PrismSearch runs on your own machine — the client starts it, so there is no endpoint to ping. 189 installs a week from npm. Last commit 4 Nov 2026.
Multi-engine web, image and WeChat search with page/PDF fetching over local MCP stdio.
Today is the operative word: we check PrismSearch every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add prismsearch -- npx -y prismsearch
{
"mcpServers": {
"prismsearch": {
"command": "npx",
"args": [
"-y",
"prismsearch"
]
}
}
}
[mcp_servers.prismsearch]
command = "npx"
args = ["-y", "prismsearch"]
{
"mcpServers": {
"prismsearch": {
"command": "npx",
"args": [
"-y",
"prismsearch"
]
}
}
}
{
"servers": {
"prismsearch": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"prismsearch"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
BRAVE_API_KEY (Brave Search API key (optional, comma-separated for rotation)), GOOGLE_API_KEY (Google Custom Search API key (optional, comma-separated for rotation)), GOOGLE_CSE_ID (Google Programmable Search Engine ID (cx), used with GOOGLE_API_KEY), PRISMSEARCH_HOME (Local data directory for SQLite cache and default config lookup (optional)), PRISMSEARCH_CONFIG (Path to a YAML/JSON/TOML config file (optional)).
Zero-API-key MCP search server: multi-engine web/academic search, PDF parsing, secure web fetch
No-API-key web search, page fetching and document reading across many engines. Local-first.
PDF parsing server with text extraction, metadata, search, images, and TOC via MCP
Local RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup
Offline MCP server for local Qt 4.8, Qt 5, and Qt 6 documentation with full-text search.
Hybrid search over your local documents, with file and page citations. One binary, fully local.
Read-only local-first MCP server for private Markdown, PDF, and Tika-backed search on Windows.
Extract local PDF text with page-level paragraphs and English/German OCR fallback.
Answers built from our own checks of this server.