MCP server that provides design-pattern selection expertise to AI coding agents
Design Pattern MCP is an MCP integration. MCP server that provides design-pattern selection expertise to AI coding agents.
The published oci package is docker.io/olkowa/design-pattern-mcp:1.0.1. Its declared MCP transport is stdio.
The package declares DESIGN_PATTERN_GENERATOR_API_KEY (required): API key for the generator LLM (LiteLLM provider).; DESIGN_PATTERN_GENERATOR_PROVIDER: LiteLLM provider prefix, e.g. openai, anthropic, openrouter.; DESIGN_PATTERN_GENERATOR_MODEL: Model name, combined as / via LiteLLM.; DESIGN_PATTERN_GENERATOR_BASE_URL: OpenAI-compatible base URL (LiteLLM api_base).; DESIGN_PATTERN_PATTERN_DIRECTORY: Directory with the catalog records (.json main records plus per-language files). The image bakes the 438-record catalogue at /app/pattern.; DESIGN_PATTERN_EMBEDDER_BASE_URL (required): Required: the dense retrieval leg embeds the 438-record catalogue during startup warmup and the server refuses to start when the endpoint is unreachable. TEI embeddings endpoint: on the Docker host use http://host.docker.internal:8080 (add --add-host=host.docker.internal:host-gateway on Linux); on a shared Docker network use http://design-pattern-tei-embed:8080.; DESIGN_PATTERN_EMBEDDER_API_KEY: API key for the embedder. Keyless TEI accepts any non-empty value; use 'not-needed' there.; DESIGN_PATTERN_RERANKER_BASE_URL (required): Required: retrieval runs a mandatory TEI cross-encoder rerank whenever the fused pool has more than one candidate. On the Docker host use http://host.docker.internal:8080; on a shared Docker network use http://design-pattern-tei-rerank:8080..
This package has launch arguments in its registry record. Use the maintainer’s configuration for those arguments rather than launching it with only the package name.
Check the maintainer’s instructions for account access, authentication and the supported client configuration. Once connected, inspect the tools your client receives and try a small task that matches the server’s stated purpose. The registry description does not include a verified, complete tool list.
View the publisher’s registry entry · Project repository. This profile uses version 1.0.1 from the registry. Registration identifies the publisher namespace; it does not establish that this is a first-party integration for every service it connects.
Browse related kubernetes & containers MCP servers for tools that cover the same kind of work.
| Variable | Description | Required |
|---|---|---|
| DESIGN_PATTERN_GENERATOR_API_KEY | API key for the generator LLM (LiteLLM provider). | Yes |
| DESIGN_PATTERN_GENERATOR_PROVIDER | LiteLLM provider prefix, e.g. openai, anthropic, openrouter. | Check documentation |
| DESIGN_PATTERN_GENERATOR_MODEL | Model name, combined as / via LiteLLM. | Check documentation |
| DESIGN_PATTERN_GENERATOR_BASE_URL | OpenAI-compatible base URL (LiteLLM api_base). | Check documentation |
| DESIGN_PATTERN_PATTERN_DIRECTORY | Directory with the catalog records (.json main records plus per-language files). The image bakes the 438-record catalogue at /app/pattern. | Check documentation |
| DESIGN_PATTERN_EMBEDDER_BASE_URL | Required: the dense retrieval leg embeds the 438-record catalogue during startup warmup and the server refuses to start when the endpoint is unreachable. TEI embeddings endpoint: on the Docker host use http://host.docker.internal:8080 (add --add-host=host.docker.internal:host-gateway on Linux); on a shared Docker network use http://design-pattern-tei-embed:8080. | Yes |
| DESIGN_PATTERN_EMBEDDER_API_KEY | API key for the embedder. Keyless TEI accepts any non-empty value; use 'not-needed' there. | Check documentation |
| DESIGN_PATTERN_RERANKER_BASE_URL | Required: retrieval runs a mandatory TEI cross-encoder rerank whenever the fused pool has more than one candidate. On the Docker host use http://host.docker.internal:8080; on a shared Docker network use http://design-pattern-tei-rerank:8080. | Yes |
kubectl with a conversational interface — inspect pods, read logs, diagnose clusters and manage workloads.
Container operations in conversation — inspect, run, debug and clean up Docker workloads.
Manage Docker containers and compose stacks through natural language with Claude AI.
Enables interaction with Kubernetes clusters through Model Control Protocol (MCP) tools.
Enables Claude Desktop to utilize Deepseek models running in Docker containers.
Provides natural language processing and API access to Kubernetes clusters, combining kubectl commands and the Kubernetes Python client.