pulsemcp scanned Safe content atomic mcp-remote

AI Vision

AI Vision MCP provides AI assistants with powerful image and video analysis capabilities through Google's Gemini and Vertex AI models, supporting both Google AI Studio API keys and Vertex AI service accounts for flexible deployment options. Built by tan-yong-sheng with TypeScript, it offers three core tools: analyze_image for single image analysis, compare_images for multi-image comparison (up to 4 images), and analyze_video for video content analysis, with intelligent file handling that supports URLs, local file paths, and base64 data. The implementation features smart upload strategies that automatically choose between direct API calls for smaller files and cloud storage (Google Cloud Storage for Vertex AI, Files API for Gemini) for larger files, with comprehensive error handling, retry logic, and configurable processing limits, making it valuable for content moderation, visual data analysis, educational applications, and any workflow requiring AI-powered understanding of visual media.

Cognium trust score

61%

Tier

Scanned

Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-02.

Scan details: Circle-IR · 2026-09-02 · Appeal

View full trust & usage report →

Metadata

Version: 1.0.0
Skill type: atomic
Execution layer: mcp-remote
Category: devops-ci
Source: PulseMCP
Repository: github.com/tan-yong-sheng/ai-vision-mcp
Author type: human
Last scanned: 2026-09-02
Updated: 2026-09-02

View source Find related skills

MCP

Resolve AI Vision from your agent

Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.

One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.

claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp

Swap --scope user for --scope project to commit it to .mcp.json.

Your client Same endpoint everywhere; only the config key differs. The full list is in the descriptor.

Claude Desktop · Settings → Connectors → Add custom connector

https://api.skillsregistry.net/mcp

Paste the URL as the connector endpoint. No authentication.

ChatGPT · Settings → Connectors → Create (developer mode) → MCP server URL

https://api.skillsregistry.net/mcp

Authentication: none. Works in chat and deep research — the server exposes the connector search and fetch tools.

Codex CLI · ~/.codex/config.toml

[mcp_servers.skillsregistry]
url = "https://api.skillsregistry.net/mcp"