ultrathink-mcp
Ultrathink MCP Server
Save and search your Ultrathink knowledge base from any MCP-compatible client: Claude Desktop, Claude Code, Cursor, Zed and more.
Ultrathink is a second-brain app that captures notes, links, screenshots, AI conversations, PDFs and more into a single AI-searchable knowledge base.
New: the hosted Ultrathink MCP server
Ultrathink now runs its own MCP server online, so there is nothing to install. It has more tools than this package: search, read an entry in full, related entries, recent changes, everything about a person or a topic, lists of your topics and people, and adding and updating entries.
Connect Claude Code with one command, using a device key with API access:
claude mcp add --transport http ultrathink https://us-central1-ultrathink-50f7f.cloudfunctions.net/mcp --header "Authorization: Bearer YOUR_DEVICE_KEY"Any MCP client that supports remote servers over HTTP with a header can use the same address. Setup, tools and troubleshooting are in the MCP server guide.
The hosted server is the recommended way to connect. This package keeps working, with the two tools below, for clients that only run local servers.
Related MCP server: open-brain-mcp
This package
It gives your AI assistant two tools:
ultrathink_save: store a note, link, idea or snippet in your knowledge baseultrathink_search: natural-language search across everything you've captured
Install
npm install -g ultrathink-mcpOr use directly with npx ultrathink-mcp (no install needed).
Configuration
You need an Ultrathink device key. Get one at tryultrathink.com.
Set as environment variables:
export ULTRATHINK_DEVICE_KEY="your-device-key-here"Optional:
export ULTRATHINK_API_BASE="https://us-central1-ultrathink-50f7f.cloudfunctions.net" # default
export ULTRATHINK_SOURCE="claude-code" # tag entries with a source labelUse with Claude Code
Add to your ~/.claude.json mcpServers:
{
"mcpServers": {
"ultrathink": {
"command": "npx",
"args": ["-y", "ultrathink-mcp"],
"env": {
"ULTRATHINK_DEVICE_KEY": "your-device-key-here"
}
}
}
}Use with Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"ultrathink": {
"command": "npx",
"args": ["-y", "ultrathink-mcp"],
"env": {
"ULTRATHINK_DEVICE_KEY": "your-device-key-here"
}
}
}
}Tools
ultrathink_save
Save an entry to your Ultrathink knowledge base.
Inputs:
title(required): title of the entrynotes: main content for most entriescontent: full content for longer entriestype: one ofnote,link,idea,snippet,para,chatgpt,claude,perplexity,notion,long-note,profile. Default:noteurl: required whentypeislinkvisibility:private(default) ororg
ultrathink_search
Natural-language search across your Ultrathink knowledge base. Returns an AI-generated answer based on stored entries.
Inputs:
query(required): natural-language search queryentityFilter: optional, one ofproject,task,knowledge
Licence
MIT
Available Tools
2 toolsultrathink_saveB
Save an entry to Ultrathink knowledge base. Use this to store notes, ideas, links, snippets, and other knowledge.
Inputs: title (required), url, type, notes, +2 more.
ultrathink_searchA
Search the Ultrathink knowledge base using natural language. Returns an AI-generated answer based on stored entries.
Inputs: query (required), entityFilter.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools perform clearly opposite, non-overlapping operations: write (save) and read (search). An agent can instantly choose between storing knowledge and retrieving it, with no ambiguity.
Both tools follow an identical pattern: the `ultrathink_` namespace prefix plus a concise verb (save, search). Fully predictable and consistent.
Two tools is on the thin side for a knowledge base server; a minimal capture-and-retrieve surface works, but there is little else an agent can do. It sits at the borderline of under-scoped.
Core store-and-query flow is covered, but obvious knowledge-management operations are absent: no update, delete, list/recent entries, or get-by-id. Agents cannot correct or manage stored entries, only add and search.
Related MCP Connectors
Persistent memory for AI assistants. Save once; recall from Claude, ChatGPT, or any MCP client.
Personal knowledge base MCP server with semantic search, auto-categorization, metadata extraction
Persistent memory layer for AI tools. Save and recall notes across Claude and other MCP clients.
KnowMan MCP server: search, ask, save and read your Knowledge Base from any MCP client.
1
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP Memory Server for Claude Code that provides persistent context across sessions using semantic search (RAG).Apache 2.0
- AlicenseNot gradedqualityDmaintenanceAn MCP server for storing and retrieving thoughts, notes, and ideas with semantic vector search, enabling integration with Claude Desktop and other MCP clients.MIT
- AlicenseNot gradedqualityDmaintenancePersistent memory MCP server for Claude Code. Store, search, and retrieve memories across sessions using hybrid vector + keyword search powered by SQLite, FTS5, and sqlite-vec.10 npm1MIT
- FlicenseNot gradedqualityDmaintenanceAn MCP server that enables Claude Desktop or Claude Code to ingest and search local documents using vector embeddings, returning relevant chunks as tool results for the model to reason over.-