MCP.so
Sign In

Agent Knowledge

@Ddhjx-code

Repository

About Agent Knowledge

AI agent面试skill，可以模拟面试过程

#aiagent-agent-knowledeg

Config

Add this server to your MCP-compatible client using the configuration below.

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

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

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

FAQ from Agent Knowledge

What dependencies are required?

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

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/.

Where is the data stored?

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

What parameters does search_knowledge accept?

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

Can Agent Knowledge run offline?

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

Frequently asked questions

What dependencies are required?

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

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/`.

Where is the data stored?

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

What parameters does `search_knowledge` accept?

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

Can Agent Knowledge run offline?

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

Comments

Basic information

Category

AI & Agents

Transports

stdio

Author

Ddhjx-code

Submitted by

Zijing Wang

More AI & Agents MCP servers

LinkedIn MCP Server

stickerdaniel

Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI agent access to profiles, companies, jobs, and messages.

2.7K

Shell and Coding agent for Claude and other mcp clients

rusiaaman

Shell and coding agent on mcp clients

666

Mcp Agent

lastmile-ai

Build effective agents using Model Context Protocol and simple workflow patterns

8.4K

MCP Client for Ollama (ollmcp)

jonigl

Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre

768

欢迎来到 智言平台

Shy2593666979

AgentChat 是一个基于 LLM 的智能体交流平台，内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作，Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术，实现高效的知识检索与工具调用，使用 FastAPI 构建高性能后端服务。

797