Orca is an MCP server that provides a two-layer architecture for reliable LLM code generation by separating program structure from computation and verifying the structure automatically before execution.
From the registry: Go from natural language to verified finite state machines — topology bugs caught before code runs.
This server lives in a monorepo. The README covers the whole collection, so we can't extract a single canonical install. Multi-package monorepo managed with pnpm/Turborepo. Packages: orca-lang (core), runtime-ts, runtime-python, runtime-go, demo-ts, demo-python, demo-go, demo-nanolab, mcp-server. The MCP server is in packages/mcp-server/ and published as @orcalang/orca-mcp-server.
Real-time Kubernetes network traffic visibility and API analysis for HTTP, gRPC, Redis, Kafka, DNS.