Skip to content
CrewAI Documentation

MCP DSL Integration

Overview

Section titled “Overview”

CrewAI’s MCP DSL (Domain Specific Language) integration provides the simplest way to connect your agents to MCP (Model Context Protocol) servers. Just add an mcps field to your agent and CrewAI handles all the complexity automatically.

Basic Usage

Section titled “Basic Usage”

Add MCP servers to your agent using the mcps field:

from crewai import Agent


agent = Agent(
    role="Research Assistant",
    goal="Help with research and analysis tasks",
    backstory="Expert assistant with access to advanced research tools",
    mcps=[
        "https://mcp.exa.ai/mcp?api_key=your_key&profile=research"
    ]
)


# MCP tools are now automatically available!
# No need for manual connection management or tool configuration

Supported Reference Formats

Section titled “Supported Reference Formats”

External MCP Remote Servers

Section titled “External MCP Remote Servers”
# Basic HTTPS server
"https://api.example.com/mcp"


# Server with authentication
"https://mcp.exa.ai/mcp?api_key=your_key&profile=your_profile"


# Server with custom path
"https://services.company.com/api/v1/mcp"

Specific Tool Selection

Section titled “Specific Tool Selection”

Use the # syntax to select specific tools from a server:

# Get only the forecast tool from weather server
"https://weather.api.com/mcp#get_forecast"


# Get only the search tool from Exa
"https://mcp.exa.ai/mcp?api_key=your_key#web_search_exa"

Connected MCP Integrations

Section titled “Connected MCP Integrations”

Connect MCP servers from the CrewAI catalog or bring your own. Once connected in your account, reference them by slug:

# Connected MCP with all tools
"snowflake"


# Specific tool from a connected MCP
"stripe#list_invoices"


# Multiple connected MCPs
mcps=[
    "snowflake",
    "stripe",
    "github"
]

Complete Example

Section titled “Complete Example”

Here’s a complete example using multiple MCP servers:

from crewai import Agent, Task, Crew, Process


# Create agent with multiple MCP sources
multi_source_agent = Agent(
    role="Multi-Source Research Analyst",
    goal="Conduct comprehensive research using multiple data sources",
    backstory="""Expert researcher with access to web search, weather data,
    financial information, and academic research tools""",
    mcps=[
        # External MCP servers
        "https://mcp.exa.ai/mcp?api_key=your_exa_key&profile=research",
        "https://weather.api.com/mcp#get_current_conditions",


        # Connected MCPs from catalog
        "snowflake",
        "stripe#list_invoices",
        "github#search_repositories"
    ]
)


# Create comprehensive research task
research_task = Task(
    description="""Research the impact of AI agents on business productivity.
    Include current weather impacts on remote work, financial market trends,
    and recent academic publications on AI agent frameworks.""",
    expected_output="""Comprehensive report covering:
    1. AI agent business impact analysis
    2. Weather considerations for remote work
    3. Financial market trends related to AI
    4. Academic research citations and insights
    5. Competitive landscape analysis""",
    agent=multi_source_agent
)


# Create and execute crew
research_crew = Crew(
    agents=[multi_source_agent],
    tasks=[research_task],
    process=Process.sequential,
    verbose=True
)


result = research_crew.kickoff()
print(f"Research completed with {len(multi_source_agent.mcps)} MCP data sources")

Tool Naming and Organization

Section titled “Tool Naming and Organization”

CrewAI automatically handles tool naming to prevent conflicts:

# Original MCP server has tools: "search", "analyze"
# CrewAI creates tools: "mcp_exa_ai_search", "mcp_exa_ai_analyze"


agent = Agent(
    role="Tool Organization Demo",
    goal="Show how tool naming works",
    backstory="Demonstrates automatic tool organization",
    mcps=[
        "https://mcp.exa.ai/mcp?api_key=key",      # Tools: mcp_exa_ai_*
        "https://weather.service.com/mcp",         # Tools: weather_service_com_*
        "snowflake"                                # Tools: snowflake_*
    ]
)


# Each server's tools get unique prefixes based on the server name
# This prevents naming conflicts between different MCP servers

Error Handling and Resilience

Section titled “Error Handling and Resilience”

The MCP DSL is designed to be robust and user-friendly:

Graceful Server Failures

Section titled “Graceful Server Failures”
agent = Agent(
    role="Resilient Researcher",
    goal="Research despite server issues",
    backstory="Experienced researcher who adapts to available tools",
    mcps=[
        "https://primary-server.com/mcp",         # Primary data source
        "https://backup-server.com/mcp",          # Backup if primary fails
        "https://unreachable-server.com/mcp",     # Will be skipped with warning
        "snowflake"                               # Connected MCP from catalog
    ]
)


# Agent will:
# 1. Successfully connect to working servers
# 2. Log warnings for failing servers
# 3. Continue with available tools
# 4. Not crash or hang on server failures

Timeout Protection

Section titled “Timeout Protection”

All MCP operations have built-in timeouts:

  • Connection timeout: 10 seconds
  • Tool execution timeout: 30 seconds
  • Discovery timeout: 15 seconds
# These servers will timeout gracefully if unresponsive
mcps=[
    "https://slow-server.com/mcp",        # Will timeout after 10s if unresponsive
    "https://overloaded-api.com/mcp"      # Will timeout if discovery takes > 15s
]

Performance Features

Section titled “Performance Features”

Automatic Caching

Section titled “Automatic Caching”

Tool schemas are cached for 5 minutes to improve performance:

# First agent creation - discovers tools from server
agent1 = Agent(role="First", goal="Test", backstory="Test",
               mcps=["https://api.example.com/mcp"])


# Second agent creation (within 5 minutes) - uses cached tool schemas
agent2 = Agent(role="Second", goal="Test", backstory="Test",
               mcps=["https://api.example.com/mcp"])  # Much faster!

On-Demand Connections

Section titled “On-Demand Connections”

Tool connections are established only when tools are actually used:

# Agent creation is fast - no MCP connections made yet
agent = Agent(
    role="On-Demand Agent",
    goal="Use tools efficiently",
    backstory="Efficient agent that connects only when needed",
    mcps=["https://api.example.com/mcp"]
)


# MCP connection is made only when a tool is actually executed
# This minimizes connection overhead and improves startup performance

Integration with Existing Features

Section titled “Integration with Existing Features”

MCP tools work seamlessly with other CrewAI features:

from crewai.tools import BaseTool


class CustomTool(BaseTool):
    name: str = "custom_analysis"
    description: str = "Custom analysis tool"


    def _run(self, **kwargs):
        return "Custom analysis result"


agent = Agent(
    role="Full-Featured Agent",
    goal="Use all available tool types",
    backstory="Agent with comprehensive tool access",


    # All tool types work together
    tools=[CustomTool()],                          # Custom tools
    apps=["gmail", "slack"],                       # Platform integrations
    mcps=[                                         # MCP servers
        "https://mcp.exa.ai/mcp?api_key=key",
        "snowflake"
    ],


    verbose=True,
    max_iter=15
)

Best Practices

Section titled “Best Practices”

1. Use Specific Tools When Possible

Section titled “1. Use Specific Tools When Possible”
# Good - only get the tools you need
mcps=["https://weather.api.com/mcp#get_forecast"]


# Less efficient - gets all tools from server
mcps=["https://weather.api.com/mcp"]

2. Handle Authentication Securely

Section titled “2. Handle Authentication Securely”
import os


# Store API keys in environment variables
exa_key = os.getenv("EXA_API_KEY")
exa_profile = os.getenv("EXA_PROFILE")


agent = Agent(
    role="Secure Agent",
    goal="Use MCP tools securely",
    backstory="Security-conscious agent",
    mcps=[f"https://mcp.exa.ai/mcp?api_key={exa_key}&profile={exa_profile}"]
)

3. Plan for Server Failures

Section titled “3. Plan for Server Failures”
# Always include backup options
mcps=[
    "https://primary-api.com/mcp",       # Primary choice
    "https://backup-api.com/mcp",        # Backup option
    "snowflake"                          # Connected MCP fallback
]

4. Use Descriptive Agent Roles

Section titled “4. Use Descriptive Agent Roles”
agent = Agent(
    role="Weather-Enhanced Market Analyst",
    goal="Analyze markets considering weather impacts",
    backstory="Financial analyst with access to weather data for agricultural market insights",
    mcps=[
        "https://weather.service.com/mcp#get_forecast",
        "stripe#list_invoices"
    ]
)

Troubleshooting

Section titled “Troubleshooting”

Common Issues

Section titled “Common Issues”

No tools discovered:

# Check your MCP server URL and authentication
# Verify the server is running and accessible
mcps=["https://mcp.example.com/mcp?api_key=valid_key"]

Connection timeouts:

# Server may be slow or overloaded
# CrewAI will log warnings and continue with other servers
# Check server status or try backup servers

Authentication failures:

# Verify API keys and credentials
# Check server documentation for required parameters
# Ensure query parameters are properly URL encoded

Advanced: MCPServerAdapter

Section titled “Advanced: MCPServerAdapter”

For complex scenarios requiring manual connection management, use the MCPServerAdapter class from crewai-tools. Using a Python context manager (with statement) is the recommended approach as it automatically handles starting and stopping the connection to the MCP server.