code-memory is a deterministic, high-precision code intelligence layer that operates as a Model Context Protocol (MCP) server, enabling semantic searches against a locally indexed codebase.
From the registry: Local semantic code search with Git history. Works offline, no API key needed.

Please install the `code-memory` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Python 3.13+** — Required Python version.
- **uv (for uvx)** — Install uv package manager to run via uvx. (https://docs.astral.sh/uv/)
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["code-memory"]
- optional environment variables:
- `CODE_MEMORY_LOG_LEVEL`: Logging verbosity (DEBUG, INFO, WARNING, ERROR). (example: `INFO`)
- `EMBEDDING_MODEL`: HuggingFace model ID for embeddings. (example: `jinaai/jina-code-embeddings-0.5b`)
Note: First run downloads embedding model (~600MB). Fully local with no API key. Standalone binaries also available.
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.CODE_MEMORY_LOG_LEVELLogging verbosity (DEBUG, INFO, WARNING, ERROR)EMBEDDING_MODELHuggingFace model ID for embeddingsReal-time Kubernetes network traffic visibility and API analysis for HTTP, gRPC, Redis, Kafka, DNS.