MCP server that provides AI agent pattern expertise for designing agent systems
Agent Pattern MCP is an MCP integration. MCP server that provides AI agent pattern expertise for designing agent systems.
The published oci package is docker.io/olkowa/agent-pattern-mcp:1.0.3. Its declared MCP transport is stdio.
The package declares GENERATOR_API_KEY (required): API key for the generator LLM (LiteLLM provider).; GENERATOR_PROVIDER: LiteLLM provider prefix, e.g. openai, anthropic, openrouter, minimax.; GENERATOR_MODEL: Model name, combined as / via LiteLLM.; GENERATOR_BASE_URL: OpenAI-compatible base URL (LiteLLM api_base).; PATTERN_DIRECTORY: Directory with -pattern.json files. The image bakes the 61-pattern catalog at /app/pattern.; EMBEDDER_PROVIDER: Embedding backend for pattern retrieval: tei, openai, ollama, vllm or hosted_vllm.; EMBEDDER_BASE_URL: Embedder endpoint. For TEI sidecars on the host use http://host.docker.internal:8080/v1 (add --add-host=host.docker.internal:host-gateway on Linux).; EMBEDDER_API_KEY: API key for the embedder. Required for startup even with keyless TEI; use 'not-needed' there.; RERANKER_BASE_URL: TEI cross-encoder reranker endpoint used during pattern retrieval..
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 1.0.3 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 other integrations MCP servers for tools that cover the same kind of work.
| Variable | Description | Required |
|---|---|---|
| GENERATOR_API_KEY | API key for the generator LLM (LiteLLM provider). | Yes |
| GENERATOR_PROVIDER | LiteLLM provider prefix, e.g. openai, anthropic, openrouter, minimax. | Optional |
| GENERATOR_MODEL | Model name, combined as / via LiteLLM. | Optional |
| GENERATOR_BASE_URL | OpenAI-compatible base URL (LiteLLM api_base). | Optional |
| PATTERN_DIRECTORY | Directory with -pattern.json files. The image bakes the 61-pattern catalog at /app/pattern. | Optional |
| EMBEDDER_PROVIDER | Embedding backend for pattern retrieval: tei, openai, ollama, vllm or hosted_vllm. | Optional |
| EMBEDDER_BASE_URL | Embedder endpoint. For TEI sidecars on the host use http://host.docker.internal:8080/v1 (add --add-host=host.docker.internal:host-gateway on Linux). | Optional |
| EMBEDDER_API_KEY | API key for the embedder. Required for startup even with keyless TEI; use 'not-needed' there. | Optional |
| RERANKER_BASE_URL | TEI cross-encoder reranker endpoint used during pattern retrieval. | Optional |
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.