広告掲載
MCP.so
ログイン

Contexo MCP Server

@sugihAF

リポジトリホームページ

基本情報

カテゴリ

メモリとナレッジ

トランスポート

stdio

作者

sugihAF

投稿者

Sugih AF

Contexo MCP Server について

AI Agent Context Versioning and Synchronization

#ai#llm#context

Contexo 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": {
    "contexo": {
      "command": "ctx",
      "args": [
        "mcp"
      ]
    }
  }
}

Contexo 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 Contexo?

Contexo is an open-source MCP server that gives AI coding agents a persistent, shared memory of your project. Instead of re‑explaining architecture, conventions, and past decisions each session, agents pull what’s already known before starting work and push back what they learn afterward. Knowledge is stored in a git‑backed repository, making it versioned, diffable, reviewable, and shareable across teammates and tools—and because it’s built on MCP, the same knowledge can be used with Claude Code, Cursor, Codex, and other compatible agents.

How to use Contexo?

Contexo is available as an MIT‑licensed Go CLI and server that you can self‑host, plus an optional hosted version. Install the CLI and run the server to start capturing and sharing project context with your AI coding agents. The README does not provide specific installation or configuration commands.

Key features of Contexo

  • Persistent, versioned project memory stored in git
  • Section‑aware diffs and full history
  • Drift detection to flag outdated context
  • Agent‑assisted merges for collaborative updates
  • Structured capture of the why behind decisions
  • Cross‑agent compatibility via the MCP protocol

Use cases of Contexo

  • Avoid repeating architecture and conventions in every new AI session
  • Share project decisions, gotchas, and reasoning across a team
  • Keep context in sync between different AI coding tools (e.g., Claude Code and Cursor)
  • Track how project knowledge evolves over time with diffs and history

よくある質問

1

What problem does Contexo solve?

Contexo eliminates the “context tax” by giving AI agents a shared memory of your project, so they don’t need to re‑learn architecture, conventions, or past decisions every session.

2

How is Contexo different from storing context in `CLAUDE.md` or vendor‑specific memory?

Contexo centralizes context in a git‑backed repository that is versioned, diffable, reviewable, and shareable across teammates and tools, rather than scattering it in local files or vendor‑specific features.

3

Is Contexo open source and can I self‑host it?

Yes. Contexo is open‑core: the Go CLI and server are MIT‑licensed and can be self‑hosted. An optional hosted version is also available.

4

Which AI coding agents work with Contexo?

Contexo works with any MCP‑compatible agent, including Claude Code, Cursor, Codex, and others.

5

Where does project knowledge actually live?

Knowledge lives in a git‑backed repository, so it is versioned, diffs are visible, and the history is reviewable alongside your codebase.

コメント

「メモリとナレッジ」の他のコンテンツ

Context7 MCP - Up-to-date Docs For Any Cursor Prompt

upstash

Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

58.7K

server-noonien - shared memory MCP

sequico

Shared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph.

Sooveryn

PANDAPROG

Sooveryn gives Claude Code a team of AI personas that remembers your project. Soov, the partner and team lead, keeps your decisions and how you work in a lasting memory, and finds them again by words and by meaning, from

ctxfile

ctxfile

Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.

2

Leviathan Systems Public Content MCP

Leviathan Systems

Search published GPU deployment, rack integration and structured cabling resources; read canonical documents and Leviathan Systems company service scope. Anonymous, read-only Streamable HTTP MCP. No credentials required.

広告掲載