mcpField
M
MCP APP

MCP APP

Local
github.com/sdkim96Memory & Knowledge1Updated 82w ago
Repository

About MCP APP

MCP APP is an MCP server application with RAG and web-search tools for LLM workflows that retrieve and expand document-based context. It uses PostgreSQL with PGVector for storage and OpenAI for embeddings.

Key features

  1. 01RAG retrieval tools
  2. 02Add documents to expand context
  3. 03Web-search tools
  4. 04PostgreSQL database interaction
  5. 05PGVector vector storage

Use cases

  1. 01Retrieve material from a vector store
  2. 02Add new documents to searchable context
  3. 03Supplement information with web searches

MCP support

The project implements an MCP server application that exposes RAG and web-search tools to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCP APP

This repository serves an MCP application with RAG and Web Searching tools. RAG tools let LLM not only retrieve knowledge from vectorstore but add documents, augmenting size of knowledge that LLM uses.

Technology stack

  • ⚙️ MCP Server Application for implementation of MCP server.
  • 🧰 SQLAlchemy for the SQL database interaction (ORM)
  • 🤖 OpenAI for the embedding of vectorstore.
  • 💾 PostgreSQL as the SQL database.
  • 🦜 PGVector as vectorstore.

QuickStart

uv sync
source .venv/bin/activate
mcp dev run

Combining Claude Desktop with MCP APP

# You must install all dependencies written in pyproject.toml
mcp install server.py --env-file .env --with sqlalchemy --with pgvector --with openai --with "psycopg[binary]" --with pydantic --with python-dotenv --with tavily-python

Preview of Claude Desktop

First Query Second Query Result of execution of adding document to db

TODO

  • Make asynchronous implementations.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.