CKB transforms your codebase into a queryable knowledge base, allowing users to ask questions, understand impact, find owners, and detect dead code through CLI, API, or AI assistants.
From the registry: Code intelligence MCP server — 80+ tools for navigation, impact analysis, and architecture
$ npx @tastehub/ckb initPlease install the `ckb` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Initialize CKB** — Initialize CKB in your project directory Run: `npx @tastehub/ckb init`
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["@tastehub/ckb","mcp"]
- optional environment variables:
- `CKB_REPO`: Absolute path to the repository (needed for clients without project context like Claude Desktop) (example: `<your-repo-path>`)
Note: Code Knowledge Backend — code intelligence MCP with 80+ tools. Run `ckb index` + `ckb setup` once per repo. Go-based with SCIP indexing.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Real-time Kubernetes network traffic visibility and API analysis for HTTP, gRPC, Redis, Kafka, DNS.