Sahayak Ai

v1.0.0

A powerful MCP server built with NitroStack

Connection Setup

Add via Cursor Settings UI (Settings > Features > MCP > Add New MCP Server):

{
  "mcpServers": {
    // your other mcp servers
    "sahayak-ai": {
      "url": "https://sahayak-ai-6a5b18e9-nova-amrita-university-amritapuri-campus-1.app.nitrocloud.ai/mcp"
    }
  }
}

Connect remote tools directly via Claude's Web UI:

Add custom connector BETA
Connect Claude to your data and tools. Learn more about connectors or get started with pre-built ones.
Advanced settings
Only use connectors from developers you trust. Anthropic does not control which tools developers make available and cannot verify that they will work as intended or that they won't change.

Configure custom tools directly via ChatGPT's Web UI:

New App
PNG only. Best results at 256 x 256 px or larger. Max file size: 10 KB
Custom MCP servers introduce risk. Learn more
OpenAI hasn't reviewed this MCP server. Attackers may attempt to steal your data or trick the model into taking unintended actions, including destroying data.

Add the following configuration block under mcpServers in your Antigravity configuration file (~/.gemini/config/mcp_config.json):

{
  "mcpServers": {
    // your other mcp servers
    "sahayak-ai": {
      "serverUrl": "https://sahayak-ai-6a5b18e9-nova-amrita-university-amritapuri-campus-1.app.nitrocloud.ai/mcp"
    }
  }
}

Add the following configuration block to your Codex configuration file (~/.codex/config.toml):

[mcp_servers.sahayak-ai]
url = "https://sahayak-ai-6a5b18e9-nova-amrita-university-amritapuri-campus-1.app.nitrocloud.ai/mcp"

Connect directly using the Server-Sent Events endpoint:

https://sahayak-ai-6a5b18e9-nova-amrita-university-amritapuri-campus-1.app.nitrocloud.ai/mcp
Available Tools
calculate

Perform basic arithmetic calculations

convert_temperature

Convert temperature units based on file content or direct input. Supports Celsius (C) and Fahrenheit (F).

transcribe_and_fill_form

FIRST STEP: Transcribe audio file containing banking details (name, amount, account number, account type, transaction type) and extract structured form fields. This is the initial data capture step. Merges with any pre-filled values from read_receipt. Always call this first when a user provides their banking details.

read_receipt

Extract key fields from a bank receipt, passbook, or slip image using vision. Generates plain-language spoken summary. Use this when user provides a passbook/receipt image to pre-fill form fields.

read_back_form

Generate a clear, simple spoken-style confirmation script from form data. Output is ready for text-to-speech.

correct_form_field

Transcribe a spoken correction and update a single form field. Returns updated form for re-confirmation.

generate_bank_form

Map confirmed form data onto a bank form template and generate a print-ready PDF. Leaves signature area blank.

end_session

Clear all session data (form, transcript, receipt data). No data is persisted. Session resets for next user.