Emilia Protocol runs on your own machine — the client starts it, so there is no endpoint to ping. 91 installs a week from npm. Last commit 28 Oct 2026.
Exact-action approval for consequential agent actions: request, track, and verify signed receipts.
We read the source, 4 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
…n)(cxt,p)}.test(${key})`))}return(0,codegen_1.not)(definedProp)}function deleteAdditional(key){gen.code((0,codegen_1._)`delete ${data}[${key}]`)}function additionalPropertyCode(key){if(opts.removeAdditional==="all"||opts.removeAdditional&&schema===false){deleteAdditional(key);ret…
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
'eyJzdWIiOiJhZ2VudC0xIiwiYWRnIjoiWWxIcDNNNEpJV0ZQUFpJVkF3QW1ZT0JPTWZVeWIyYmpFNnZlM0FEMmlhUSIsImRzcCI6InVTRWdPRzlVQzFJV0d4ekJhbEp2NWNJYmZ4RThreG1vS0YyNXlyUmwxZnMiLCJycWYiOiIxR0w3Q0lnMUprS0dhR2ZIZ2RGNV85M3JWeDRGcWZqb1kwbFlaNnhialEwIiwiaW50IjoiY2xlYW4iLCJqdGkiOiIwMTIzNDU2Nzg5YWJ…
const result = spawnSync(process.execPath, [resolveVerifierCli(), ...args], {
return candidate && existsSync(path.join(root, candidate)) ? candidate : null;
return subprocess.run(arguments, text=True, capture_output=True, check=False)
- '.npmrc'
"timestamp_proof": "MIICvAYJKoZIhvcNAQcCoIICrTCCAqkCAQMxDzANBglghkgBZQMEAgEFADBrBgsqhkiG9w0BCRABBKBcBFowWAIBAQYEKgMEATAxMA0GCWCGSAFlAwQCAQUABCC7wqpceRiyTyn/5zcyaxnH7NYfVwhd10sgUt5BFCw6aAIBAhgPMjAyNjA3MDYxNzQ0NDRaMAMCAQEBAf8xggIkMIICIAIBATBSMDoxGzAZBgNVBAMMEkVQIENvbmZvcm1hbm…
…</dd>`:h+=`<dt>${u[e]}:</dt><dd>${a[e]}</dd>`:"Errata"==u[e]&&(h+=`<dt>More info:</dt><dd>${a[e]}</dd>`)}),h+="</dl>",e.innerHTML=h}catch(e){console.log(e)}else console.log("Could not locate metadata <div> element");function r(e){return e.charAt(0).toUpperCase()+e.slice(1)}}windo…
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp-server -- npx -y @emilia-protocol/mcp-server
{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@emilia-protocol/mcp-server"
]
}
}
}
[mcp_servers.mcp-server]
command = "npx"
args = ["-y", "@emilia-protocol/mcp-server"]
{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@emilia-protocol/mcp-server"
]
}
}
}
{
"servers": {
"mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@emilia-protocol/mcp-server"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
EP_API_KEY (API key for live action-guard, signoff, and write operations. Public receipt lookup may work without it), EP_INCLUDE_PROTOCOL_TOOLS (Set to true to advertise handshake, commit, and delegation tools in addition to the default three-tool action front door), EP_INCLUDE_REGISTRY_TOOLS (Set to true to advertise the complete 36-tool legacy registry and reputation catalog).
Independent effect verification and signed receipts for consequential AI agent actions.
Portable signed records for agent, API, MCP, and cross-runtime interactions.
Issue & verify signed (ed25519), hash-chained, timestamped provenance receipts for agent actions.
Verify agent actions against the system of record and get signed completion receipts.
Signed, hash-chained provenance receipts for AI agent actions.
Pre-execution policy gate for consequential agent actions with durable trust receipts.
Human-in-the-loop approval for agent actions, with verifiable action-bound receipts.
Spending control for AI agents: approved budgets, a decision before each payment, signed receipts.
Answers built from our own checks of this server.