KIMI AI
MCP server implementation that provides AI assistants with access to KIMI AI services through OpenAI-compatible API endpoints, featuring both text generation and vision capabilities using Qwen models (Qwen2.5-72B-Instruct for text and Qwen2.5-VL-72B-Instruct for vision tasks). The implementation includes a FastAPI-based server architecture with MCP protocol support, custom detection services, and a web-based client interface for testing interactions. Built with configurable API endpoints and model selection, it serves users who want to integrate KIMI's AI capabilities into their workflows through standardized MCP tooling, supporting use cases like multilingual text generation, image analysis, and custom AI service integration with existing MCP-compatible applications.
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
- media
- Source
- PulseMCP
- Repository
- github.com/adamleen/mcp-kimi
- Author type
- human
- Last scanned
- 2026-09-02
- Updated
- 2026-09-02
Use via MCP
Resolve KIMI AI 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.