Agent Pattern MCP server

<!-- mcp-name: io.github.olk/agent-pattern-mcp -->

agent-pattern-mcp

MCP server that provides AI agent pattern expertise: generate, analyze, and evaluate agent system designs against a curated catalog of 61 agent patterns (ReAct, supervisor-worker, reflexion, self-RAG, LLMCompiler, and more).

Table of Contents

• Quickstart
• Connect Your Agent
• Use the Tools
• Tools at a Glance
• Prompts
• Pattern Catalog
• SKILL for AI Agents
• Install Alternatives
• Configuration
• Extending with Custom Patterns
• Troubleshooting
• Building & Development

⚡ Quickstart

# 1. Clone
git clone https://github.com/olk/agent-pattern-mcp.git && cd agent-pattern-mcp

# 2. Add your API key (the dev compose pins GENERATOR_PROVIDER=minimax and
#    loads docker/.env — not the repo-root .env)
echo 'MINIMAXAI_API_KEY=sk-...' > docker/.env

# 3. Build the images once (TEI model weights are baked in at build time,
#    ~5 GB download on the first run), then start the stack
make docker-build-all
make docker-up

# 4. Demo
make client

🔌 Connect Your Agent

Claude Code

# Install (one-time)
npm install -g @anthropic-ai/claude-code

# Run as stdio subprocess — pass API key via env
GENERATOR_API_KEY=sk-... claude mcp add agent-pattern-mcp -- python -m src.main --transport stdio

OpenCode

# Terminal 1: start the server
make docker-up
# or locally:
uv run python -m src.main

# Terminal 2: add to ~/.config/opencode/opencode.json

{
  "mcp": {
    "agent-pattern-mcp": {
      "type": "remote",
      "url": "http://localhost:8061/mcp",
      "enabled": true
    }
  }
}

Codex CLI

# Install (one-time)
brew install codex

# Add to ~/.codex/config.toml

[mcp_servers.agent-pattern-mcp]
url = "http://localhost:8061/mcp"

Use the Tools

Design your first agent system

Ask your agent (or call the tool directly):

Use designagentsystem to design a research assistant that combines web search with sandboxed code execution for multi-hop questions. Domain: tool-use-tasks.

The tool runs the full pipeline — analyze (pattern retrieval + requirements-weighted scoring) → generate (LLM structured output) → evaluate (metric scoring) → refine (bounded retry loop) — and returns a complete AgentSystemDesign with agents, relationships, tool contracts, and quality scores.

Explore the pattern catalog

List all agent patterns in the tool_use category.

Get the full JSON of the react pattern.

Async job pattern: submitagentdesignjob + getagentdesignstatus

ONLY for clients with short request timeouts (Cursor, Claude Desktop, TS-SDK). The default is designagentsystem with heartbeat defence. submitagentdesignjob returns a jobid immediately; poll getagentdesign_status until done:

submit_agent_design_job(requirements, domain, override_topology)  → job_id
get_agent_design_status(job_id)                                  → {status, result, error}
cancel_agent_design(job_id)                                    → {cancelled, status}

Shortened. The full README is on GitHub.