---
title: "What is an MCP memory server and how does it work?"
description: "An MCP memory server is a program that stores facts outside the model and hands an AI tools to save and search them, so memory survives a new chat."
image: "https://bombos.ai/assets/og-en-v2.png"
---

# What is an MCP memory server and how does it work?

Short answer

An MCP memory server is a small program that keeps facts outside the AI model and exposes them as tools over the Model Context Protocol. The AI calls those tools to save, search and delete memories, so what it learned survives a new chat. Where that memory lives, and who else can read it, depends entirely on the server you pick.

*Piet Baudoin · published November 16, 2026 · November 16, 2026*

## The moving parts

The Model Context Protocol (MCP) is an open standard for connecting AI applications to outside systems: data sources, tools and workflows. Its makers compare it to a USB-C port for AI. Claude, ChatGPT, Visual Studio Code and Cursor all speak it.

A memory server is just one kind of MCP server. It does three things:

1.  **Stores** facts somewhere outside the model: a file, a graph database or a hosted account.
2.  **Exposes tools** the AI can call, like “add a memory” or “search memories”.
3.  **Returns results** that the client puts into the model’s context for that turn.

So the AI does not “remember” in the human sense. It decides to call a search tool, gets text back, and reasons with it. If it does not call the tool, the memory is not there.

## Three common servers side by side

| Aspect | Official server-memory | Graphiti MCP (Zep) | Mem0 MCP |
| --- | --- | --- | --- |
| Storage | Local JSONL file | Graph database (FalkorDB or Neo4j) | Your Mem0 account, hosted |
| Runs where | On your machine, started by the client | Docker or Python, HTTP on localhost:8000 by default | [https://mcp.mem0.ai/mcp](https://mcp.mem0.ai/mcp) |
| Example tools | create\_entities, add\_observations, search\_nodes, read\_graph | add\_memory, search\_memory\_facts, get\_episodes | add\_memory, search\_memories, delete\_memory |
| Status per its own docs | Reference implementation, not production-ready | Experimental, no authentication | Needs a Mem0 Platform account and API key |

The official server stores a knowledge graph of entities, relations and observations, with nine tools. Graphiti adds time awareness: facts carry when they were true. Mem0 keeps memories in its cloud and signs you in through the browser or an API key.

## How a memory call actually flows

1.  You tell Claude: “Remember that our invoices go out on the 25th.”
2.  Claude decides to call a tool: on the official server it creates an entity with `create_entities`, or adds the fact to an existing entity with `add_observations`.
3.  The server writes that line to its file or database.
4.  Next week, in a new chat, you ask about invoicing. Claude calls `search_nodes` with “invoice”.
5.  The server returns the stored fact, and Claude answers with it.

Step 4 is not automatic: the client must retrieve the stored fact and include it in the model’s context. The model has to think of searching. Many people add an instruction to their system prompt or project instructions that tells the AI to check memory first.

## The common misunderstanding

People expect an MCP memory server to give “the AI” a memory. It gives one MCP client, with that server configured, access to one store. The official server, for example, writes to a file on your disk. Your colleague’s Claude does not see it. Your own ChatGPT does not see it either, unless you connect it to a server it can reach. The official README notes that each client starts its own server process; it uses a lock file so writes from several clients on one machine take turns, and warns that sharing is unsafe on a network file system that does not honor exclusive file creation.

Graphiti can be reached over HTTP, but its own page warns that it has no authentication or authorization: anyone who can reach it can read, change and delete everything.

## What this means for a team

A memory server is personal unless you make it shared on purpose. To share it you need a remote server, sign-in per person, rules about who may write, and a way to see why the AI used a certain fact. Before sharing a store, check each server’s identity model, access controls and provenance features; MCP itself does not provide these. How memories are stored, selected and searched also depends entirely on the server. If you want the deeper setup steps, see [how to set up server-memory in Claude](https://bombos.ai/en/questions/mcp/how-to-set-up-server-memory-mcp-in-claude/), and for the risks read [is MCP safe to use in a company](https://bombos.ai/en/questions/mcp/is-mcp-safe-to-use-in-a-company/).

## Where Bombos fits

Bombos is a plugin that gives every AI tool a team uses (Claude, Claude Code, ChatGPT, Copilot, Grok, Codex, Cursor, your own agents) one shared memory. It holds team knowledge, rules the AI learned about how you work, and what already exists in mail, documents and repos, and it shows what each answer rests on. It runs in our cloud or on your own server, and one person can try it first for their own agents.

## Related questions

Does an MCP memory server make the model itself remember?

No. The model stays the same. The server stores the data, and the model only sees a memory when it calls a tool such as search\_nodes or search\_memories and the result lands in its context.

Which MCP memory server is the official one?

The MCP project publishes a reference server called Knowledge Graph Memory Server (package @modelcontextprotocol/server-memory). The project describes its reference servers as educational examples, not production-ready solutions.

Can Claude, ChatGPT and Copilot share one MCP memory server?

Only if the server is reachable by all of them, which in practice means a remote server over HTTPS with proper authentication. A local stdio server on one laptop is only visible to the clients on that laptop.

Is an MCP memory server the same as Claude memory or ChatGPT memory?

No. The built-in memory of Claude or ChatGPT lives inside that product. An MCP memory server is a separate store that any MCP client can call, if you connect it.

## Sources

1.  [What is the Model Context Protocol (MCP)?](https://modelcontextprotocol.io/docs/getting-started/intro)
2.  [Knowledge Graph Memory Server (modelcontextprotocol/servers)](https://github.com/modelcontextprotocol/servers/tree/main/src/memory)
3.  [Graphiti MCP Server](https://github.com/getzep/graphiti/tree/main/mcp_server)
4.  [Mem0 MCP integration](https://docs.mem0.ai/platform/mem0-mcp)

## What does your AI forget?

1.  01You tell us which AI you use and where it keeps starting over.
2.  02We show what a shared memory changes there, on your own examples.
3.  03You keep the plan, with or without Bombos.

![Piet Baudoin](https://bombos.ai/assets/team/piet-klein.jpg)

**Piet Baudoin**You talk to Piet, from the Bombos teamDutch team from Utrecht and Nijmegen · data in Europe

## More questions about MCP

-   [How does the Notion MCP server work for a team?](https://bombos.ai/en/questions/mcp/notion-mcp-server/)
-   [What is an MCP server?](https://bombos.ai/en/questions/mcp/what-is-an-mcp-server/)
-   [What is the Filesystem MCP server and is it safe to use at work?](https://bombos.ai/en/questions/mcp/filesystem-mcp-server/)
-   [How do I set up the official MCP memory server (server-memory) in Claude Desktop?](https://bombos.ai/en/questions/mcp/how-to-set-up-server-memory-mcp-in-claude/)
-   [Does the Mem0 MCP server give a whole team shared AI memory?](https://bombos.ai/en/questions/mcp/mem0-mcp-server-vs-shared-team-memory/)
-   [What is Mem0, and is it open source or a paid platform?](https://bombos.ai/en/questions/mcp/what-is-mem0/)
-   [Where do you find MCP servers, and which can you trust?](https://bombos.ai/en/questions/mcp/where-to-find-trustworthy-mcp-servers/)
-   [What is the AWS MCP Server and how do you set it up safely?](https://bombos.ai/en/questions/mcp/aws-mcp-server/)

[All questions about MCP →](https://bombos.ai/en/questions/mcp/)


---

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://bombos.ai/#organization","name":"Bombos","url":"https://bombos.ai/","logo":"https://bombos.ai/assets/bombos-bee.png","description":"Bombos is the memory layer under every AI your team uses. One shared memory for Claude, ChatGPT, Copilot, Cursor and your own agents, that learns how you work.","sameAs":["https://www.linkedin.com/company/bombos-ai","https://www.youtube.com/@truebombos","https://www.instagram.com/truebombos/","https://bsky.app/profile/bombostrue.bsky.social","https://www.threads.com/@truebombos","https://mastodon.social/@Bombos","https://www.tiktok.com/@truebombos","https://t.me/truebombos","https://www.pinterest.com/truebombos/","https://github.com/bombos-ai","https://linktr.ee/bombos.ai","https://bombosai.substack.com","https://hashnode.com/@bombosai","https://hackernoon.com/u/bombos","https://dev.to/bombos"],"email":"info@bombos.ai","areaServed":["NL","Europe"],"knowsLanguage":["nl","en"],"contactPoint":{"@type":"ContactPoint","email":"info@bombos.ai","contactType":"sales","url":"https://bombos.ai/en/contact/","availableLanguage":["nl","en"]}},{"@type":"WebSite","@id":"https://bombos.ai/#website","name":"Bombos","url":"https://bombos.ai/","inLanguage":["nl-NL","en"],"publisher":{"@id":"https://bombos.ai/#organization"}}]}

{"@context":"https://schema.org","@type":"Article","headline":"What is an MCP memory server and how does it work?","description":"An MCP memory server is a program that stores facts outside the model and hands an AI tools to save and search them, so memory survives a new chat.","abstract":"An MCP memory server is a small program that keeps facts outside the AI model and exposes them as tools over the Model Context Protocol. The AI calls those tools to save, search and delete memories, so what it learned survives a new chat. Where that memory lives, and who else can read it, depends entirely on the server you pick.","datePublished":"2026-11-16T00:00:00.000Z","dateModified":"2026-11-16T00:00:00.000Z","author":{"@type":"Person","name":"Piet Baudoin"},"publisher":{"@type":"Organization","@id":"https://bombos.ai/#organization","name":"Bombos","logo":{"@type":"ImageObject","url":"https://bombos.ai/assets/bombos-bee.png"}},"image":"https://bombos.ai/assets/og-en-v2.png","mainEntityOfPage":"https://bombos.ai/en/questions/mcp/what-is-an-mcp-memory-server/","inLanguage":"en-US","isPartOf":{"@type":"CollectionPage","name":"MCP","url":"https://bombos.ai/en/questions/mcp/"},"citation":[{"@type":"CreativeWork","name":"What is the Model Context Protocol (MCP)?","url":"https://modelcontextprotocol.io/docs/getting-started/intro"},{"@type":"CreativeWork","name":"Knowledge Graph Memory Server (modelcontextprotocol/servers)","url":"https://github.com/modelcontextprotocol/servers/tree/main/src/memory"},{"@type":"CreativeWork","name":"Graphiti MCP Server","url":"https://github.com/getzep/graphiti/tree/main/mcp_server"},{"@type":"CreativeWork","name":"Mem0 MCP integration","url":"https://docs.mem0.ai/platform/mem0-mcp"}]}

{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Bombos","item":"https://bombos.ai/en/"},{"@type":"ListItem","position":2,"name":"Questions","item":"https://bombos.ai/en/questions/"},{"@type":"ListItem","position":3,"name":"MCP","item":"https://bombos.ai/en/questions/mcp/"},{"@type":"ListItem","position":4,"name":"What is an MCP memory server and how does it work?","item":"https://bombos.ai/en/questions/mcp/what-is-an-mcp-memory-server/"}]}

{"@context":"https://schema.org","@type":"FAQPage","mainEntity":[{"@type":"Question","name":"Does an MCP memory server make the model itself remember?","acceptedAnswer":{"@type":"Answer","text":"No. The model stays the same. The server stores the data, and the model only sees a memory when it calls a tool such as search_nodes or search_memories and the result lands in its context."}},{"@type":"Question","name":"Which MCP memory server is the official one?","acceptedAnswer":{"@type":"Answer","text":"The MCP project publishes a reference server called Knowledge Graph Memory Server (package @modelcontextprotocol/server-memory). The project describes its reference servers as educational examples, not production-ready solutions."}},{"@type":"Question","name":"Can Claude, ChatGPT and Copilot share one MCP memory server?","acceptedAnswer":{"@type":"Answer","text":"Only if the server is reachable by all of them, which in practice means a remote server over HTTPS with proper authentication. A local stdio server on one laptop is only visible to the clients on that laptop."}},{"@type":"Question","name":"Is an MCP memory server the same as Claude memory or ChatGPT memory?","acceptedAnswer":{"@type":"Answer","text":"No. The built-in memory of Claude or ChatGPT lives inside that product. An MCP memory server is a separate store that any MCP client can call, if you connect it."}}]}
```
