memory-mcp
Manage and analyze episodic memory via MCP tools to retrieve historical context and identify behavioral patterns.
Install
mkdir -p .claude/skills/memory-mcp && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/395" && unzip -o skill.zip -d .claude/skills/memory-mcp && rm skill.zipInstalls to .claude/skills/memory-mcp
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
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.Key capabilities
- →Query episodic memory
- →Analyze interaction patterns
- →Perform predictive modeling
- →Monitor server health metrics
- →Validate MCP implementation
How it works
It exposes episodic memory through the Model Context Protocol, allowing tools to query and analyze historical interaction data.
Inputs & outputs
When to use memory-mcp
- →Retrieving past project context using query_memory
- →Analyzing user interaction patterns for behavior insights
- →Validating the integration of a Memory MCP server
- →Troubleshooting memory retrieval failures
About this skill
Memory MCP Server
Interacts 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
- Token Optimization - Reduce token usage by 80-85%
When to Use
- Starting or configuring the do-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 do-memory-mcp server exposes episodic memory functionality through the Model Context Protocol:
- Query past experiences and learned patterns
- Analyze successful strategies from historical episodes
- Perform advanced statistical and predictive analysis
- Monitor server health and metrics
- Note:
execute_agent_codeis unavailable / fail-closed (WASM sandbox removed; no working execution backend)
Location: ./target/release/do-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 | Unavailable / fail-closed (WASM sandbox removed) |
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 do-memory-mcp-server
# Run directly
export TURSO_DATABASE_URL="file:./data/memory.db"
./target/release/do-memory-mcp-server
# Run via MCP Inspector for testing
npx -y @modelcontextprotocol/inspector ./target/release/do-memory-mcp-server
See configuration.md for full environment setup and validation.md for MCP Inspector workflow.
When not to use it
- →Real-time code execution
- →Non-episodic data storage
Prerequisites
Limitations
- →Execution backend is unavailable
- →Requires specific server configuration
How it compares
It provides a standardized protocol for memory retrieval compared to custom database queries.
Compared to similar skills
memory-mcp side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| memory-mcp (this skill) | 6 | 28d | Review | Intermediate |
| massgen-log-analyzer | 1 | 4mo | Review | Advanced |
| python-repl | 6 | 4mo | Review | Beginner |
| memory-systems | 9 | 4mo | No flags | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
massgen-log-analyzer
massgen
Run MassGen experiments and analyze logs using automation mode, logfire tracing, and SQL queries. Use this skill for performance analysis, debugging agent behavior, evaluating coordination patterns, and improving the logging structure, or whenever an ANALYSIS_REPORT.md is needed in a log directory.
python-repl
gptme
Interactive Python REPL automation with common helpers and best practices
memory-systems
sickn33
Design short-term, long-term, and graph-based memory architectures
agent-v3-memory-specialist
ruvnet
Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist
context-degradation
muratcankoylan
This skill should be used when the user asks to "diagnose context problems", "fix lost-in-middle issues", "debug agent failures", "understand context poisoning", or mentions context degradation, attention patterns, context clash, context confusion, or agent performance degradation. Provides patterns for recognizing and mitigating context failures.
langsmith-fetch
ComposioHQ
Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior, investigating errors, analyzing tool calls, checking memory operations, or examining agent performance. Automatically fetches recent traces and analyzes execution patterns. Requires langsmith-fetch CLI installed.