NestDaddy

Search Memory

io.github.kefyusuf/search-memory-mcp · v1.2.0

Free web search and long-term memory for AI assistants. No API keys; data stays local.

Connect Runs on your machine

Terminal
claude mcp add search-memory-mcp -e SEARCH_PROVIDERS=<SEARCH_PROVIDERS> -e CACHE_DB_PATH=<CACHE_DB_PATH> -e INGEST_ALLOWED_DIRS=<INGEST_ALLOWED_DIRS> -e SEARXNG_BASE_URL=<SEARXNG_BASE_URL> -e BRAVE_SEARCH_API_KEY=<BRAVE_SEARCH_API_KEY> -e TAVILY_API_KEY=<TAVILY_API_KEY> -e EXA_API_KEY=<EXA_API_KEY> -e READER_FALLBACK_URL=<READER_FALLBACK_URL> -- npx -y [email protected]
claude_desktop_config.json
{
  "mcpServers": {
    "search-memory-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "SEARCH_PROVIDERS": "<SEARCH_PROVIDERS>",
        "CACHE_DB_PATH": "<CACHE_DB_PATH>",
        "INGEST_ALLOWED_DIRS": "<INGEST_ALLOWED_DIRS>",
        "SEARXNG_BASE_URL": "<SEARXNG_BASE_URL>",
        "BRAVE_SEARCH_API_KEY": "<BRAVE_SEARCH_API_KEY>",
        "TAVILY_API_KEY": "<TAVILY_API_KEY>",
        "EXA_API_KEY": "<EXA_API_KEY>",
        "READER_FALLBACK_URL": "<READER_FALLBACK_URL>"
      }
    }
  }
}
~/.cursor/mcp.json
{
  "mcpServers": {
    "search-memory-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "SEARCH_PROVIDERS": "<SEARCH_PROVIDERS>",
        "CACHE_DB_PATH": "<CACHE_DB_PATH>",
        "INGEST_ALLOWED_DIRS": "<INGEST_ALLOWED_DIRS>",
        "SEARXNG_BASE_URL": "<SEARXNG_BASE_URL>",
        "BRAVE_SEARCH_API_KEY": "<BRAVE_SEARCH_API_KEY>",
        "TAVILY_API_KEY": "<TAVILY_API_KEY>",
        "EXA_API_KEY": "<EXA_API_KEY>",
        "READER_FALLBACK_URL": "<READER_FALLBACK_URL>"
      }
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "search-memory-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "SEARCH_PROVIDERS": "<SEARCH_PROVIDERS>",
        "CACHE_DB_PATH": "<CACHE_DB_PATH>",
        "INGEST_ALLOWED_DIRS": "<INGEST_ALLOWED_DIRS>",
        "SEARXNG_BASE_URL": "<SEARXNG_BASE_URL>",
        "BRAVE_SEARCH_API_KEY": "<BRAVE_SEARCH_API_KEY>",
        "TAVILY_API_KEY": "<TAVILY_API_KEY>",
        "EXA_API_KEY": "<EXA_API_KEY>",
        "READER_FALLBACK_URL": "<READER_FALLBACK_URL>"
      }
    }
  }
}

Replace the values in angle brackets with your own. Keys stay on your machine; we never see them.

Tools

This server runs locally, so its tools are listed by your MCP client once it starts.

Environment variables

NameDescription
SEARCH_PROVIDERS
Optional
Comma-separated search provider order, for example duckduckgo,marginalia,bing
CACHE_DB_PATH
Optional
Path of the local SQLite database for cache, memory, and index
INGEST_ALLOWED_DIRS
Optional
Comma-separated directories whose files ingest_document may read; local file reading is off when unset
SEARXNG_BASE_URL
Optional
Base URL of a SearXNG instance with JSON output, used by the searxng provider
BRAVE_SEARCH_API_KEY
Optional, secret
Optional Brave Search API key; the brave provider then uses the official API instead of scraping
TAVILY_API_KEY
Optional, secret
Optional Tavily API key; adds the tavily provider with news-topic search and publish dates
EXA_API_KEY
Optional, secret
Optional Exa API key; adds the exa provider with neural (semantic) web search
READER_FALLBACK_URL
Optional
Optional reader service (for example https://markdown.new/) used when a page cannot be fetched directly; sends the page URL to that service

Details

Package[email protected] (NPM, stdio)
First published28 Oct 2026
Last updated28 Oct 2026
Registry nameio.github.kefyusuf/search-memory-mcp

More search and web servers See all

Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.