Genkit
This Genkit MCP plugin, developed by Firebase, provides seamless integration between Genkit and the Model Context Protocol (MCP). It enables Genkit developers to both consume MCP tools, prompts, and resources as a client and expose Genkit functionality as an MCP server. The client automatically discovers and registers available MCP actions with Genkit, while the server exposes Genkit tools and prompts via MCP. Built with TypeScript, it offers flexible configuration options for connecting to MCP servers, including local process spawning and remote connections. The implementation handles parsing and coercion of MCP responses for compatibility with Genkit's structured approach. It is particularly useful for developers looking to extend Genkit's capabilities with external MCP-compatible services or expose their Genkit-based AI assistants as MCP servers.
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
- ai-ml
- Source
- PulseMCP
- Author type
- human
- Updated
- 2026-05-27
Use via MCP
Resolve Genkit 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.