Praison AI

Server: Agents MCP

Deploy agents as MCP servers using Agent.launch(protocol='mcp')

Publish single or multi-agent systems over MCP with launch(protocol="mcp") — the built-in idiom that delegates to serve_agents(...) under the hood.

Diagram

agent.launch(protocol=’mcp’)

⚙️ serve_agents([agent])

PraisonAIAgents(…).launch(protocol=’mcp’)

serve_agents([…])

🔧 ask_{name} + list_agents

🌐 /mcp (http-stream)

Quick Start

  1. Install Dependencies
    bash
    pip install praisonai-mcp

    praisonai-mcp is an optional package imported lazily. Without it, launch(protocol="mcp") prints: “MCP serving requires the ‘praisonai-mcp’ package.”

  2. Set API Key
    bash
    export OPENAI_API_KEY="your-key"
  3. Create Agent MCP Server
    python
    from praisonaiagents import Agent

agent = Agent(
    name="TweetAgent",
    instructions="Create engaging tweets",
    llm="gpt-4o-mini"
)
agent.launch(port=8080, protocol="mcp")
  4. Verify
    bash
    curl http://localhost:8080/mcp

Which idiom fits your code?

Diagram

You already hold an Agent object

You already hold a PraisonAIAgents object

Imperative script, no object yet

How is your code shaped?

agent.launch(protocol=’mcp’)

agents.launch(protocol=’mcp’)

serve_agents([…])

✅ Same tools · same /mcp · same sessions

Single Agent as MCP

python
from praisonaiagents import Agent

agent = Agent(
    name="TweetAgent",
    instructions="Create engaging tweets",
    llm="gpt-4o-mini"
)
agent.launch(port=8080, protocol="mcp")
# Equivalent to: serve_agents([agent], port=8080)

Published tools: ask_tweetagent + list_agents. The output comes from praisonai-mcp and the endpoint is /mcp.

Multi-Agent as MCP

python
from praisonaiagents import Agent
from praisonaiagents.agents import PraisonAIAgents

researcher = Agent(name="Researcher", instructions="Research topics", llm="gpt-4o-mini")
writer = Agent(name="Writer", instructions="Write content", llm="gpt-4o-mini")

agents = PraisonAIAgents(agents=[researcher, writer])
agents.launch(port=8080, protocol="mcp")
# Equivalent to: serve_agents([researcher, writer], port=8080)

Each agent gets its own ask_{name} tool — here ask_researcher and ask_writer — plus one shared list_agents.

MCP Endpoints

EndpointMethodDescription
/mcpPOSTJSON-RPC over spec-compliant streamable HTTP

See Serve Agents for the canonical tool schema and session model.

launch() Parameters

ParameterTypeDefaultDescription
portint8000Server port
hoststr0.0.0.0Server host
protocolstrmcpMust be mcp
debugboolFalseDebug mode

Connect MCP Client

Claude Desktop (claude_desktop_config.json):

json
{
  "mcpServers": {
    "praisonai-agent": {
      "url": "http://localhost:8080/mcp",
      "transport": "http-stream"
    }
  }
}

Cursor (.cursor/mcp.json):

json
{
  "mcpServers": {
    "praisonai-agent": {
      "url": "http://localhost:8080/mcp",
      "transport": "http-stream"
    }
  }
}

Test MCP Tools

bash
# List tools
curl -X POST http://localhost:8080/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc": "2.0", "method": "tools/list", "id": 1}'

# Call tool
curl -X POST http://localhost:8080/mcp \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "method": "tools/call",
    "params": {"name": "ask_tweetagent", "arguments": {"message": "Create a tweet about AI"}},
    "id": 2
  }'

Docker Deployment

app.py:

python
from praisonaiagents import Agent

agent = Agent(instructions="Create tweets", llm="gpt-4o-mini")
agent.launch(port=8080, protocol="mcp")

Dockerfile:

dockerfile
FROM python:3.11-slim
WORKDIR /app
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt
COPY app.py .
EXPOSE 8080
CMD ["python", "app.py"]

requirements.txt:

praisonaiagents
praisonai-mcp

Build and run:

bash
docker build -t agent-mcp-server .
docker run -p 8080:8080 -e OPENAI_API_KEY=$OPENAI_API_KEY agent-mcp-server

Troubleshooting

IssueFix
Port in uselsof -i :8080
MCP serving requires the 'praisonai-mcp' package.pip install praisonai-mcp
No API keyexport OPENAI_API_KEY="your-key"
Client can’t connectCheck firewall, use host="0.0.0.0"

Related