MCP.so
Sign In
A

Almega MCP Server

@almega-ai

Basic information

Category

Other

Transports

stdio

Author

almega-ai

Submitted by

almega-ai

About Almega MCP Server

Give your AI agents a wallet they can't abuse. Almega is an MCP server that puts a control layer in front of every payment: per-agent spending limits, allow-listed categories, 1-click human approval on sensitive transactions, and a full audit ledger. Two backends ship in one file

Almega MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "almega": {
      "command": "python",
      "args": [
        "/absolute/path/to/almega_mcp.py"
      ],
      "env": {
        "ALMEGA_BACKEND": "memory"
      }
    }
  }
}

Almega MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Almega?

Almega is a wallet and guardrail for AI agents, exposed as a Model Context Protocol (MCP) server. It lets any MCP-compatible client (Claude Desktop, Claude Agent SDK, etc.) give agents hard spending limits, a human approval step, and a full ledger. It ships with two backends: memory (in-process, zero setup) and stripe (real Stripe Issuing test-mode cardholders and virtual cards).

How to use Almega?

Install via pip install almega-mcp or run with uvx almega-mcp. For the Stripe backend, set environment variables ALMEGA_BACKEND=stripe and STRIPE_SECRET_KEY=sk_test_.... Configure Claude Desktop’s MCP server JSON to point to almega_mcp.py with those variables. Then agents can call tools like open_wallet, pay, approve_pending, reject_pending, get_wallet, list_transactions, and reset. Two resources (almega://wallets, almega://ledger) are also available.

Key features of Almega

  • Wallet with monthly limit, allow/block rules, and approval threshold.
  • Pay tool returns APPROVED, BLOCKED, or AWAITING_YOU.
  • Human can approve or reject pending transactions.
  • Full ledger with filtering by agent and status.
  • Memory backend needs no accounts or env vars.
  • Stripe backend creates real test-mode cards visible in Stripe dashboard.

Use cases of Almega

  • Give an AI agent a budget and watch it attempt payments in real time.
  • Demo human-in-the-loop approval for sensitive purchases.
  • Experiment with Stripe Issuing test-mode without touching live cards.
  • Script a multi‑step scenario to exercise spend rules and approvals.

Frequently asked questions

1

What backends does Almega support?

Two: `memory` (in‑process, everything lost on restart) and `stripe` (real Stripe Issuing test‑mode cardholders and cards, no real money).

2

Does Almega persist wallet data between restarts?

No. Wallets live in memory. With the Stripe backend, cardholders and cards remain in Stripe, but the agent‑to‑card link is forgotten on restart.

3

Can I use Almega with live money?

No. The Stripe backend only accepts test‑mode secret keys (`sk_test_...`). Almega refuses to start with a live key.

4

What are the dependencies and runtime requirements?

Python 3.10+ is recommended. Install `mcp[cli]`, `stripe`, and `requests`. No external accounts needed for the memory backend.

5

Is there any authentication or access control?

No. Anyone with an MCP connection to Almega can call any tool or access all resources.

Comments

More Other MCP servers