Skip to main content
Glama
DuongNAD

Animal Map Vision MCP

by DuongNAD

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}
prompts
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
discover_map_artifactsA

Read-only inventory of map screenshots, manifests, and world-generation stage outputs inside the configured Animal Engine project root. Call this first.

inspect_map_viewsA

Returns PNG/JPEG/WebP viewport captures as actual MCP image content so Gemini can visually inspect seams, holes, floating assets, navigation, collision, lighting, spawn safety, and consistency. Paths must come from discover_map_artifacts.

validate_map_manifestA

Runs deterministic map quality gates: schema, bounds, unique ids, colliders, spawn-to-exit connectivity, navmesh coverage, 2:1 panorama, aligned depth/normals/cameras, and species-biome-climate-medium plausibility.

prepare_team_reviewA

Builds an evidence-first review brief with four parallel roles for Antigravity /teamwork-preview. It inventories artifacts and includes deterministic manifest issues when a manifest is available.

Prompts

Interactive templates invoked by user choice

NameDescription
animal-map-team-reviewReusable kickoff prompt for Antigravity teamwork-preview using Gemini 3.6 Flash.

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/DuongNAD/mcp-vision'

If you have feedback or need assistance with the MCP directory API, please join our Discord server