MCP.so
ログイン

Claude Server MCP Server

@davidteren

基本情報

カテゴリ

AI とエージェント

トランスポート

stdio

作者

davidteren

Claude Server MCP Server について

Claude Server is an MCP implementation that enhances Claude's capabilities by providing sophisticated context management across sessions, enabling persistent knowledge organization through hierarchical project contexts and continuous conversation threads stored in a well-structur

Claude Server MCP Server の設定

標準の設定はありません

このサーバーの README には解析可能な MCP 設定ブロックが含まれていません。インストール手順はリポジトリをご確認ください。

リポジトリ

Claude Server 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 Claude Server MCP?

Claude Server MCP is a Model Context Protocol server that provides persistent context management for Claude, enabling organized context storage across sessions, project-specific context organization, and conversation continuity. It is intended for users who need to maintain and retrieve context information across multiple conversations with Claude.

How to use Claude Server MCP?

The server is automatically configured in the Claude desktop app’s MCP settings. Contexts are stored in ~/.claude/. Users invoke the server through Claude’s use_mcp_tool function with tools like save_project_context, save_conversation_context, get_context, and list_contexts. For development, clone the repository, run npm install, then npm run build.

Key features of Claude Server MCP

  • Hierarchical project context organization with parent-child relationships
  • Cross-referencing between contexts and project-specific metadata
  • Session-based conversation tracking and conversation chaining
  • Flexible tagging system with metadata-rich context storage
  • JSON-based storage with quick lookup indexing
  • Asynchronous operations and organized directory structure

Use cases of Claude Server MCP

  • Save and organize context from a design discussion for later reference
  • Chain related conversations under the same session for continuity
  • Retrieve project-specific context when resuming work after a break
  • Index and tag contexts for quick filtering by project or topic

よくある質問

1

What runtime and dependencies are required?

Node.js is required. The server is built with npm; install dependencies with `npm install` and build with `npm run build`.

2

Where is context data stored?

All contexts are stored locally in `~/.claude/`, organized into a `contexts/` directory, a `projects/` directory, and a `context-index.json` index file.

3

How is the server configured for use with Claude Desktop?

The server is configured in the Claude desktop app’s configuration file at `~/Library/Application Support/Claude/claude_desktop_config.json` under the `mcpServers` key.

4

What tools are available in Claude Server MCP?

Tools include `save_project_context`, `save_conversation_context`, `get_context`, and `list_contexts`. Each accepts specific arguments for IDs, project IDs, content, tags, and metadata.

コメント

「AI とエージェント」の他のコンテンツ