Replicate
This Replicate MCP server, developed by Tzafrir Rehan, provides a standardized interface for AI assistants to interact with various AI models hosted on Replicate. Built using Python and FastMCP, it currently focuses on image generation capabilities, offering model schema inspection, customizable parameter inputs, and output resizing. The server abstracts the complexities of the Replicate API, handling authentication, model execution, and result processing. It's designed for AI developers and researchers who need flexible access to state-of-the-art AI models, enabling use cases like dynamic image creation, model exploration, and integration of advanced AI capabilities into broader applications. The implementation's roadmap includes expanding support for text and video generation models, as well as adding features like version management and caching.
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/tzafrir/mcp-server-replicate
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Replicate 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.