Mem.Center
Read-only access to your saved Mem.Center memories from any MCP client
- Pricing
- Paid
- Platforms
- API
- Runs
- Remotely
- Version
- 1.0.0
- Listing updated
- 2 days ago
About Mem.Center
Mem.Center is a paid MCP server for knowledge and memory. It runs as a hosted remote server, so there is nothing to install locally.
Mem.Center's server gives an AI client a view of the memories you already saved there, and nothing more. It exposes no write or delete tools and does not import or sync chats from other AI clients. Access goes through OAuth with a read-only memories scope, and you can revoke a connection at any time.
Semantic retrieval is optional and requires separately enabling semantic indexing in your account. Requests count against your usage allowance, and the endpoint allows 30 requests per account per minute, including initialization and tool discovery. An active Pro membership is required; without it the server answers with a PRO_REQUIRED error.
The docs give setup steps for ChatGPT, Claude Code, Cursor and VS Code with GitHub Copilot, plus a troubleshooting list for 401, 403 and empty results.
Install
Run in a terminal
claude mcp add --transport http mem-center https://mem.center/mcpAdd to Settings → Connectors → Add custom connector
https://mem.center/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"mem-center": {
"url": "https://mem.center/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"mem-center": {
"type": "http",
"url": "https://mem.center/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"mem-center": {
"serverUrl": "https://mem.center/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"mem-center": {
"type": "http",
"url": "https://mem.center/mcp"
}
}
}Tools this server provides (2)
Taken from the project documentation; the running server may differ.
- search_memories
- Finds saved memories relevant to a query; optional semantic mode.
- build_context
- Prepares a cited context preview for a task, with a quick, standard or deep budget.
What it does
- Memory search
- Finds saved memories relevant to a query, with an optional semantic mode.
- Cited context previews
- Builds a context preview for a task at quick, standard or deep budget.
- Read-only scope
- No memory writes or deletes are exposed.
- OAuth consent
- Connect through a browser sign-in and revoke it later.
- Rate limit
- 30 requests per account per minute.
Good for
- Pull last week's saved notes into a weekly report
- Give a coding agent context from memories you saved earlier
- Search saved memories from inside Cursor or VS Code
- Preview which memories a task would draw on before using them
Pricing
Paid
Requires a Mem.Center Pro membership; price not published
Prices change. Check mem.center before you buy.
Mem.Center FAQ
Can it change or delete my memories?
No. Only read tools are exposed, and it does not write or sync conversations.
Do I need a paid account?
Yes, an active Mem.Center Pro membership is required.
How do I stop access?
Revoke the client under Connections; this stops future access but cannot recall information already shared.
Is there a request limit?
Yes, 30 requests per account per minute.
Is Mem.Center free?
No. Mem.Center is a paid product.
How do I add Mem.Center to Claude Code?
Run this command in your terminal: claude mcp add --transport http mem-center https://mem.center/mcp
What are the best alternatives to Mem.Center?
The closest alternatives to Mem.Center are Codebase Memory, XERJ, Claude Code Ultimate Guide, Nautilus Compass Memory and note1.
Alternatives to Mem.Center

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Claude Code Ultimate Guide
MCP serverMCP server for searching the Claude Code Ultimate Guide from any MCP client
Runs locally- Open source
- 6.5K GitHub stars
- AI models and LLM tooling

Nautilus Compass Memory
MCP serverLocal-first long-term memory layer for AI agents, served over MCP
Not checked yet- 5 tools
- Remote
- Open source
- 1.3K GitHub stars
- Knowledge and memory

note1
MCP serverMCP server giving AI assistants search and summaries across your note1 meetings
- 4 tools
- Remote
- Free trial
- 1 GitHub star
- Productivity
MedXpert 图书馆连接器(通用版)
MCP serverLocal MCP server that searches and answers questions over your own Markdown wiki
Runs locally- 4 tools
- Open source
- Knowledge and memory