npx",
"args": [
"-y",
"opensearch-mcp"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json.
Freshness
Maintained — last maintenance signal 36d ago. The newest of the signals below sets the band.
Last commit (default branch)
2026-09-03 · 36d ago · GitHub
Latest release
2026-09-03 · 36d ago · GitHub · @minpeter/opensearch@0.1.3
Package published
no data · npm/PyPI
Registry entry updated
no data · official registry
FAQ
›How do I install the Opensearch MCP server in Claude Code?
Run: claude mcp add opensearch-minpeter -- npx -y opensearch-mcp. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.
›Does Opensearch require an API key?
No required environment variables are declared in its published metadata.
›Can I use Opensearch as a remote (hosted) MCP server?
No hosted endpoint is published; it runs locally over stdio.
›Is Opensearch in the official MCP registry?
No. It was indexed from npm.
Alternatives to Opensearch
Other web search MCP servers.
FetchActiveWeb content fetching and conversion for efficient LLM usage
WigoloActiveLocal web search, fetching, crawling, extraction and research, with multi-engine search, local ML reranking, a SQLite cache and JavaScript rendering.
ExaActiveConnect AI agents to Exa for web search, content fetching, and multi-step research.
ArxivActiveSearch arXiv papers, read original LaTeX sections, get BibTeX from arXiv metadata and set topic watches, with papers stored locally.
DevflowincStaleCrawl, embed, chunk, search and retrieve information from datasets through Trieve.
BrightdataActiveDiscover, extract and interact with the web via Bright Data, one interface for automated access to the public internet.