Free web search and long-term memory for AI assistants. No API keys; data stays local.
Search Memory is an MCP integration. Free web search and long-term memory for AI assistants. No API keys; data stays local.
The published npm package is search-memory-mcp, version 1.0.3. Its declared MCP transport is stdio.
The package declares SEARCH_PROVIDERS: Comma-separated search provider order, for example duckduckgo,marginalia,bing; CACHE_DB_PATH: Path of the local SQLite database for cache, memory, and index; INGEST_ALLOWED_DIRS: Comma-separated directories whose files ingest_document may read; local file reading is off when unset; SEARXNG_BASE_URL: Base URL of a SearXNG instance with JSON output, used by the searxng provider; BRAVE_SEARCH_API_KEY: Optional Brave Search API key; the brave provider then uses the official API instead of scraping; READER_FALLBACK_URL: Optional reader service (for example https://markdown.new/) used when a page cannot be fetched directly; sends the page URL to that service.
Check the maintainer’s instructions for account access, authentication and the supported client configuration. Once connected, inspect the tools your client receives and try a small task that matches the server’s stated purpose. The registry description does not include a verified, complete tool list.
View the publisher’s registry entry · Project repository. This profile uses version 1.0.3 from the registry. Registration identifies the publisher namespace; it does not establish that this is a first-party integration for every service it connects.
Browse related search & web scraping MCP servers for tools that cover the same kind of work.
| Variable | Description | Required |
|---|---|---|
| SEARCH_PROVIDERS | Comma-separated search provider order, for example duckduckgo,marginalia,bing | Check documentation |
| CACHE_DB_PATH | Path of the local SQLite database for cache, memory, and index | Check documentation |
| INGEST_ALLOWED_DIRS | Comma-separated directories whose files ingest_document may read; local file reading is off when unset | Check documentation |
| SEARXNG_BASE_URL | Base URL of a SearXNG instance with JSON output, used by the searxng provider | Check documentation |
| BRAVE_SEARCH_API_KEY | Optional Brave Search API key; the brave provider then uses the official API instead of scraping | Check documentation |
| READER_FALLBACK_URL | Optional reader service (for example https://markdown.new/) used when a page cannot be fetched directly; sends the page URL to that service | Check documentation |
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.
Asks 8 AI crawlers for your page, checks who really answered, and writes the fixes. MIT.
SEO for AI agents: keywords, SERPs, backlinks, rank tracking, audits, Search Console, Analytics
Most web scraping tools give your agent one of two bad outputs:
Weibo posts, hot search, comments and profiles to JSON. No login or cookies needed.