Log inSubmit server
Emilia Protocol logo

Emilia Protocol

by emiliaprotocol

Requires named human approval for consequential agent actions and issues verifiable Ed25519 trust receipts.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Emilia Protocol

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "emiliaprotocol-emilia-protocol": {
      "command": "npx",
      "args": [
        "-y",
        "@emilia-protocol/mcp-server"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 3 tools correctly (1mo ago).

Overview

The emiliaprotocol/emilia-protocol MCP server adds named human approval gates to consequential agent actions such as payment releases, record changes, and deployments. After approval, it issues an offline-verifiable Ed25519 Trust Receipt describing the admitted action. It also exposes trust profiles, receipt verification, disputes, and delegation. Reach for it when an agent needs a human-controlled authority boundary and portable evidence of that decision.

Use cases

  • Require human approval before releasing a payment
  • Gate agent-driven record changes
  • Authorize deployments with named sign-off
  • Verify action receipts offline
  • Manage delegated authority and disputes

Key features

  • Named human approval gates
  • Ed25519 Trust Receipts
  • Offline receipt verification
  • Trust profiles
  • Disputes and delegation
  • Authority freeze support

Tools3

What Emilia Protocol lets your agent do. Expand a tool for its parameters.

Verified live~569 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

21/21 checks healthy over the last 79d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 9d ago via OSV.dev · @emilia-protocol/mcp-server (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars599Stargazers on the source repository.
npm downloads1.1kPackage downloads in the last 30 days.
Last commitTodayMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed3Callable tools this server registers over MCP.
Directory activity6 viewsConfig copies, upvotes, and views on AllMCPs.

How Emilia Protocol works

What emiliaprotocol/emilia-protocol MCP server does

The emiliaprotocol/emilia-protocol MCP server is intended for workflows where an AI agent may prepare or request a consequential action, but a named human must approve it before execution. Supported examples include releasing a payment, changing a record, or deploying code. The approval applies to the action presented for review rather than serving as general permission for unrelated work.

After the approval flow, the server can mint an Ed25519 Trust Receipt. The receipt is designed to be verifiable offline, giving another system a portable record of the authority decision and the action associated with it. The server also provides access to trust profiles, receipt verification, disputes, and delegation capabilities.

This places the project in the 🔒 Security category. It is relevant to developers building agent workflows that need explicit human authorization and evidence that an authorization decision occurred.

How it works

A protected workflow presents an exact action for review by a named human. When the required approval is provided, the action can proceed through the configured control path and a Trust Receipt is produced. Consumers can later verify that receipt without depending on a live central service.

The broader protocol describes a gate that checks authority for the exact action, reserves that authority before provider entry, and permits one admitted provider attempt for the covered authorization instance. If the result is unknown, the workflow requires reconciliation rather than an automatic retry. These controls depend on the action path being fully mediated and on authoritative shared state.

The repository also describes an emergency authority freeze. Within a covered control domain, a freeze blocks new reservations and prevents older reservations from entering after the control epoch changes. It does not stop the agent itself, reverse an effect that already entered a provider, or provide instant control over disconnected leased domains.

Setup and configuration

Install the MCP package with:

Terminal
npx -y @emilia-protocol/mcp-server

Configure the server according to the package and the authority boundaries in the workflow you intend to protect.

Tools and capabilities

The emiliaprotocol/emilia-protocol MCP server covers these documented capabilities:

  • Requesting named human sign-off before an irreversible action.
  • Creating offline-verifiable Ed25519 Trust Receipts.
  • Inspecting trust profiles.
  • Verifying receipts.
  • Handling disputes.
  • Supporting delegation.

The repository also includes a local authority map, an EMILIA Gate reference implementation, approval flows, and conformance material.

Limitations and notes

The protocol only constrains paths that pass through its enforcement point. An integration that leaves alternate execution paths available cannot claim the same preventive control over those paths. A receipt does not by itself prove source truth, payment authorization, settlement, customer demand, or successful deployment.

The repository states that the current reference implementation covers local in-memory and PostgreSQL control domains. Leased-edge freeze propagation and portable signed freeze-event evidence are identified as implementation gaps. The project is Apache-2.0 licensed, and its policy engine is described as formally verified; verification evidence should still be evaluated against the specific deployment and control path being used.

The emiliaprotocol/emilia-protocol MCP server is therefore best suited to workflows where the developer can define the protected boundary, retain durable authority state, and require reconciliation for uncertain provider outcomes.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Emilia Protocol

Run `npx -y @emilia-protocol/mcp-server`.

It supports named human approval for consequential actions such as payment releases, record changes, and deployments.

Yes. It issues Ed25519 Trust Receipts designed for offline verification and exposes receipt verification.

Related MCP servers

All in Security All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewEmilia Protocol AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/emiliaprotocol-emilia-protocol?style=directory)](https://allmcps.com/mcp/emiliaprotocol-emilia-protocol)
HTML Embed
<a href="https://allmcps.com/mcp/emiliaprotocol-emilia-protocol"><img src="https://allmcps.com/api/badge/emiliaprotocol-emilia-protocol?style=directory" alt="Emilia Protocol on AllMCPs" /></a>