Replicate
This Replicate MCP server implementation provides a bridge between the Model Context Protocol and Replicate's AI model hosting platform. Developed as an open-source project, it enables seamless interaction with Replicate's diverse collection of machine learning models through a standardized MCP interface. The server supports key operations such as listing available models, creating and managing predictions, and accessing model metadata. Built with TypeScript and leveraging the official Replicate API, it offers robust error handling, caching mechanisms, and webhook support. This implementation is particularly useful for developers and researchers looking to integrate Replicate's hosted AI models into their MCP-compatible applications, enabling easy access to a wide range of pre-trained models for tasks like image generation, text processing, and more.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- media
- Source
- PulseMCP
- Repository
- github.com/deepfates/mcp-replicate
- Author type
- human
- Updated
- 2026-05-21
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.