
memory-mcp
by d-o-hub
A modular Rust-based self-learning episodic memory system for AI agents, featuring hybrid storage with Turso (SQL) and redb (KV), async execution tracking, reward scoring, reflection, and pattern-based skill evolution. Designed for real-world applicability, maintainability, and scalable agent workflows.
SKILL.md
name: memory-mcp description: Use and troubleshoot the Memory MCP server for episodic memory retrieval and pattern analysis. Use when working with MCP server tools, validating the MCP implementation, or debugging MCP server issues.
Memory MCP Server
Interact with and troubleshoot the Memory Model Context Protocol (MCP) server for the self-learning memory system.
Quick Reference
- Tools - Complete MCP tools reference (query_memory, analyze_patterns, etc.)
- Configuration - .mcp.json structure and environment variables
- Validation - MCP Inspector validation workflow
- Troubleshooting - Common issues and solutions
- Best Practices - Tool usage, configuration, and testing guidelines
When to Use
- Starting or configuring the memory-mcp server
- Using MCP tools for memory retrieval and pattern analysis
- Validating the MCP server implementation
- Debugging MCP server issues
- Testing MCP tools using the MCP inspector
- Understanding MCP configuration and environment variables
MCP Server Overview
The memory-mcp server exposes episodic memory functionality through the Model Context Protocol:
- Query past experiences and learned patterns
- Analyze successful strategies from historical episodes
- Execute code in a secure sandbox environment
- Perform advanced statistical and predictive analysis
- Monitor server health and metrics
Location: ./target/release/memory-mcp-server
Configuration: .mcp.json
Transport: stdio (Standard Input/Output)
Available MCP Tools
| Tool | Purpose |
|---|---|
query_memory | Query episodic memory for relevant past experiences |
analyze_patterns | Analyze patterns from past episodes |
advanced_pattern_analysis | Statistical analysis, predictive modeling |
execute_agent_code | Execute TypeScript/JavaScript in sandbox |
health_check | Check server health status |
get_metrics | Get comprehensive monitoring metrics |
See tools.md for detailed tool documentation and best-practices.md for usage guidelines.
Starting the Server
# Build
cargo build --release --bin memory-mcp-server
# Run directly
export TURSO_DATABASE_URL="file:./data/memory.db"
./target/release/memory-mcp-server
# Run via MCP Inspector for testing
npx -y @modelcontextprotocol/inspector ./target/release/memory-mcp-server
See configuration.md for full environment setup and validation.md for MCP Inspector workflow.
Score
Total Score
Based on repository quality metrics
SKILL.mdファイルが含まれている
ライセンスが設定されている
100文字以上の説明がある
GitHub Stars 100以上
1ヶ月以内に更新
10回以上フォークされている
オープンIssueが50未満
プログラミング言語が設定されている
1つ以上のタグが設定されている
Reviews
Reviews coming soon



