Mnemoverse Memory
MCP server by Mnemoverse
Store and recall long-term memory across Claude, Cursor, VS Code and ChatGPT, with outcome-based re-ranking and shared rooms.
Connect to Mnemoverse Memory
Mnemoverse Memory needs sign-in. Connect with its own URL:
Your client opens Mnemoverse’s sign-in the first time you use it. The token stays between your client and Mnemoverse.
Share this server
Opens this page, with the URL and setup steps.
mcp.tc/i/mnemoverse-memoryAbout
Mnemoverse Memory connects an assistant to a hosted memory engine. You can write preferences, decisions and lessons, search them later in natural language, and report whether a recalled memory helped or misled so its ranking changes. Shared rooms let several people or agents read and write one memory pool.
The hosted endpoint uses streamable HTTP with OAuth sign-in. A local npm package, @mnemoverse/mcp-memory-server, runs through npx and reads a Mnemoverse API key instead. A free account is available at the Mnemoverse console. The server code is MIT licensed; the memory engine itself is a hosted service.
What you can do
- Write durable memories that persist across sessions and tools
- Search memory by natural-language query or list newest entries
- Send helpful or wrong feedback to re-rank recalled memories
- Create shared rooms and invite others with invite codes
- Join rooms and read or write shared memory
- Inspect association graph and memory stats
- List stored vault secret aliases without exposing values
Tools 11
memory_create_roomCreate a shared memory room other people's assistants can read and write.
memory_feedbackMark recalled memories as helpful or wrong to adjust their future ranking.
memory_graphRead association edges around concepts in your memory or a shared room.
memory_invite_to_roomMint an invite code and message for a room you own.
memory_join_roomJoin a shared room using an mnvr_ invite code.
memory_list_recentList newest memories first, with a since filter and paging cursor.
memory_list_roomsList shared rooms you own or have joined, with their addresses.
memory_readSearch long-term memory for preferences, decisions and earlier context.
memory_statsShow memory count, concept associations, domains and quality scores.
memory_writeStore a durable long-term memory that persists across sessions and tools.
vault_listList stored secret aliases and purposes; values are never returned.
From the package’s own manifest, not a live connection, on 17 Nov 2026.
Example prompts
Remember that I prefer TypeScript with strict mode for new projects.
What did we decide about the database schema last week?
Create a shared room for me and my teammate and give me an invite.
Join the room with code mnvr_EXAMPLE and show what's new.
Set up
Every client connects to mcp.mnemoverse.com, and Mnemoverse asks you to sign in the first time. Pick yours; the page remembers your choice.
Claude Code
- Run this in a terminal, in your project folder:
claude mcp add --transport http mnemoverse-memory https://mcp.mnemoverse.com/mcp- Start Claude Code, type
/mcp, pick mnemoverse-memory and choose Authenticate. A browser window opens for the Mnemoverse sign-in.
Add --scope user to make it available in every project, not just this one.
Claude Desktop
- Open Customize → Connectors, click + Add, then Add custom connector.
- Name it Mnemoverse Memory and paste this URL:
https://mcp.mnemoverse.com/mcp- Click Add, then Connect, and sign in when Mnemoverse asks.
Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.
claude.ai
- Open the connector form on claude.ai. This button fills in the name and URL for you:
Add to claude.ai (opens in a new tab)
- Check that the URL reads
https://mcp.mnemoverse.com/mcpand click Add. - Click Connect and sign in when Mnemoverse asks.
Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under Organization settings → Connectors.
ChatGPT
- On chatgpt.com, go to Plugins, select +, then Add custom MCP server.
- Enter a name for the server.
- Under Connection, paste
https://mcp.mnemoverse.com/mcpas the server URL, then for authentication choose OAuth. ChatGPT sends you to Mnemoverse to sign in. - Check I understand and want to continue, then select Create as a plugin.
Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).
Cursor
Add to Cursor (opens in a new tab)
Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):
{
"mcpServers": {
"mnemoverse-memory": {
"url": "https://mcp.mnemoverse.com/mcp"
}
}
}Cursor shows Needs authentication next to the server. Click the button beside it to sign in.
VS Code
Install in VS Code (opens in a new tab)
Or from a terminal:
code --add-mcp '{"name":"mnemoverse-memory","type":"http","url":"https://mcp.mnemoverse.com/mcp"}'Or commit it to the repo in .vscode/mcp.json:
{
"servers": {
"mnemoverse-memory": {
"type": "http",
"url": "https://mcp.mnemoverse.com/mcp"
}
}
}VS Code asks you to sign in the first time the server starts.
Devin Desktop
- Add it to
~/.config/devin/mcp_config.json(macOS and Linux) or%APPDATA%\devin\mcp_config.json(Windows):
{
"mcpServers": {
"mnemoverse-memory": {
"serverUrl": "https://mcp.mnemoverse.com/mcp"
}
}
}- Refresh the MCP server list in Cascade and sign in when asked.
Devin Desktop is the new name for Windsurf. It reads serverUrl (or url) for remote servers.
Codex
codex mcp add mnemoverse-memory --url https://mcp.mnemoverse.com/mcp
codex mcp login mnemoverse-memoryOr edit ~/.codex/config.toml directly:
[mcp_servers.mnemoverse-memory]
url = "https://mcp.mnemoverse.com/mcp"Gemini CLI
gemini mcp add --transport http mnemoverse-memory https://mcp.mnemoverse.com/mcpThen, inside Gemini CLI, run /mcp auth mnemoverse-memory to sign in.
This adds it to the current project. Add -s user to use it everywhere.
Any client
Most clients accept this shape. Some name the URL field differently: serverUrl in Devin Desktop, httpUrl in Gemini CLI’s settings file.
{
"mcpServers": {
"mnemoverse-memory": {
"type": "http",
"url": "https://mcp.mnemoverse.com/mcp"
}
}
}Zed puts servers under context_servers in its settings. Cline needs "type": "streamableHttp", or it assumes SSE.
Client only starts local servers? Bridge it with npx -y mcp-remote https://mcp.mnemoverse.com/mcp.
Embed
Show Mnemoverse Memory in a README or on your site. Each embed links to this page, uses the server’s own URL, and sets no cookies. How embeds work
The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.
README badge
[](https://mcp.tc/i/mnemoverse-memory)<a href="https://mcp.tc/i/mnemoverse-memory"><img src="https://mcp.tc/i/mnemoverse-memory/badge.svg" alt="Mnemoverse Memory on mcp.tc" height="20"></a>It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.
Website card
<script src="https://mcp.tc/w/mnemoverse-memory.js" async></script>The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.
iframe
<iframe src="https://mcp.tc/embed/mnemoverse-memory" title="Mnemoverse Memory on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.
JSON
The listing as data for your own pages and tools: name, tagline, the server’s own URL, tools and the “Add to” links. Any site can read it (CORS is open).
https://mcp.tc/i/mnemoverse-memory.jsonAI prompt
Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the Mnemoverse Memory card to your site.
Add the mcp.tc card for Mnemoverse Memory, an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.
Put this tag where the card should appear. The card renders right before it:
```html
<script src="https://mcp.tc/w/mnemoverse-memory.js" async></script>
```
To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.
```html
<div data-mcptc="mnemoverse-memory"><a href="https://mcp.tc/i/mnemoverse-memory">Mnemoverse Memory on mcp.tc</a></div>
```
Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.
If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).
For a README or other Markdown docs, use the badge instead:
```markdown
[](https://mcp.tc/i/mnemoverse-memory)
```
Reference: https://mcp.tc/embedChange history
We read the tool list in this server’s bundle manifest on GitHub every 3 hours and record what changes. Last read 18 Nov 2026, 05:31 UTC.
-
2 tools changed.
Details, 13 Nov 2026, 23:55 UTC
Changed 2
memory_readdescriptionBeforeSearch long-term memory for user preferences, past decisions, project setup, people, or earlier context. The memory persists across sessions and across every AI tool the user has connected. It applies when an answer may depend on something from an earlier session or another tool; it is not needed for general world knowledge. Returns matches ranked by relevance (or newest-first with order_by: 'recency'); each result carries an id; after the answer, memory_feedback takes these ids to record which memories helped. A correction is a fresh
memory_write:it is stored alongside the earlier memory, whichis not deleted or hidden,unless it is too close to an existing memory, in which case the write isrefused.No MCP deletion tool is exposed; a user can permanently delete an individual personal memory through the REST API or withhelp from support.AfterSearch long-term memory for user preferences, past decisions, project setup, people, or earlier context. The memory persists across sessions and across every AI tool the user has connected. It applies when an answer may depend on something from an earlier session or another tool; it is not needed for general world knowledge. Returns matches ranked by relevance (or newest-first with order_by: 'recency'); each result carries an id; after the answer, memory_feedback takes these ids to record which memories helped. A correction is a fresh memory_write. Without supersedes it is stored alongside the earlier memory, which stays as it was, unless it is too close to an existing memory, in which case the write is refused; with supersedes, the earlier memory is marked replaced, is hidden from reads when the account hides replaced memories, and include_history returns it. No MCP deletion tool is exposed; a user can permanently delete an individual personal memory through the REST API or with help…
memory_writedescriptionBeforeStore a long-term memory that persists across sessions and across every AI tool the user has connected to Mnemoverse. Suited to durable information: a stated preference, a decision, a fact about people, roles or project setup, a lesson learned; transient chatter that only matters this turn does not belong here. Never store passwords, API keys, payment data, MFA codes, government IDs, or health records. Behavior: outside shared rooms, a novelty gate refuses a write the embedder cannot tell apart from a memory already stored in the same domain, so the result tells you whether the memory was stored or refused. Write `content` as a self-contained statement that still makes sense when recalled out of context.
AfterStore a long-term memory that persists across sessions and across every AI tool the user has connected to Mnemoverse. Suited to durable information: a stated preference, a decision, a fact about people, roles or project setup, a lesson learned; transient chatter that only matters this turn does not belong here. Never store passwords, API keys, payment data, MFA codes, government IDs, or health records. Behavior: outside shared rooms, a novelty gate refuses a write the embedder cannot tell apart from a memory already stored in the same domain, so the result tells you whether the memory was stored or refused. Write `content` as a self-contained statement that still makes sense when recalled out of context. To correct a memory you have checked is outdated, pass its memory_id in supersedes.
-
3 tools changed.
Details, 30 Oct 2026, 05:42 UTC
Changed 3
memory_create_roomdescriptionBeforeCreate a SHARED memory room — a space OTHER people's assistants can read, and write too when their
invite granted read_write (the default scope),acrossClaude/ChatGPT/Cursor.Use when the user wants to share context or collaborate with someone else (e.g. 'make a room for me and my teammate'). Returns the room's address; pass that address as the `domain` on memory_write/memory_read to use it, and on memory_list_recent to catch up on what others added. People join through an invite minted with memory_invite_to_room.AfterCreate a SHARED memory room — a space OTHER people's assistants can read, and write too when their membership scope is read_write, across the AI tools members connect to Mnemoverse. Members can access the room's existing history, including memories saved before they joined; joining does not expose their private account memory. Use when the user wants to share context or collaborate with someone else (e.g. 'make a room for me and my teammate'). Returns the room's address; pass that address as the `domain` on memory_write/memory_read to use it, and on memory_list_recent to catch up on what others added. People join through an invite minted with memory_invite_to_room.
memory_readdescriptionBeforeSearch long-term memory for user preferences, past decisions, project setup, people, or earlier context. The memory persists across sessions and across every AI tool the user has
connected (Claude, ChatGPT, Cursor, VS Code).It applies when an answer may depend on something from an earlier session or another tool; it is not needed for general world knowledge. Returns matches ranked by relevance (or newest-first with order_by: 'recency'); each result carries an id; after the answer, memory_feedback takes these ids to record which memories helped. Awrongorstale memoryiscorrected by writingafresh onewithmemory_write, not by deleting it.AfterSearch long-term memory for user preferences, past decisions, project setup, people, or earlier context. The memory persists across sessions and across every AI tool the user has connected. It applies when an answer may depend on something from an earlier session or another tool; it is not needed for general world knowledge. Returns matches ranked by relevance (or newest-first with order_by: 'recency'); each result carries an id; after the answer, memory_feedback takes these ids to record which memories helped. A correction is a fresh memory_write: it is stored alongside the earlier memory, which is not deleted or hidden, unless it is too close to an existing memory, in which case the write is refused. No MCP deletion tool is exposed; a user can permanently delete an individual personal memory through the REST API or with help from support.
memory_writedescriptionBeforeStore a long-term memory that persists across sessions and across every AI tool the user has connected to
Mnemoverse (Claude, ChatGPT, Cursor, VS Code).Suited to durable information: a stated preference, a decision, a fact about people, roles or project setup, a lesson learned; transient chatter that only matters this turn does not belong here. Never store passwords, API keys, payment data, MFA codes, government IDs, or health records. Behavior: outside shared rooms, a novelty gate refuses a write the embedder cannot tell apart from a memory already stored in the same domain, so the result tells you whether the memory was stored or refused. Write `content` as a self-contained statement that still makes sense when recalled out of context.AfterStore a long-term memory that persists across sessions and across every AI tool the user has connected to Mnemoverse. Suited to durable information: a stated preference, a decision, a fact about people, roles or project setup, a lesson learned; transient chatter that only matters this turn does not belong here. Never store passwords, API keys, payment data, MFA codes, government IDs, or health records. Behavior: outside shared rooms, a novelty gate refuses a write the embedder cannot tell apart from a memory already stored in the same domain, so the result tells you whether the memory was stored or refused. Write `content` as a self-contained statement that still makes sense when recalled out of context.
-
1 tool changed.
Details, 23 Oct 2026, 16:41 UTC
Changed 1
memory_list_recentdescriptionBeforeList the NEWEST memories first — no search query needed. Semantic search answers 'what do I know about X'; this answers 'what happened lately': resuming work after a break, catching up on a shared room ('any new messages?'), or reviewing what was saved recently. Pass `since` (your last-seen time) to get only what's new, and page through older entries with the returned cursor. Complete by construction WITHIN ONE SCOPE — nothing is skipped there, unlike a semantic search. A page is also bounded by SIZE, so a page of long entries comes back shorter than `limit` and hands you a cursor for the rest — nothing is dropped, and following the cursor is how you get it. To catch up on a shared room you MUST pass its address as `domain`: rooms are separate stores and an unscoped call never covers
them.AfterList the NEWEST memories first — no search query needed. Semantic search answers 'what do I know about X'; this answers 'what happened lately': resuming work after a break, catching up on a shared room ('any new messages?'), or reviewing what was saved recently. Pass `since` (your last-seen time) to get only what's new, and page through older entries with the returned cursor. Complete by construction WITHIN ONE SCOPE — nothing is skipped there, unlike a semantic search. A page is also bounded by SIZE, so a page of long entries comes back shorter than `limit` and hands you a cursor for the rest — nothing is dropped, and following the cursor is how you get it. To catch up on a shared room you MUST pass its address as `domain`: rooms are separate stores and an unscoped call never covers them, though it names the ones you have (`rooms_not_searched`).
-
1 tool changed.
Details, 22 Oct 2026, 22:43 UTC
Changed 1
memory_feedbackdescriptionBeforeReport whethermemories returned by memory_readwere actually helpful. This is a learning signal, not a log:positive feedback raises a memory'sranking so it surfaces faster next time (across all of the user's tools),negative feedback lowers it so other memories out-rank it — nothing iserased and nothing decays with time. Use it after an answer that relied onorrejected memories from memory_read: pass the ids of those memories as memory_ids, with outcome 1 when they helped and -1 when they were wrong or stale.For memories read from a shared room,alsopass that room's address as domain; your own memories need no domain. A read-only room member cannot rate the room's memories.AfterRate memories returned by memory_read to help improve future retrieval ranking. Pass their IDs as memory_ids and an outcome from -1 (unhelpful) to 1 (helpful). Records feedback and updates ranking signals: positive feedback raises a memory's ranking; negative feedback lowers it so other memories out-rank it — nothing is erased. Saved text is not changed or deleted. For memories read from a shared room, pass that room's address as domain; your own memories need no domain. A read-only room member cannot rate the room's memories.
-
Tracking started: 11 tools.
FAQ
Can I paste mcp.tc/i/mnemoverse-memory into my MCP client?
No. mcp.tc links are pages, not server addresses. Connect with https://mcp.mnemoverse.com/mcp, so your client talks to Mnemoverse Memory directly. The sign-in token only works there anyway. The quick link is for sharing: it opens this page, with setup steps for every client.
Does Mnemoverse Memory need an API key or a sign-in?
Yes, you need a Mnemoverse account. The first time your client connects, it opens Mnemoverse’s sign-in page. The token goes straight to the server’s own URL, never through mcp.tc.
Is Mnemoverse Memory a remote or a local server?
Remote. Mnemoverse hosts it at https://mcp.mnemoverse.com/mcp, and it speaks Streamable HTTP. There’s nothing to install.
What can Mnemoverse Memory do?
It has 11 tools, including memory_create_room, memory_feedback and memory_graph. You can write durable memories that persist across sessions and tools, search memory by natural-language query or list newest entries and send helpful or wrong feedback to re-rank recalled memories.
Which clients can use it?
Any client that supports remote MCP servers: Claude Code, Claude Desktop, claude.ai, ChatGPT, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. The setup steps cover each one.
Does mcp.tc track changes to Mnemoverse Memory?
Yes. We follow the tool list in Mnemoverse Memory’s bundle manifest, and its History tab shows each change we find, plus new versions and edits by its owner. Follow the listing to get an email when it changes.
Who wrote this page?
mcp.tc’s robot read Mnemoverse Memory’s own metadata (its MCP handshake, tool list and public pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.
mcp.tc isn’t affiliated with Mnemoverse. This page was built from Mnemoverse Memory’s public metadata, last checked on 17 Nov 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.