Server: Recipes MCP

Deploy recipes as MCP servers using praisonai mcp serve-recipe

Deploy any PraisonAI recipe as an MCP server for Claude Desktop, Cursor, and other MCP clients.

Quick Start

1. Install Dependencies

   pip install "praisonai[mcp]"
   
2. Set API Key

   export OPENAI_API_KEY="your-key"
   
3. List Available Recipes

   praisonai mcp list-recipes
   
4. Serve Recipe as MCP

   praisonai mcp serve-recipe support-reply --transport stdio
   

CLI - STDIO Transport

For Claude Desktop local integration:

praisonai mcp serve-recipe support-reply --transport stdio

Expected Output:

🚀 Starting Recipe MCP Server 'support-reply'
📡 Transport: stdio
🛠️ Available tools: support_reply.run, support_reply.agent.respond

CLI - HTTP Stream Transport

For remote access:

praisonai mcp serve-recipe support-reply --transport http-stream --port 8080

Expected Output:

🚀 Starting Recipe MCP Server 'support-reply'
📡 HTTP Stream endpoint: http://127.0.0.1:8080/mcp
🛠️ Available tools: support_reply.run, support_reply.agent.respond

Python SDK

from praisonai.mcp_server import RecipeMCPAdapter, RecipeMCPConfig

# Create adapter with config
config = RecipeMCPConfig(
    recipe_name="support-reply",
    expose_agent_tools=True,
    expose_run_tool=True,
    safe_mode=True
)

adapter = RecipeMCPAdapter("support-reply", config=config)
adapter.load()

# Get MCP server
server = adapter.to_mcp_server()
server.run(transport="stdio")

Recipe MCP Mapping

Recipe Component	MCP Primitive
Recipe metadata	Server metadata
Agent tools	MCP Tools (namespaced)
Agent instructions	MCP Prompts
Recipe config	MCP Resources
Recipe outputs	MCP Resources

RecipeMCPConfig Options

Field	Type	Default	Description
recipe_name	str	-	Recipe to serve
expose_agent_tools	bool	True	Expose agent tools
expose_run_tool	bool	True	Expose run tool
tool_namespace	str	prefixed	flat, nested, prefixed
expose_config	bool	True	Expose config as resource
expose_outputs	bool	True	Expose outputs as resource
expose_prompts	bool	True	Expose prompts
safe_mode	bool	True	Enable security restrictions
tool_allowlist	list	None	Allowed tool names
tool_denylist	list	None	Denied tool names

CLI Options

Option	Default	Description
--transport	stdio	stdio or http-stream
--host	127.0.0.1	HTTP host
--port	8080	HTTP port
--safe-mode	True	Enable security
--log-level	warning	Log level

Generate Client Config

# Generate Claude Desktop config
praisonai mcp config-generate-recipe support-reply --client claude-desktop

Output:

{
  "mcpServers": {
    "support-reply": {
      "command": "praisonai",
      "args": ["mcp", "serve-recipe", "support-reply", "--transport", "stdio"]
    }
  }
}

Connect MCP Client

Claude Desktop (claude_desktop_config.json):

For STDIO:

{
  "mcpServers": {
    "support-reply": {
      "command": "praisonai",
      "args": ["mcp", "serve-recipe", "support-reply", "--transport", "stdio"]
    }
  }
}

For HTTP Stream:

{
  "mcpServers": {
    "support-reply": {
      "url": "http://localhost:8080/mcp",
      "transport": "http-stream"
    }
  }
}

Validate Recipe

Check if a recipe is MCP-compatible:

praisonai mcp validate-recipe support-reply

Output:

✅ Recipe 'support-reply' is MCP-compatible

Tools: 3
  • support_reply.run
  • support_reply.agent.respond
  • support_reply.agent.analyze

Resources: 2
  • recipe://support-reply/config
  • recipe://support-reply/outputs

Prompts: 1
  • support_reply.instructions

Inspect Recipe Schema

praisonai mcp inspect-recipe support-reply

Security

Default denied tools (dangerous operations):

• shell.exec, shell.run
• file.write, file.delete
• db.write, db.delete
• execute_command, os.system

Override with --safe-mode=false (not recommended).

Troubleshooting

Issue	Fix
Recipe not found	praisonai mcp list-recipes
Missing deps	pip install "praisonai[mcp]"
Tool denied	Check tool_denylist
Port in use	Change --port

Related

• Tools MCP - Deploy tools as MCP server
• Agents MCP - Deploy agents as MCP server
• PraisonAI MCP - Full PraisonAI MCP server