RAMen Connector
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RAMEN_APP | No | The app name on your notes' receipts. By default, the name your app gives itself. | |
| RAMEN_DEBUG | No | Set to 1 for more messages (on stderr). | |
| RAMEN_LICENSE_KEY | No | Your RAMen license key (free at getramenai.com). Without it the connector starts and lists its tools, and each tool asks for the key. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
RAMen Memory is the user's own memory, shared by their AI apps. Call recall when a conversation starts on something that depends on the user (their people, work, projects, rules, preferences) or on earlier conversations, and when they mention something that is not in this chat; what this chat already says needs no lookup. Call remember when they tell you a lasting fact about themselves or ask you to remember something; the details of the work at hand stay in the chat, and save_thread keeps them. When two notes disagree, the later one holds now. When recall finds no note, try other words or ask; don't guess, and don't tell the user they never said it. When the user wants to go on with a long chat in a fresh one or in another app, call save_thread; in the new chat, resume_thread brings it back and recall_thread finds the details. RAMen needs your license key: set RAMEN_LICENSE_KEY in this app's MCP settings, then restart the app. Get a free key at https://getramenai.com.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| recallA | 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. |
| rememberA | 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. |
| save_threadA | 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. |
| resume_threadA | 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. |
| recall_threadA | 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. |
| forgetA | 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. |
| memory_statusB | 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. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
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.