MCP server · Developer tools
Vexor MCP server
by scarletkc
Lets your AI find files and code by describing what they do, not by remembering their names.
Vexor is a search helper that finds files on your computer by meaning instead of exact names. You describe what you are looking for in plain words, and it points you to the right file. It is handy if you work with lots of documents or code and often remember what a file does but not what it is called.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI one extra skill, here the skill of searching your files and code by description. Once it is connected, your AI can ask Vexor to look through a folder and come back with the files that match what you described. You just ask in normal words, and the AI does the looking for you.
What this MCP server does
You tell your AI what you are trying to find, in your own words. The AI passes that description to Vexor through this helper. Vexor looks through the folder you pointed it at, builds a small index of what each file is about, and ranks the files by how well they match. Your AI then shows you the best matches, usually with a short preview of the content so you can spot the right one quickly.
Click to zoomWhat you can do with it
- Find a file by describing what it does, like config loader or login page
- Search inside a specific project folder instead of your whole computer
- Get short previews of the matching files right in the chat
- Build or refresh the search index for a folder before you search
- Search code and documents together in the same query
- Work fully offline if you set it up with a local model
Try asking your AI
- “Find the file that loads our app configuration”
- “Which file handles user login in this project?”
- “Search my notes folder for anything about the budget meeting”
- “Look in this project for code that talks to the payment service”
What it gives back to you
You get back a short list of matching files, each with a similarity score and a preview of the content. The preview usually gives you enough to know if it is the right file, so you often do not need to open anything else. If you asked it to build an index, it tells you that the index is ready.
Before you start
What you need
- Vexor installed on your computer (either the standalone download or pip install vexor)
- An API key from an embedding provider such as OpenAI, Gemini or Voyage, unless you set it up to run fully offline with a local model
- An MCP-capable AI client, such as Claude Code, Cursor, Windsurf or Zed
Good to know
Vexor reads the files in the folders you point it at, so avoid aiming it at folders with private or sensitive material unless you are comfortable with that.
Install it with your AI
Add Vexor MCP server to your AI, no technical skills needed
You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.
Sign in to get the install prompt
Members get a ready-made prompt that lets the Claude desktop app check Vexor MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.
Who it's for
Anyone who works with a lot of files or code and often remembers what something does but not where it lives, especially developers, writers and researchers.
