About Sarvam MCP Server
Sarvam MCP Server is an MCP server published by Shobhit-Nagpal in the Developer Tools category: talk to sarvam APIs directly, without code. It has been installed 0 times through Conduid.
The repository has 13 stars and 2 forks, with the last commit a year ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues (0) before depending on it in production.
Install
npx sarvam-mcp-serverThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Ask AI
Ask AI about Sarvam MCP Server
Powered by Claude · Grounded in docs
Security checks
- ·README presentNot checked yet.
- ·License declaredNot checked yet.
- ·Tests presentNot checked yet.
- ·Dependencies pinnedNot checked yet.
- ·No dynamic code executionNot checked yet.
- !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.
README
Sarvam MCP Server
An MCP server implementation that integrates the Sarvam API, providing comprehensive text processing capabilities for Indian languages.
Features
- Language Identification: Detect language and script of input text (e.g., en-IN, hi-IN, Latin, Devanagari)
- Text Analytics: Perform deep analysis and answer specific questions about text content
- Text Translation: Translate between languages with speaker gender, mode, and script controls
- Smart Processing: Support for numerals format, spoken form, and custom processing options
Tools
-
language-identification
- Identifies language and script of input text
- Inputs:
input(string): Text to identify language and script
-
text-analytics
- Performs comprehensive text analysis
- Inputs:
text(string): Text to analyzequestions(string[]): Array of questions to answer about the text
-
translate-text
- Translates text between languages
- Inputs:
input(string): Text to translatesource_language_code(string): Source language codetarget_language_code(string): Target language codespeaker_gender(string, optional): Speaker's gendermode(string, optional): Translation modemodel(string, optional): Translation modelenable_processing(boolean, optional): Enable additional processingoutput_script(string, optional): Target scriptnumerals_format(string, optional): Format for numerals
-
transliterate-text
- Converts text between different scripts
- Inputs:
input(string): Text to transliteratesource_language_code(string): Source language codetarget_language_code(string): Target language codenumerals_format(string, optional): Format for numeralsspoken_form(boolean, optional): Enable spoken formspoken_form_numerals_language(string, optional): Language for spoken numerals
Configuration
Getting an API Key
- Sign up for a Sarvam API account
- Generate your API key from the developer dashboard
Usage with Claude Desktop
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"sarvam": {
"command": "npx",
"args": [
"-y",
"sarvam-mcp-server"
],
"env": {
"SARVAM_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}
NPM Package
The package is available on npm as sarvam-mcp-server. Install it using:
npm install sarvam-mcp-server
Usage with Docker
The server is available as a Docker image at shbhtngpl/sarvam-mcp-server.
- Pull the image:
docker pull shbhtngpl/sarvam-mcp-server
- Run the container:
docker run -i --rm -e SARVAM_API_KEY=your_api_key_here shbhtngpl/sarvam-mcp-server
For Claude Desktop integration, use this configuration in your claude_desktop_config.json:
{
"mcpServers": {
"sarvam": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"SARVAM_API_KEY",
"shbhtngpl/sarvam-mcp-server"
],
"env": {
"SARVAM_API_KEY": "YOUR_API_KEY_HERE"
}
}
}
}
Development
Local Development
- Clone the repository:
git clone https://github.com/Shobhit-Nagpal/sarvam-mcp-server.git
cd sarvam-mcp-server
- Install dependencies:
npm install
- Run the server:
npm start
License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
README mirrored from the source repository 3 months ago. The original is authoritative.