New in v3.1
MCP Integration
Give your AI tools persistent memory with the Model Context Protocol (MCP). Works with Claude, ChatGPT, Gemini, Cursor, VS Code, Windsurf, and any MCP-compatible tool.
What is MCP?
The Model Context Protocol (MCP) is an open standard that enables AI assistants to connect to external tools and data sources. ACE implements MCP to give any compatible AI tool access to your memory infrastructure - no custom integrations needed.
Supported AI Tools & IDEs
ACE MCP works with any MCP-compatible tool. Here are the most popular:
What ACE MCP Provides
20 Tools
Executable functions the AI can call to store, search, and manage memories
ace_rememberace_recallace_get_contextace_searchace_track_issueace_resolve_issueace_find_solutionsace_track_decisionace_best_practicesace_get_statsace_log_workace_architectureace_patternsace_manage_tagsace_graph_traverseace_graph_connectace_graph_relatedace_graph_listace_generate_planace_create_plan9 Resources
Read-only data accessible via ace:// URIs
ace://{namespace}/memoriesace://{namespace}/decisionsace://{namespace}/issuesace://{namespace}/work-logsace://{namespace}/architectureace://{namespace}/patternsace://{namespace}/best-practicesace://{namespace}/statsace://{namespace}/graph6 Prompts
Pre-built slash commands for common workflows
/review-code/start-session/end-session/document-decision/track-bug/find-contextQuick Start
1. Install & Start ACE
# Requires Node.js 18+ npm install -g @ace3-memory/ace ace login ace init ace start
2. Configure Your AI Tool
Add ACE to your MCP configuration (example for Claude Desktop):
{
"mcpServers": {
"ace": {
"command": "ace",
"args": ["mcp", "start"],
"env": {
"ACE_NAMESPACE": "my-project"
}
}
}
}3. Use It
Your AI can now use ACE tools. Try asking:
- "Remember that we use PostgreSQL for the auth database"
- "What do you know about our authentication system?"
- "Track an issue: the login form has a race condition"