広告掲載
MCP.so
ログイン
M

Memtrace MCP Server

@syncable-dev

リポジトリ

基本情報

カテゴリ

その他

トランスポート

stdio

作者

syncable-dev

投稿者

Lishuai Jing

Memtrace MCP Server について

Memtrace — Structural Memory for AI Coding Agents

#memory#code-intelligence#knowledge-graph#ast#structural-analysis#codebase-context#agent-memory#blast-radius#temporal-memory#bi-temporal#hybrid-search#graph-rag#developer-tools-ai-agents

Memtrace MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "memtrace": {
      "command": "memtrace",
      "args": [
        "mcp"
      ],
      "env": {
        "MEMTRACE_ARCADEDB_BOLT_URL": "bolt://localhost:7687"
      }
    }
  }
}

Memtrace MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Memtrace?

Memtrace is a structural memory layer for AI coding agents, delivered as an MCP server. It compiles any codebase into a live, bi-temporal knowledge graph from the AST, enabling agents like Claude Code, Cursor, Windsurf, and Zed to instantly query callers, callees, blast radius, dependency chains, and code evolution without re-reading source files on every turn.

How to use Memtrace?

Install Memtrace with a single command (npm install -g memtrace), start the graph server (memtrace start), and index your repository (memtrace index .). The MCP server starts automatically and connects to any MCP-compatible agent. No configuration, cloud account, or telemetry required.

Key features of Memtrace

  • Structural knowledge graph compiled from the AST across 12 languages and 3 IaC formats.
  • Bi-temporal episodic memory enables time-travel through code history beyond git commits.
  • Blast radius analysis computes exactly which files, functions, and services break before any change.
  • Hybrid retrieval engine fused BM25, HNSW vector search, and graph traversal.
  • Six traversal strategies: Impact, Novel, Recent, Compound, Directional, and Overview.
  • API topology mapping for cross-service dependency chains and dead endpoint detection.
  • 40+ MCP tools covering indexing, search, relationships, impact analysis, and graph algorithms.
  • Local-first, closed-source Rust—code never leaves the machine, no account, no telemetry.

Use cases of Memtrace

  • Giving AI coding agents persistent structural memory to reduce token waste by up to 90%.
  • Computing blast radius before a refactor—knowing exactly which callers, services, and tests break.
  • Detecting structural drift and regressions mid-session, catching breaking changes the moment they happen.
  • Onboarding agents to large, unfamiliar codebases instantly with full symbol graph and dependency tree queryable from the first turn.
  • Time-travelling through code evolution to understand how a function, type, or module changed over time.

よくある質問

1

What agents and IDEs does Memtrace work with?

Memtrace works with any MCP-compatible agent or IDE, including Claude Code, Cursor, Zed, VS Code, Windsurf, Continue, Aider, and OpenAI Codex CLI.

2

Does Memtrace send my code to the cloud?

No. Memtrace is fully local-first. Your code never leaves your machine. There is no account, no telemetry, and no cloud dependency.

3

How long does indexing take?

Initial indexing typically completes in seconds for most repositories. Each file save triggers an incremental re-index that completes in 200–800ms.

4

Which programming languages are supported?

Memtrace supports 12 programming languages and 3 IaC formats via Tree-sitter grammars: TypeScript, JavaScript, Python, Rust, Go, Java, C, C++, Ruby, PHP, C#, Swift, plus Terraform, Kubernetes, and Docker.

5

How is Memtrace different from RAG-based code search tools?

RAG tools return lexically or semantically similar snippets. Memtrace returns structurally meaningful answers—the actual callers, real blast radius, and deterministic dependency chains—because it reasons over a compiled knowledge graph, not over embeddings.

6

Does Memtrace replace existing tools like LSP or GitHub Copilot?

No. Memtrace is additive. It gives agents a structural memory layer that LSP servers and embedding-based tools don't provide. Existing tools keep working; agents gain access to 40+ additional MCP tools for graph-based reasoning.

コメント

「その他」の他のコンテンツ

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K

YOUB

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

DeepMark

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

FastMCP v2 🚀

jlowin

🚀 The fast, Pythonic way to build MCP servers and clients.

26.0K

Senso MCP for Joomla

sensomedia

Senso MCP turns a Joomla 5 or 6 site into a remote MCP server. It runs inside Joomla itself (no extra server, no Node.js bridge) and is secured with OAuth 2.1 and Joomla's own ACL. The free pack lets an AI assistant crea

広告掲載