About Memocore
Memocore is cloud memory for AI agents and teams, storing decisions and project details for retrieval in later chats. Its hosted service lets teams share memory across agents without installing or running a server.
Key features
- 01Save private or project memos
- 02Search by meaning and keywords
- 03Manage projects and tags
- 04Attach files to memos
- 05Share project memos by link
Use cases
- 01Recall decisions across chats
- 02Share project memory among a team's agents
- 03Store project files and retrieve download links
MCP support
This is a hosted remote MCP server that clients connect to over Streamable HTTP with OAuth. It exposes memo, project, tag, file, and sharing capabilities to MCP clients.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://memocore.ai/mcpclaude mcp add --transport http ai-memocore https://memocore.ai/mcp{"mcpServers":{"ai-memocore":{"type":"http","url":"https://memocore.ai/mcp"}}}Open in Cursor{"servers":{"ai-memocore":{"type":"http","url":"https://memocore.ai/mcp"}}}Open in VS Code{"mcpServers":{"ai-memocore":{"type":"http","url":"https://memocore.ai/mcp"}}}{"mcpServers":{"ai-memocore":{"serverUrl":"https://memocore.ai/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEMemocore MCP
Remote Model Context Protocol server for Memocore.
Memocore is cloud memory for AI agents and teams. Your agent saves decisions, project details and how your team works, then finds them again in the next chat. The same memory is available in Claude, ChatGPT, Cursor and any other AI tool connected to your account, and a team can share one memory across all its agents.
The server is hosted by Memocore, so there is nothing to install or run.
Server
- URL:
https://memocore.ai/mcp - Transport: Streamable HTTP
- Auth: OAuth. No API keys to paste: your AI tool opens the Memocore sign-in page when it connects.
A Memocore account is required. The free plan is enough to start, and you can sign up during the first sign-in.
Setup
VS Code (GitHub Copilot)
Add the server to .vscode/mcp.json:
{
"servers": {
"memocore": {
"type": "http",
"url": "https://memocore.ai/mcp"
}
}
}
Start the server and sign in to Memocore when VS Code asks. The tools are then available in Copilot Chat agent mode.
Cursor
Add the server with one click from cursor.directory.
Other clients
For clients that use the mcpServers config:
{
"mcpServers": {
"memocore": {
"type": "http",
"url": "https://memocore.ai/mcp"
}
}
}
Setup guides for Claude, ChatGPT and other AI tools: https://memocore.ai/mcp
What agents can do
| Category | Capabilities |
|---|---|
| Memos | Save private or project memos, search them by meaning and keywords, read, update, delete and restore, view change history |
| Projects | Find, read, create and update shared projects, query rows in table projects |
| Tags | Find, create, update and delete tags |
| Files | Attach files to memos and get download links |
| Sharing | Share a project memo by link and open memocore.ai/m/ links |
Try it
- "Remember that we only deploy on Fridays after QA sign-off"
- "What did we decide about retrying failed payments?"
- "Save this as a memo in the Backend project"
Links
- Website: https://memocore.ai
- Setup for other AI tools: https://memocore.ai/mcp
- Help: https://memocore.ai/help
- Privacy: https://memocore.ai/privacy
- Support: [email protected]
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.