This OpenSearch MCP package supplies web search, code search and page fetching through a local Node.js server with provider fallbacks.
This OpenSearch MCP package supplies web search, code search and page fetching through a local Node.js server with provider fallbacks.
The minpeter package exposes code_search, web_search and web_fetch as stdio tools. It runs the project's Node search runtime and can use available public provider fallbacks without API keys. Optional provider credentials can add another route when configured.
The README says code search checks GITHUB_TOKEN or GH_TOKEN, then can obtain a token from an authenticated GitHub CLI. That affects the provider used by the local process. Review the environment and intended account before using the server in a shared machine or workspace.
Search for a known code symbol or public page, then fetch a returned URL and compare the text with the source. Provider fallback is useful when one route fails, but it does not guarantee that every query has the same coverage. Playwright is an optional fallback that must be installed separately; the basic package does not install it automatically. Use the package's Node.js requirement and inspect which provider produced an important result.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| code_search | Search code through the configured provider chain. |
| web_search | Search the web through the runtime’s providers. |
| web_fetch | Fetch page content using the configured fallback chain. |
{
"mcpServers": {
"opensearch": {
"command": "npx",
"args": [
"-y",
"opensearch-mcp"
]
}
}
}Node.js 22 or later; optional provider credentials or Playwright are configured separately.
Retrieve public web pages as readable Markdown with the reference Fetch MCP server, including pagination for longer responses.
Use Firecrawl MCP to retrieve website content and extract information for research through Firecrawl’s API-backed web tools.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Automates browsers and APIs, enabling Large Language Models (LLMs) to interact with web pages for tasks like screenshot capture and JavaScript
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.