Agent Memory Mcp
Provides MCP tools guidance and assistance for orchestrating AI agents and multi-step workflows.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add hainamchung-agent-memory-mcp npx -- -y @trustedskills/hainamchung-agent-memory-mcp
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"hainamchung-agent-memory-mcp": {
"command": "npx",
"args": [
"-y",
"@trustedskills/hainamchung-agent-memory-mcp"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill, hainamchung-agent-memory-mcp, provides an Agent Memory Cache using Microsoft Cosmos DB. It allows agents to store and retrieve information across multiple interactions, enabling them to maintain context and build upon previous conversations or tasks. This persistent memory improves agent performance in complex workflows requiring long-term recall.
When to use it
- Complex Task Management: For agents handling multi-step processes that require remembering details from earlier steps (e.g., booking travel arrangements).
- Personalized Interactions: To enable agents to remember user preferences or past interactions for a more tailored experience.
- Knowledge Base Integration: To store and retrieve information from an external knowledge base, allowing the agent to answer questions based on previously accessed data.
- Long-Running Conversations: When you need an agent to maintain context over extended conversations that span multiple sessions.
Key capabilities
- Microsoft Cosmos DB integration for persistent memory storage
- Agent Memory Cache functionality
- Ability to store and retrieve information across interactions
Example prompts
- "Remember I prefer flights with window seats."
- "What was the last item I added to my shopping list?"
- "Based on our previous conversations, what are my dietary restrictions?"
Tips & gotchas
- Requires a Microsoft Cosmos DB account and connection string for proper functionality.
- Consider data privacy and security implications when storing user information in persistent memory.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.