PluginBench
MCP Server
Active
MIT

Agent Pattern MCP MCP Server

io.github.olk/agent-pattern-mcp

RepositoryRegistry
How to choose

What this kind of tool is for

  • Hand your agent a structured way to call a model or an inference API.
  • Compare outputs from two different providers on the same prompt.
  • Wire retrieval, embeddings, or generation into an existing agent workflow.

How to compare servers like this

Provider coverage:
Match the tool's supported providers and models to the ones your project uses.
Cost exposure:
Model-backed tools spend real API budget; check how usage and limits are configured.
Maintenance signal:
The provider landscape shifts weekly; prefer tools updated within the last few months.
Config surface:
Prefer tools whose environment-variable or config keys are documented plainly.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the Agent Pattern MCP MCP server?

MCP server that provides AI agent pattern expertise for designing agent systems

How to install Agent Pattern MCP

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • GENERATOR_API_KEY
    required
    secret

    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 <provider>/<model> 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
    secret

    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.

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "agent-pattern-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "docker.io/olkowa/agent-pattern-mcp:1.0.3",
        "--add-host",
        "host.docker.internal:host-gateway",
        "--transport",
        "stdio"
      ],
      "env": {
        "GENERATOR_API_KEY": "<YOUR_GENERATOR_API_KEY>",
        "GENERATOR_PROVIDER": "<YOUR_GENERATOR_PROVIDER>",
        "GENERATOR_MODEL": "<YOUR_GENERATOR_MODEL>",
        "GENERATOR_BASE_URL": "<YOUR_GENERATOR_BASE_URL>",
        "PATTERN_DIRECTORY": "<YOUR_PATTERN_DIRECTORY>",
        "EMBEDDER_PROVIDER": "<YOUR_EMBEDDER_PROVIDER>",
        "EMBEDDER_BASE_URL": "<YOUR_EMBEDDER_BASE_URL>",
        "EMBEDDER_API_KEY": "<YOUR_EMBEDDER_API_KEY>",
        "RERANKER_BASE_URL": "<YOUR_RERANKER_BASE_URL>"
      }
    }
  }
}

Related MCP servers

MCP server that provides architecture design expertise to AI coding agents

0
Python
MIT
View repository →

Multi-LLM council: 25+ frontier models in parallel, consensus scoring, verdict-first code review.

Persistent, local-first memory for AI coding agents. Works with Claude, GPT, Gemini, Cursor—no cloud, no vendor lock-in.

205
Python
Apache-2.0
View repository →
OMOMEGA Memory logo

Local-first persistent memory for AI agents. Works with Claude, GPT, Gemini, Cursor—no cloud, no vendor lock-in.

205
Python
Apache-2.0
View repository →

Turn any goal with a deadline into a private, gamified, evidence-based execution calendar.

0
View repository →

Search, scrape, and crawl the web for AI agents. Batch scraping and answers with citations.