Memtrace Structural Memory
Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · Hermes · VS Code · Windsurf.
What is Memtrace Structural Memory?
Memtrace Structural Memory is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to structural memory for ai coding agents. bi-temporal graph, mcp-native, zero llm calls. cursor · claude code · codex · hermes · vs code · windsurf.
Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · Hermes · VS Code · Windsurf.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Structural memory for AI coding agents. Bi-temporal graph, M
Use Cases
Maintainer
Works with
Installation
NPM
npx -y memtraceManual Installation
npx -y memtraceConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Memtrace Structural Memory
Memtrace is a structural memory layer for AI coding agents, built as a bi-temporal knowledge graph that tracks AST-driven symbols, their relationships, and how they evolve over time — without making any LLM calls for retrieval. It supports 16+ programming languages and integrates with Claude Code, Cursor, Codex, Windsurf, VS Code, Hermes, and others, providing 25+ MCP tools for code search, impact analysis, complexity detection, API topology mapping, and temporal evolution queries.
Prerequisites
- Node.js 18 or higher (LTS recommended)
- Git installed (required for temporal analysis features; full repo history gives best results)
- At least 8 GB RAM (16-32 GB recommended for large monorepos)
- 5 GB free disk space
- An MCP-compatible coding agent: Claude Code, Cursor, Codex, Windsurf, VS Code Copilot, Hermes, OpenCode, or Kiro
Install Memtrace globally
Install the memtrace npm package globally. The installer handles MCP configuration for all supported editors automatically.
npm install -g memtraceRun the automatic setup
The install command detects your editors and configures MCP settings, skills files, and indexing hooks for each one.
memtrace installAdd to your MCP client configuration manually
For clients like Cline or Roo Code that require manual setup, add this block to your MCP config file.
{
"mcpServers": {
"memtrace": {
"command": "memtrace",
"args": ["mcp"],
"env": {}
}
}
}Index your codebase
Ask your coding agent to index the project, or invoke the index_directory tool directly. Memtrace parses ASTs, resolves symbols, and builds the graph.
(Optional) Enable live incremental indexing
Use watch_directory to keep the graph updated as you edit files, so the agent always sees the current state of the codebase.
(Optional) Disable telemetry
Memtrace collects anonymous usage telemetry by default. Set the environment variable to opt out.
export MEMTRACE_TELEMETRY=off
# Or add to your MCP env config:
# "env": { "MEMTRACE_TELEMETRY": "off" }Memtrace Structural Memory Examples
Client configuration (Claude Code / stdio)
MCP server configuration for Claude Code or Claude Desktop.
{
"mcpServers": {
"memtrace": {
"command": "memtrace",
"args": ["mcp"],
"env": {
"MEMTRACE_TELEMETRY": "off"
}
}
}
}Prompts to try
Natural language queries that automatically trigger the appropriate Memtrace MCP tools.
- "Find where the authentication module is defined in this codebase."
- "Show me all functions that call the payment processor."
- "What is the blast radius if I refactor the UserService class?"
- "Identify all unused helper functions in the src/ directory."
- "Map out the service dependencies and HTTP API endpoints."
- "What changed in the auth module over the last two weeks?"Troubleshooting Memtrace Structural Memory
Indexing is slow or runs out of memory on a large monorepo
Ensure you have at least 16 GB RAM. For very large repos, index specific subdirectories first with index_directory rather than the entire project root.
Temporal analysis returns no results
Memtrace requires full Git history for evolution queries. Ensure you cloned with full history (not a shallow clone) and that Git is accessible in PATH.
MCP server not appearing in the coding agent after install
Re-run 'memtrace install' and restart your editor. For manual setup, verify the config file path matches your editor's expected location (see the installation table in the README).
Frequently Asked Questions about Memtrace Structural Memory
What is Memtrace Structural Memory?
Memtrace Structural Memory is a Model Context Protocol (MCP) server that structural memory for ai coding agents. bi-temporal graph, mcp-native, zero llm calls. cursor · claude code · codex · hermes · vs code · windsurf. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Memtrace Structural Memory?
Install via npm with the command: npx -y memtrace. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Memtrace Structural Memory?
Memtrace Structural Memory works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Memtrace Structural Memory free to use?
Yes, Memtrace Structural Memory is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Memtrace Structural Memory Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Memtrace Structural Memory? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Memtrace Structural Memory in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Memtrace Structural Memory?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.