mcpField
M
MCPBot

MCPBot

Local
gkenios.github.ioDeveloper Tools2Updated 64w ago
RepositoryVisit website

About MCPBot

MCPBot is a thesis project implementing an MCP client and server with FastAPI. It is designed to run locally or with Azure resources; local setup can use a supplied ChromaDB folder or create a vector database from documents.

Key features

  1. 01MCP client and server implementation
  2. 02Built with FastAPI
  3. 03Local or Azure-based operation
  4. 04Create a vector database from documents

Use cases

  1. 01Run the project locally
  2. 02Use the project with Azure resources
  3. 03Create a vector database from documents

MCP support

MCPBot implements both an MCP client and an MCP server. The README does not describe which tools or resources the server exposes, or how the client manages server connections.

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

MCPBot

Documentation: https://gkenios.github.io/mcpbot

An implementation of an MCP client and server, using FastAPI. Designed for running locally or using Azure resources.

To Do

  • Change OAuth2 to the new MCP OAuth2 flow

Local

To run locally

  • Run uv sync --group local
  • In the .env file, set the secrets defined in the mcpbot/config-local.py file
  • If you have access download the whole .chromadb folder this link and place it in the root directory of the project.
    Otherwise, create your own vector database using the scripts/create_document.py script.

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.