MemoryBase MCP Server
MCP server that logs insights from Claude sessions and sends them via HTTP to a server for Telegram notification and storage in memoryBase.
README
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_insight - MCP 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
Architecture
Claude (any session)
↓
MCP (log_insight)
↓ HTTP POST
Server (tg-bot)
↓
Telegram notification
↓
User confirms → saves to memoryBase
Tools
| Tool | Description |
|---|---|
log_insight |
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-mcp
2. Create virtual environment
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
3. Configure environment
cp .env.example .env
nano .env
Fill 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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.