Skip to main content
Glama
Pacamaraprogress

Google Cloud Natural Language MCP Server

๐Ÿง  Google Cloud Natural Language API โ€” MCP Server

A Model Context Protocol (MCP) server that connects Claude to the Google Cloud Natural Language API, enabling sentiment analysis, entity extraction, content classification, and syntax analysis as native Claude tools.

๐Ÿ” No .env file needed. Your API key is stored securely in your local Claude Desktop config โ€” it never touches this repo.


โœจ Features

Tool

Description

analyze_sentiment

Detects overall and per-sentence emotional tone (-1.0 to +1.0)

extract_entities

Identifies people, places, orgs, dates, and more with salience scores

classify_content

Categorizes text using Google's content taxonomy with confidence scores

analyze_syntax

Tokenizes text and labels parts-of-speech and dependency roles


Related MCP server: Company MCP Server - Google Workspace Integration

๐Ÿ“‹ Prerequisites

  • Python 3.10+

  • A Google Cloud account

  • The Cloud Natural Language API enabled in your GCP project

  • A valid Google API Key

  • Claude Desktop installed


๐Ÿš€ Setup

1. Clone the repo

git clone https://github.com/YOUR_USERNAME/google-nl-mcp-server.git
cd google-nl-mcp-server

2. Create a virtual environment

python -m venv venv
source venv/bin/activate        # macOS/Linux
venv\Scripts\activate           # Windows

3. Install dependencies

pip install -r requirements.txt

4. Add your API key to Claude Desktop config

Your API key is configured locally in Claude Desktop only โ€” not in this repo. This means it is never exposed on GitHub.

Open your Claude Desktop config file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

Add the following block, replacing the path and key with your own:

{
  "mcpServers": {
    "google-nl": {
      "command": "python",
      "args": ["/absolute/path/to/google-nl-mcp-server/server.py"],
      "env": {
        "GOOGLE_API_KEY": "AIza..."
      }
    }
  }
}

๐Ÿ’ก Use the absolute path to server.py on your machine (e.g. /Users/yourname/projects/google-nl-mcp-server/server.py on macOS).

Then restart Claude Desktop. The tools will appear automatically in Claude's tool picker.


๐Ÿงช Example Usage with Claude

Once connected, you can ask Claude things like:

"Analyze the sentiment of this customer review: 'The product arrived late and was damaged. Very disappointing.'"

"Extract all the entities mentioned in this news article..."

"What category does this blog post belong to?"

"Break down the syntax of this sentence for me."

Claude will automatically call the appropriate tool and reason over the structured results.


๐Ÿ“ Project Structure

google-nl-mcp-server/
โ”œโ”€โ”€ server.py             # Main MCP server
โ”œโ”€โ”€ requirements.txt      # Python dependencies
โ”œโ”€โ”€ .gitignore            # Keeps secrets out of git
โ””โ”€โ”€ README.md             # You are here

๐Ÿ” Security Notes

  • Your API key lives only in claude_desktop_config.json on your local machine โ€” never in this repo

  • Restrict your Google API key to the Natural Language API only via GCP Console

  • Consider adding API key IP restrictions for extra security


๐Ÿ“š Resources


๐Ÿ“„ License

MIT License โ€” feel free to fork, modify, and use this in your own projects.

A
license - permissive license
-
quality - not tested
D
maintenance

Maintenance

โ€“Maintainers
โ€“Response time
โ€“Release cycle
โ€“Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Pacamaraprogress/naturallanguageapimcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server