広告掲載
MCP.so
ログイン

Agent Knowledge MCP Server

@Ddhjx-code

リポジトリ

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

Ddhjx-code

投稿者

Zijing Wang

Agent Knowledge MCP Server について

AI agent面试skill，可以模拟面试过程

#aiagent-agent-knowledeg

Agent Knowledge 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": {
    "interview-rag": {
      "command": "uvx",
      "args": [
        "mcp-server-interview-rag"
      ]
    }
  }
}

Agent Knowledge 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。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is Agent Knowledge?

Agent Knowledge is an MCP (Model Context Protocol) server that powers AI Agent job interview simulations with a RAG knowledge base. It integrates FAISS vector search and a Chinese embedding model (BAAI/bge-base-zh-v1.5) to provide semantic retrieval from the hello-agents tutorial and Agent-Learning-Hub external resources. It is designed for developers preparing for AI Agent technical interviews.

How to use Agent Knowledge?

Install dependencies (pip install -r interview_rag_server/requirements.txt), build the FAISS index by running the provided scripts, then configure the MCP server in .claude/settings.json. Use it through Claude Code’s /interview skill; no direct invocation is needed.

Key features of Agent Knowledge

  • Semantic knowledge retrieval via FAISS vector index (1086 vectors, 768-dim)
  • Three MCP tools: search_knowledge, get_interview_questions, get_learning_path
  • Uses BAAI/bge-base-zh-v1.5 for Chinese embeddings
  • Knowledge sources include 16-chapter tutorial and 90+ external resources
  • Zero-infrastructure, single-file persistence for vector store

Use cases of Agent Knowledge

  • Real-time knowledge lookup during AI Agent mock interviews
  • Dynamically retrieving interview questions based on candidate’s weak topics
  • Generating personalized learning paths for interview preparation

よくある質問

1

What dependencies are required?

Python packages: `fastmcp>=2.0.0`, `faiss-cpu>=1.7.4`, `sentence-transformers>=2.2.0`.

2

How is the knowledge base built?

Run `python -m interview_rag_server.knowledge_base.build_index` after cloning two source repos and fetching web sources. The index is created under `interview_rag_server/data/`.

3

Where is the data stored?

The FAISS index (`faiss_index.bin`) and metadata (`metadata.json`) reside in the `interview_rag_server/data/` directory.

4

What parameters does `search_knowledge` accept?

It accepts `query` (required), `topic` (optional), and `top_k` (optional).

5

Can Agent Knowledge run offline?

Yes, set the environment variable `HF_HUB_OFFLINE=1` and ensure the embedding model is cached locally.

コメント

「AI とエージェント」の他のコンテンツ

superbot

EZO Labs

superbot is your own AI agent: anything you can do on your computer, it can do, fast. Its MCP server gives other agents one tool for errands: fax, calls, texts, Gmail drafts, calendar, web search. Free in your browser, n

Poly-Glot AI Workspace

hmoses

1,000+ fully localized prompt templates across 40+ categories. Compare Mode — send the same prompt to up to 9 AI providers (ChatGPT, Claude, Gemini, Grok, Groq, Copilot, Mistral, Perplexity, DuckDuckGo AI) and compare an

HeyLead: LinkedIn Outreach & Lead Generation MCP Server

D4umak

HeyLead: AI agent for LinkedIn outreach. Finds the right people, writes in your voice, follows up and handles replies, from Claude Code, Cursor, any MCP client or a web dashboard.

9

SlopIt

SimbaStack

Instant blogs for AI agents: a publishing CMS with no dashboard. One signup call returns a blog, an API key and a live URL; then publish markdown posts and get public URLs back.

Agent Traffic Lab

Agent Traffic Lab

ATL doesn’t just help agents find tools — it gets the job done. It finds and chooses the right AI provider, tool, or MCP server, executes the task, and switches to a fallback when a provider fails. It can optimize for lo

広告掲載