MCP Knowledge Base Reader

@fmicalizzi

リポジトリ

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

fmicalizzi

MCP Knowledge Base Reader について

MCP server for reading JSON knowledge bases without modifications

MCP Knowledge Base Reader 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

MCP Knowledge Base Reader 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 MCP Knowledge Base Reader?

It is a Model Context Protocol (MCP) server that reads a structured JSON knowledge base and makes its information available to Claude or other LLMs. It is designed for users who want to provide a curated, static knowledge base to an AI assistant without modifying the underlying data.

How to use MCP Knowledge Base Reader?

Install Node.js 18 or higher, clone the repository, install dependencies, and compile the TypeScript code (npm run build). Then configure it in your MCP client (e.g., Claude Desktop) by adding an entry to claude_desktop_config.json with the compiled script path and the KNOWLEDGE_BASE_PATH environment variable set to the absolute path of your JSON file. After configuration, the server’s tools become available for the LLM to call.

Key features of MCP Knowledge Base Reader

Reads structured JSON knowledge bases
Searches entries by keyword in title, content, and tags
Retrieves a specific entry by its ID
Filters entries by category or tags
Finds related entries for a given entry
Provides statistics on the knowledge base
Purely read-only; never modifies the JSON file

Use cases of MCP Knowledge Base Reader

A Claude assistant that answers questions using a curated company knowledge base
Searching for definitions or procedures by keyword in a reference database
Exploring entries within a specific category (e.g., “introduction to MCP”)
Finding related topics after reviewing an entry
Getting an overview of the knowledge base structure and content

よくある質問

What are the runtime requirements?

Node.js 18 or higher and npm or yarn are required.

How do I configure the server for Claude Desktop?

Add an entry to `claude_desktop_config.json` with the command set to `node`, args pointing to the absolute path of the compiled `dist/index.js`, and the environment variable `KNOWLEDGE_BASE_PATH` set to the absolute path of your JSON knowledge base file.

Why do I get a “Server disconnected” error?

This usually happens when paths are not absolute or incorrect, the compiled JavaScript file doesn’t exist at the specified location, or the user lacks execution permissions. Verify all paths and permissions.

Does the server modify my JSON knowledge base?

No. The server operates in read-only mode. It only retrieves information and never writes to the JSON file.

What tools does the server expose?

It exposes seven tools: `read_knowledge_base`, `search_entries`, `get_entry_by_id`, `get_entries_by_category`, `get_entries_by_tags`, `get_related_entries`, and `get_knowledge_stats`.

「メモリとナレッジ」の他のコンテンツ

LoreKeeper RPG (lorekeeper.com)

LoreKeeper Ltd

Mess in, magic out: pour in your D&D and TTRPG notes and LoreKeeper keeps them as a private store for your world. Ask Claude or ChatGPT about it, or build a sourcebook.

Groundwork

Rarefied-Earth

Groundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.

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

OpenLore

aakarim

Serve your docs to AI agents over SSH and MCP. Agents use ls, cat, grep, find, and pipes against a virtual filesystem backed by your documentation. Identity-scoped access, governed writing with human approval, and portab

ctxfile

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