Almega

io.github.almega-aiPublished by GitHub account almega-aiv0.2.0Updated Oct 25, 2026

The immutable delegation frame for AI agents: gate any sensitive action, human-in-the-loop.

VerifiedSTDIODesktop onlySecurity & Monitoring

Overview

AI-generated overview

Almega is a local MCP server that gives AI agents an immutable delegation frame, gating sensitive actions behind human-in-the-loop approval.

What you can do
Provides a delegation frame for AI agents so sensitive actions can be gated before they run, with human-in-the-loop approval in the loop. Runs with a zero-config in-memory backend by default, or a Stripe backend that issues real Stripe Issuing test-mode virtual cards. The manifest lists no individual tools, so the exact operations are not documented here.
When to use it
Consider it when you want an agent's sensitive actions to pass through an explicit approval step rather than executing directly, or when you want to test agent-driven card issuance against Stripe test mode without real money.
Requirements
Runs locally as a Python package (almega-mcp) via uvx over stdio; desktop only. Optional environment variables: ALMEGA_BACKEND set to memory (default) or stripe, and STRIPE_SECRET_KEY, a Stripe test secret key required only when the backend is stripe.
Before you install
The stripe backend requires a Stripe secret key in STRIPE_SECRET_KEY; the server states it refuses live keys, but keep the key scoped to test mode. The stripe backend issues virtual cards in Stripe test mode, which the description says involves no real money. The manifest lists no tools, so review what actions the gate covers before relying on it.

Installation

In SourceWeft

  1. Open Almega in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.2.0LatestSep 16, 2026

Score

25% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.