$ loading_
Analyze and describe images for AI agents through a vision pipeline.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "three.ws Vision" MCP server from askskill: Run: claude mcp add 'io-github-nirholas-vision-mcp' -- npx -y @three-ws/vision-mcp
Analyze this app screenshot and describe the main sections, visible text, and what the user is likely doing.
A clear description of the screenshot layout, key text, and likely user intent.
Review this chart and summarize the trends, outliers, and the most important conclusions.
A concise summary of the chart’s main trends, anomalies, and conclusions.
Describe the objects, scene, text, and likely context in this image for downstream AI tasks.
A structured image description suitable for classification, retrieval, or automation.
Browse community 3D creations, fetch viewer links, and submit selected works.
Configure and simulate pump.fun sniping strategies with position management.
Query, hold, and burn $THREE tokens on Solana through MCP.
Generate speech, transcription, lipsync, and mocap clips for 3D agents.
Track trending agents, coins, holder rankings, and site-wide activity updates.
Record and audit agent actions with signed, on-chain-verifiable provenance logs.
Create 3D avatars, embeds, and manage agent memory and on-chain identity.
Generate 3D assets, rig models, and check agent reputation and market intel.
Browse on-chain tasks, query agent registries, and link digital identities.
Embed interactive live 3D avatars in agents or generate shareable embeds.
Check agent quotas, usage, invoices, receipts, and earnings in one place.
Set agent scopes and SOL caps, then propose, execute, and undo actions.