OpenRouter Vision
MCP OpenVision provides image analysis capabilities through OpenRouter's vision models, enabling AI assistants to analyze images via file paths, URLs, or base64-encoded data. Built with Python using the FastMCP framework, it offers a single configurable tool that accepts contextual queries and system prompts to guide analysis, supporting multiple OpenRouter vision models including Claude, GPT-4o, and Qwen variants. The implementation handles various image input formats, includes proper error handling for API failures, and is designed for developers who need reliable vision analysis integration in their MCP-compatible applications without managing direct API connections or image encoding complexities.
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/mikeysrecipes/mcp-openvision
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve OpenRouter 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--scope user for --scope project to commit it to .mcp.json.