Vision Relay
An MCP server that provides a relay bridge to Google Gemini and Alibaba Qwen vision models through their respective CLI tools, enabling image analysis capabilities without direct API integration. Built by ah-wq using TypeScript and the MCP SDK, it accepts images from local files, URLs, or base64 data, handles automatic image preparation and validation, and executes CLI commands with configurable timeouts and parameters. The implementation features a modular provider architecture that isolates CLI-specific logic, comprehensive error handling with detailed command output, and support for various image formats with size limits and extension validation, making it useful for AI assistants that need vision capabilities through existing CLI toolchains rather than direct API access.
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 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- media
- Source
- PulseMCP
- Repository
- github.com/ah-wq/mcp-vision-relay
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Vision Relay 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--scope user for --scope project to commit it to .mcp.json.