MemoryBase MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MemoryBase MCP ServerLog this feature implementation as a feature insight"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MemoryBase MCP Server
MCP server that sends insights from Claude sessions to your server.
How it works
You add this MCP server to Claude Code / Claude Desktop
When Claude completes significant tasks, it calls
log_insightMCP sends HTTP request to your server (tg-bot)
Server sends Telegram notification with [Да] [Изменить] [Нет] buttons
You confirm → insight is analyzed and saved to memoryBase
Related MCP server: Claude Memory
Architecture
Claude (any session)
↓
MCP (log_insight)
↓ HTTP POST
Server (tg-bot)
↓
Telegram notification
↓
User confirms → saves to memoryBaseTools
Tool | Description |
| Log an insight (feature, bugfix, plan, idea, decision, learning) |
Triggers
Claude should call log_insight after:
Completing a large feature
Fixing a complex bug
Finishing a multi-step plan (5+ steps)
Making an important architectural decision
Learning something valuable
Installation
1. Clone the repository
git clone git@github.com:veryCoolTimo/memorybase-mcp.git
cd memorybase-mcp2. Create virtual environment
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt3. Configure environment
cp .env.example .env
nano .envFill in:
SERVER_URL- URL of your server with tg-bot (e.g.,http://your-server:8585)API_SECRET- Secret key (must match tg-bot's API_SECRET)
4. Add to Claude Code
Edit ~/.claude/claude_desktop_config.json:
{
"mcpServers": {
"memorybase": {
"command": "/path/to/memorybase-mcp/venv/bin/python",
"args": ["/path/to/memorybase-mcp/server.py"],
"env": {
"SERVER_URL": "http://your-server:8585",
"API_SECRET": "your_secret"
}
}
}
}Or for Claude Code CLI, add to your project's .mcp.json:
{
"mcpServers": {
"memorybase": {
"command": "python",
"args": ["./tools/memorybase-mcp/server.py"],
"env": {
"SERVER_URL": "http://your-server:8585",
"API_SECRET": "your_secret"
}
}
}
}Usage
Once configured, Claude will automatically log insights. You can also explicitly ask:
"Log this as a feature insight for project X"License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Cloud-hosted MCP server for durable AI memory
Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.
Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA local MCP server that enables direct, persistent communication between multiple Claude Code agent sessions through a secure messaging channel. It includes built-in guardrails to manage message exchanges and supports optional human monitoring via Telegram.-
- AlicenseNot gradedqualityDmaintenanceA lightweight MCP server that gives Claude Code Channels on Telegram persistent memory by storing facts, conversation logs, and session summaries in Supabase.25 npm7MIT
- AlicenseNot gradedqualityDmaintenanceMCP Memory Server for Claude Code that provides persistent context across sessions using semantic search (RAG).Apache 2.0
- AlicenseNot gradedqualityCmaintenancePersistent memory MCP server for Claude Code that stores decisions and summaries locally, enabling Claude to recall past context across chats.1MIT