AI & Machine Learning

creatinginai.com

Provides tools to create, lint, search, and inspect acting and voice direction for AI character/video models using behavior cues, FACS action units, and model-specific constraints.

1 endpoint8 known toolsFirst detected October 7, 2026Last detected October 7, 2026

ENDPOINT 1

https://creatinginai.com/agents/mcp

No auth detected

MCP server metadata

Name: performance-atlas
Version: 1.0

Capabilities

tools

Server instructions

Acting direction for AI video and voice, built from a character's state rather than an emotion label. For any shot with a person in it: (1) call atlas_kit with the character's state, the shot size and the target model; (2) write the acting paragraph as prose from the kit's behaviour - never name the emotion; (3) call atlas_lint on that paragraph with the same target and shot, and revise until ok is true; (4) generate. Emotions are an index, never output: what goes in the prompt is behaviour. atlas_draft returns a mechanical scaffold paragraph - rewrite it as prose. Use atlas_targets for target ids and prompt caps, atlas_search to look up behaviour.

Known tools 8

atlas_kit

The direction kit for a character state: beat-by-beat behaviour fitted to the shot size (where the tell can be seen), eye life, breath, the target model's rules and a voice delivery line.

Inferred read-only

atlas_draft

A first-draft acting paragraph assembled from the kit and fitted to the target's character cap, already linted.

Inferred read-only

atlas_lint

Check an acting paragraph or voice direction before spending credits: emotion labels, mugging, looks into the lens, quoted speech on hosts that block it, a tell bigger than the state allows, and the target's character cap.

Inferred read-only

atlas_search

Full-text search across behaviour cues, FACS action units, expressions, display strategies, emotions, situations, modifiers, model notes and targets.

Inferred read-only

atlas_show

One atlas record by id (or an emotion by name), with the records that use it.

Inferred read-only

atlas_targets

The target models the atlas knows, with each prompt field's character cap and what the model needs.

Inferred read-only

atlas_journey

A character's arc beat by beat, with continuity flags: reset (intensity drops with no event), breach (a hidden feeling shown to the person it's hidden from), overshoot (a tell bigger than the feeling) and flat (beats that never change).

Inferred read-only

atlas_buy_pack

Buy 20 paid calls for $1.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.performance-atlas]
url = "https://creatinginai.com/agents/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "performance-atlas": {
      "type": "http",
      "url": "https://creatinginai.com/agents/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: performance-atlas
Remote MCP URL: https://creatinginai.com/agents/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "performance-atlas": {
      "url": "https://creatinginai.com/agents/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "performance-atlas": {
      "type": "http",
      "url": "https://creatinginai.com/agents/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "performance-atlas",
  "transport": "streamable-http",
  "url": "https://creatinginai.com/agents/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for creatinginai.com was fetched 2026-10-13T04:50:30.835Z.

Trust status Trusted

creatinginai.com is assessed as Trusted: Domain has an established technology history spanning over a year.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.