Volta Notes

Created By
iamredmh2 months ago
Burn-after-read encrypted notes for AI agents. Share secrets with users without them appearing in chat history — create a one-time URL, send it, they read it once and it's gone. AES-256-GCM E2E encrypted, decryption key never sent to any server.
Overview

Volta Notes MCP Server

Give your AI agent a secure credential pipeline. Instead of pasting passwords or API keys into chat, create a burn-after-read note and send the link — the agent reads it once and it's permanently destroyed.

How it works

  1. User creates a Volta note with a secret (or the agent creates one to send back)
  2. A one-time URL is generated — the decryption key lives in the #fragment, never sent to any server
  3. The recipient opens the link once — after that, the note is gone forever

Tools

create_volta_note Encrypts content and stores it on the Volta canister. Returns a one-time URL. Use this when the agent needs to hand a secret back to the user.

read_volta_note Accepts a Volta URL, retrieves and permanently destroys the note, decrypts locally, returns the plaintext. Use this when a user sends the agent a voltanotes.com link.

Installation

Add to your Claude Desktop or Claude Code config:

{
  "mcpServers": {
    "volta-notes": {
      "command": "npx",
      "args": ["-y", "@voltanotes/mcp"]
    }
  }
}
Security model
AES-256-GCM encryption runs locally on your machine
Decryption key is in the URL fragment — never transmitted to the Volta canister or any server
The canister only ever stores and returns encrypted ciphertext
Once read, the note is permanently deleted — no copy exists anywhere

Server Config

{
  "mcpServers": {
    "volta-notes": {
      "command": "npx",
      "args": [
        "-y",
        "@voltanotes/mcp"
      ]
    }
  }
}
Project Info
Created At
2 months ago
Updated At
2 months ago
Author Name
iamredmh
Star
-
Language
-
License
-
Category

Recommend Servers

View All
//beforeyouship — LLM Cost Modeling From Your Editor
@Indiegoing

Query realistic LLM cost models without leaving your editor. beforeyouship models the **true monthly cost** of an LLM app architecture — retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth — across GPT-5.x, Claude, Gemini, DeepSeek, and more. Not a token calculator: a planning tool for the design phase, before you commit to a stack. **No API key needed to try it** — demo mode covers the six free-tier models. A Pro key from [beforeyouship.dev](https://beforeyouship.dev) unlocks the full 18-model catalog. ## What you can ask - "How much will a RAG chatbot cost at 10,000 requests/day?" - "Compare Claude Haiku vs Gemini Flash pricing for my workload" - "What's the cheapest model for a multi-step agent at scale?" - "Show me current per-token prices for Anthropic models" ## Tools ### `estimate_cost` Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case monthly cost per model, 3×/10× growth scenarios, and an opinionated recommendation with reasoning. ### `get_model_prices` Current per-1M-token pricing — input, output, cached input, batch — with context windows and staleness metadata. ### `list_archetypes` Seven preset architecture patterns (simple chatbot, chatbot with history, RAG pipeline, multi-model router, coding assistant, document processor, multi-step agent) used as starting points for estimates. ## Setup **Claude Code:** ​```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ​``` **Cursor / other clients** — add a remote server: ​```json { "mcpServers": { "beforeyouship": { "type": "streamable-http", "url": "https://beforeyouship.dev/api/mcp" } } } ​``` Add an `Authorization: Bearer bys_...` header with a Pro key for the full catalog. ## Try it > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day

5 hours ago
Mnemom

6 hours ago