OpenViking MCP Server

OpenViking MCP Server

Provides semantic search and tiered loading (L0/L1/L2) to access OpenViking context DB from Claude Code, saving tokens by loading only the needed detail.

Category
Visit Server

README

OpenViking MCP Server

Claude Code から OpenViking のコンテキストDBにアクセスするMCPサーバー。

L0/L1/L2の段階的ロードでトークンを大幅に節約します。

特徴

  • セマンティック検索 — 自然言語クエリで設計書・ドキュメントを横断検索
  • 段階的ロード — L0要約(~100tok) → L1概要(~2ktok) → L2全文。必要な粒度だけ読む
  • ローカル完結 — OpenViking fork の local provider と組み合わせればAPI課金ゼロ
  • 7 tools — find / read / ls / add / abstract / overview / grep

前提

  • OpenVikingサーバーが localhost:1933 で起動済み
  • Python 3.10+

セットアップ

# 1. 依存インストール
pip install -r requirements.txt

# 2. プロジェクトルートに .mcp.json を作成（または既存ファイルに追記）

{
  "mcpServers": {
    "openviking": {
      "command": "python3",
      "args": ["/path/to/openviking-mcp/server.py"],
      "env": {
        "OPENVIKING_URL": "http://127.0.0.1:1933"
      }
    }
  }
}

# 3. Claude Codeを再起動

Tools

Tool 説明 トークンコスト
viking_find セマンティック検索。L0要約付きで返す 低
viking_abstract URIのL0要約を取得 最小
viking_overview URIのL1概要を取得 中
viking_read URIのL2全文を取得 高
viking_ls ディレクトリ一覧（L0要約付き） 低
viking_add ローカルファイルをリソース追加 —
viking_grep テキストパターン検索 低

使い方のフロー

1. viking_find("古賀凛のGhost") → L0要約付きリスト
   → "キャラ設計の古賀Ghost形成過程" (score: 0.50)

2. L0で「場所は分かったけど詳細が欲しい」
   → viking_overview("viking://resources/characters/koga-rin") → L1概要

3. L1で「具体的な記述が必要」
   → viking_read("viking://resources/characters/koga-rin/ghost.md") → L2全文

Claude Codeは各toolのdescriptionに従い、L0 → L1 → L2の順で必要最小限だけ読みます。

ローカルembedding（API課金ゼロ）

OpenViking fork の local provider を使うと、embeddingもローカルで完結します。

// ~/.openviking/ov.conf
{
  "embedding": {
    "dense": {
      "provider": "local",
      "model": "intfloat/multilingual-e5-large",
      "device": "mps"
    }
  }
}

ライセンス

Apache-2.0

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured