New:Introducing Socket Scanning for VS Code Marketplace Extensions.Learn more →
Get Started

realtime-avatar-mcp

Package Overview
Dependencies
Maintainers
2
Versions
48
Alerts
File Explorer

Advanced tools

Socket logo

Install Socket

Detect and block malicious and high-risk dependencies

Install

realtime-avatar-mcp

MCP server for Realtime Avatar — let a coding agent read your avatars, balance and bill directly.

latest
Source
npmnpm
Version
0.27.5
Version published
Weekly downloads
233
-71.89%
Maintainers
2
Weekly downloads
 
Created
Source

realtime-avatar-mcp

Published on npm as realtime-avatar-mcp — run it with npx, never installed into an app.

An MCP server for Realtime Avatar. AGENTS.md tells a coding agent what the API is; this lets it look — at your avatars, your balance, your bill — instead of guessing ids and inventing shapes.

{
  "mcpServers": {
    "realtime-avatar": {
      "command": "npx",
      "args": ["-y", "realtime-avatar-mcp"],
      "env": { "REALTIME_AVATAR_API_KEY": "tic_test_…" }
    }
  }
}

Full page, including the write tools and what they cost: https://realtimeavatar.ai/docs/mcp. You need an API key first — a sandbox key is free and needs no card.

Working on it in this repo? npm run build, then point command at node with args: ["/abs/path/to/realtime-avatar-sdk/libs/mcp/dist/bin.js"].

Tools

Tool
list_avatarsEvery avatar with the id you pass to startCall, and which are usable live
get_avatarFull detail for one
credit_balanceBalance, and what in-flight calls have reserved
list_sessionsThe itemised bill — when each session ran, how long, what it cost
list_clipsAn avatar's clip library: every clip, its status, the revision and rest pose

With REALTIME_AVATAR_ALLOW_WRITES=1:

ToolBills?
set_loopRe-direct her resting loop from a new descriptionno
set_clip_libraryDeclare an avatar's full clip set as JSON — the platform renders itno
upload_assetUpload a file from this machine's disk, get a public URLno
create_remote_assetRegister a file already on the internet — no local copyno
create_avatar_from_imageBuild an avatar from ONE still — the loop is generatedno
create_avatar_from_videoDeprecated. Closed to new callers (422). Use the image toolno
start_callMint a live session to verify an integrationyes, per second

Spending money is opt-in, and twice gated

The five tools above are read-only, and each carries readOnlyHint so a host can gate on the annotation rather than on a name it has to recognise. Pointed at a production key, this server is no more dangerous than a dashboard you left open.

REALTIME_AVATAR_ALLOW_WRITES=1 enables the write tools. Only start_call costs credits, and it refuses a tic_live_ key outright — an operator who armed writes against a test key and later swapped in a production one should not discover it by being billed. Two independent gates, because one is a single mistake away from being none.

Two things to understand before arming writes:

  • upload_asset reads local disk. It opens whatever absolute path the agent names, on the machine running the server. Relative paths are refused rather than resolved against whatever directory the host spawned it in.
  • The clip declaration retires by omission. set_clip_library takes the COMPLETE set; anything missing from it stops being served. Its plan reports kept/queued/retired clips. Declare source.motionPrompt or source.assetId; the platform hosts and prepares media. The avatar's stored source is the implicit rest state — never declared, so the id primary is reserved.

Why an MCP server at all

An agent that reads docs still guesses. ava_… ids cannot be inferred, and the failures that cost the most time here are invisible in a type signature: a reshaped connection payload is rejected by the browser client; a 429 on a call is the queue, not an error; the resting loop is the avatar's source rather than a library clip, so no declaration changes it.

list_avatars marks which avatars are actually usable. The server's instructions carry the relay rule and the per-second billing model. That is context an agent cannot derive, delivered where it is about to act.

Keywords

ai

FAQs

Package last updated on 20 Oct 2026

Related posts