Civitai
MCP server implementation by Cicatriiz that provides AI assistants with complete access to the Civitai API for browsing and discovering AI models, generated images, and creator profiles. Built with TypeScript using robust Zod schema validation and comprehensive error handling, the implementation offers 14 specialized tools including advanced model search with filtering by type, creator, tags, and base models, popularity and rating-based browsing, generated image galleries with metadata and generation parameters, creator portfolio exploration, and direct download URL access with authentication support. The server handles all major model types (Checkpoint, LORA, ControlNet, TextualInversion, etc.) with NSFW content filtering, commercial use permissions, and content safety information including pickle and virus scan results, making it valuable for AI researchers exploring model ecosystems, developers integrating Civitai's model repository into applications, and content creators discovering trending models and generation techniques.
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/cicatriiz/civitai-mcp-server
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Civitai 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.