RAMen Connector
RAMen Connector lets MCP-capable AI apps use RAMen's hosted memory to recall, save, resume, search, and delete user context across chats.
Recall memory: look up relevant facts, preferences, rules, plans, and must-know details from earlier chats.
Remember things: save lasting facts in the user's words, with options for must-know facts, profile preferences, and inferred guesses awaiting approval.
Save long chats: preserve goals, decisions, open items, current values, drafts, and other thread state for continuation elsewhere.
Resume/search threads: bring back saved threads, list open items, or look up specific details and draft text.
Forget data: delete notes or saved threads matching specified words.
Check/manage memory status: view the profile card, memory usage, pending guesses, open items, saved threads, linked computers, and change checkpoint/topic settings.
Connect across apps: works with Claude Desktop, Cursor, VS Code, Windsurf, Cline, Codex, and other MCP clients using a RAMen license key.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@RAMen Connector remember that I prefer concise answers with no emojis"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
RAMen connector (MCP)
RAMen is one memory for all your AI apps. It saves what you tell them (your people, your work, your rules, how you like answers) and looks it up when it matters, with a receipt for every note: your own words, the date and the app. Long chats can be saved and continued in a fresh chat, in any app.
This package connects RAMen to any app that runs MCP servers on your computer: Claude Desktop, Cursor, VS Code, Windsurf, Zed, Cline, Codex, Gemini CLI and others. It signs in with your RAMen license key and passes each request to RAMen's hosted service, where all of RAMen runs. It has no dependencies.
1. Get a license key
Get a free key at getramenai.com. RAMen Free keeps up to 50 notes, 3 saved chats a month and 2 connected apps. RAMen Pro is $1.99 a month, with a 14-day trial of everything.
Related MCP server: memory-mcp
2. Add it to your app
Claude Desktop (claude_desktop_config.json), Cursor (.cursor/mcp.json), Windsurf, Cline and most others:
{
"mcpServers": {
"ramen": {
"command": "npx",
"args": ["-y", "github:MatthewLeibel/ramen-mcp"],
"env": { "RAMEN_LICENSE_KEY": "your RAMen license key" }
}
}
}VS Code (.vscode/mcp.json) uses "servers" in place of "mcpServers".
Codex (~/.codex/config.toml):
[mcp_servers.ramen]
command = "npx"
args = ["-y", "github:MatthewLeibel/ramen-mcp"]
env = { RAMEN_LICENSE_KEY = "your RAMen license key" }Claude Code: claude mcp add ramen -e RAMEN_LICENSE_KEY=your-key -- npx -y github:MatthewLeibel/ramen-mcp, or
install the RAMen plugin.
Apps that connect to remote MCP servers themselves (claude.ai, ChatGPT and others) don't need this package: add
https://ramen-online.matthewsleibel.workers.dev/mcp and sign in with your key in the browser.
Needs Node.js 18.18 or later.
Tools
Tool | What it does |
| Looks up what RAMen knows that matters to your message |
| Saves a note, with your own words as its receipt |
| Deletes notes about something you name |
| Shows what RAMen keeps and what your plan includes |
| Saves a long chat (goal, decisions, open items, drafts) to continue later |
| Continues a saved chat in a fresh one |
| Finds a detail in a saved chat |
See, edit and delete everything on your RAMen page: getramenai.com.
Settings
Variable | |
| Your RAMen license key (required) |
| The app name on your notes' receipts. By default, the name your app gives itself |
| Set to |
Without a key, the connector still starts and lists RAMen's tools; using one tells you to add your key.
The sign-in is saved in ~/.config/ramen-mcp (on Windows, %APPDATA%\ramen-mcp), readable only by you, so the key
is sent to RAMen once per app and not on every start.
Privacy
Your key and your requests go only to RAMen. RAMen never receives your full conversations, only what your AI saves or looks up. Privacy policy: getramenai.com/privacy.html. Support: support@getramenai.com.
Test
npm run test:offline checks the connector without a key or network (it starts, lists the 7 tools and asks for the key on use); CI runs it on Node 18 to 24. RAMEN_LICENSE_KEY=your-key npm test starts the connector, lists the tools and runs two read-only tools against RAMen.
License
MIT, for this connector. RAMen's hosted service is not open source.
Available Tools
7 toolsforgetForget from RAMen MemoryADestructiveIdempotent
Delete what RAMen Memory keeps about something, when the user asks you to forget it: every note that contains the given words. To delete a saved thread, give 'thread: ' and its name.
Inputs: about (required).
memory_statusRAMen Memory statusBIdempotent
The user's profile card (how they want answers), then how much RAMen Memory keeps, AI guesses waiting for the user's OK, open items, the saved threads and which computers are linked. With settings it changes RAMen settings.
Inputs: settings.
recallRecall from RAMen MemoryARead-onlyIdempotent
Look up what the user told you or their other AI apps in earlier chats: their family, work, projects, rules, preferences and plans, kept in their RAMen Memory. Use it when a conversation starts on something that depends on who the user is, and when they refer to something that is not in this chat. It always gives the user's must-know facts too; for how to answer (style, length, tone), their profile card first.
Inputs: question (required).
recall_threadLook up in a RAMen threadARead-onlyIdempotent
Look up details of saved RAMen threads: the full text of a draft (ask by its title), or anything else that was saved. Without a thread it searches every thread and the user's memory notes, and says where each match is from.
Inputs: question (required), thread.
rememberSave to RAMen MemoryAIdempotent
Save a lasting fact about the user (their people, home, health, work, tastes, life plans) or what they ask you to remember, so their other AI apps know it next time. One clear sentence in their words. Not the details of the work in this chat: a saved chat keeps those.
Inputs: note (required), must, quote, profile, +1 more.
resume_threadContinue a RAMen threadARead-onlyIdempotent
Bring back a saved RAMen chat, to go on from it here. Use it when the user wants to continue earlier work, a saved chat, a project or a RAMen thread. Without a name it brings the most recent one and lists the others.
Inputs: open, thread, project.
save_threadSave this chat to RAMenAIdempotent
Save where this conversation stands, so it can go on in a fresh chat or in another AI app (Claude, ChatGPT or any app with RAMen Memory) without re-reading this whole chat: every reply in a long chat re-reads all of it, which uses up tokens and usage limits. Use it when the user asks to save the chat or to continue it in a new chat or elsewhere, or when the chat has grown long. Be complete and specific: every name, number, date, time, price and reason, every change (with what it was before), and the latest version of anything you wrote together, word for word. Saving again under the same name adds to the thread and updates its values.
Inputs: now (required), goal (required), open (required), facts (required), +6 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
The three memory-facing verbs (recall, recall_thread, memory_status) and the thread verbs (save_thread, resume_thread, recall_thread) overlap: recall_thread explicitly searches 'every thread and the user's memory notes', which duplicates recall's territory, and the boundary between resuming a thread and recalling a thread's details requires careful reading. The long descriptions help, but an agent can easily pick the wrong lookup tool.
Patterns are mixed: bare verbs (recall, remember, forget), verb_noun (save_thread, resume_thread, recall_thread), and a noun phrase (memory_status). Individually readable, but there is no single predictable convention an agent can generalize from.
Seven tools for a personal-memory connector is well-scoped: two fact tools, three thread tools, a delete, and a status/settings tool. Each earns its place and nothing feels padded or missing at the count level.
Coverage is solid: create/read/delete for facts, save/resume/read for threads, plus status and settings. Minor gaps exist—no explicit edit/correct operation for a saved fact (only re-remember), and thread listing is only implicit through resume_thread without a name.
Maintenance
Related MCP Connectors
Hosted agent memory: store, search, and recall facts across sessions from any MCP client.
Persistent personal memory for AI assistants — save, search, and recall across every MCP client.
Hosted memory for AI agents over MCP. One memory shared by all your agents.
An MCP memory server. One memory your agents share — across models, devices and apps.
Related MCP Servers
AlicenseNot gradedqualityBmaintenanceEnables persistent memory storage and retrieval for MCP clients, allowing AI assistants to remember facts and context across conversations.26 npmMIT- AlicenseAqualityDmaintenanceProvides persistent memory for AI assistants via MCP, enabling them to store and recall facts, preferences, and tasks across conversations using either local file storage or a cloud backend with semantic search.514 npmMIT
- AlicenseNot gradedqualityDmaintenanceProvides persistent, cloud-based memory for AI agents, letting them remember preferences, skills, and decisions across sessions via an MCP-compatible interface.Apache 2.0
- FlicenseNot gradedqualityDmaintenanceEnables each user to have a private, per-user memory store that persists across AI tools, allowing them to store, recall, search, list, and delete memories via MCP.-