PayVoice Collections MCP Server
Stores collection data in a Supabase database (public.collections table).
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@PayVoice Collections MCP ServerSave a collection: promise to pay 5000 on 2026-08-20."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
PayVoice Collections MCP Server
This project provides a small HTTP service that exposes a save_collection tool and stores collection data in the Supabase public.collections table.
1. Local setup
python -m venv .venv
# Windows:
.venv\Scripts\activate
# macOS/Linux:
# source .venv/bin/activate
pip install -r requirements.txtSet environment variables:
SUPABASE_URL=https://YOUR_PROJECT.supabase.co
SUPABASE_KEY=YOUR_SUPABASE_PUBLISHABLE_KEYRun:
uvicorn server:app --reload --port 8000Health check:
http://localhost:8000/healthRelated MCP server: expense-tracker
2. Deploy
You can deploy the included render.yaml to Render or deploy the same FastAPI app to another HTTPS host.
Set these environment variables on the host:
SUPABASE_URLSUPABASE_KEY
Your deployed URL will look like:
https://YOUR-SERVICE.onrender.comThe endpoint included for the simple JSON MCP-style test is:
https://YOUR-SERVICE.onrender.com/mcp3. Important Inya note
Before entering /mcp into Inya, verify which MCP transport/protocol version your Inya workspace requires. A generic HTTP JSON endpoint is not automatically equivalent to an official MCP Streamable HTTP/SSE endpoint.
If Inya rejects this URL as an invalid MCP server, the server needs to be adapted to the exact MCP transport supported by your Inya workspace.
Tool
save_collection
Arguments:
disposition: stringpayment_commitment_date: string or nullpayment_commitment_amount: integer or nullcallback_required: booleancallback_date: string or nullescalation_reason: string or nulllanguage: string
Example tool arguments:
{
"disposition": "PROMISE_TO_PAY",
"payment_commitment_date": "2026-08-20",
"payment_commitment_amount": 5000,
"callback_required": false,
"callback_date": null,
"escalation_reason": null,
"language": "Tamil"
}Security
Do not commit .env files or publish secret keys. For production, use a server-side secret with the minimum required database permissions.
This server cannot be deployed
Maintenance
Related MCP Connectors
Save and organize web finds in persistent, user-controlled collections for AI assistants.
AI Agent Utility Layer for agent safety, web monitoring, crypto research and tool discovery.
Pay-per-call tools for agents via x402 (USDC on Base): Korean data, doc-to-Markdown, web utilities.
Pay-per-use agent tools: schedule HTTP calls, extract pages, PDFs, OG images, QR codes, short links.
Related MCP Servers
- AlicenseBqualityDmaintenancePayment & Transaction Tools that allow AI agents to send, receive, and request payments1122 npm2Apache 2.0
- FlicenseNot gradedqualityDmaintenanceManages personal expenses through natural language with tools for adding, updating, searching, and summarizing expenses, backed by Supabase.-
- FlicenseNot gradedqualityCmaintenanceEnables AI agents to safely interact with Supabase through read-only and gated-write tools, with bounded queries, allowlists, and explicit project targeting.-
- FlicenseNot gradedqualityAmaintenanceEnables AI coding agents to integrate stablecoin crypto checkout into applications by registering workspaces, configuring settlement wallets and webhooks, creating payment links and invoices, and verifying payment status and webhook signatures. It exposes these payment operations as tools over stdio so agents can complete end-to-end payment setup without manual dashboard work.-