Skip to main content

​
What is Model Context Protocol (MCP)?

The Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources and tools. It provides a standardized way for AI agents to communicate with external servers and access their capabilities.

​
How MCP Works

MCP creates a bridge between your AI agents and external tool servers:
  1. Server Registration: You configure an MCP server by specifying its connection details
  2. Tool Discovery: The framework automatically discovers available tools from the server
  3. Tool Execution: When your agent needs a tool, the framework handles communication with the MCP server
  4. Result Handling: Results are returned to your agent in a standardized format

​
Key Benefits

  • Extensive Ecosystem: Access thousands of community-developed and official tools
  • No Custom Development: Use pre-built tools without writing integration code
  • Standardized Protocol: Consistent interface across different tool providers
  • Live Updates: Servers can update tools without changing your code

​
Three Ways to Use MCP

​
1. Class-Based

from upsonic import Agent, Task

class DatabaseMCP:
    command = "uvx"
    args = ["mcp-server-sqlite", "--db-path", "/tmp/test_mcp_v7.db"]

agent = Agent(
    name="Legacy MCP Agent",
    role="Database operations specialist using legacy MCP class",
    goal="Demonstrate backward compatibility with class-based MCP",
    tool_call_limit=10
)

task = Task(
    description="""
    Create a 'products' table with columns: 
    - id (integer primary key)
    - name (text)
    - price (real)
    - category (text)
    - stock (integer)
    
    Insert 5 sample products with different categories (electronics, books, clothing).
    Then query and show all products sorted by price.
    """,
    tools=[DatabaseMCP]
)

result = agent.do(task)
print(result)

​
2. MCPHandler Class

from upsonic import Agent, Task
from upsonic.tools.mcp import MCPHandler

mcp_handler = MCPHandler(
    command="uvx mcp-server-sqlite --db-path /tmp/db.db",
    timeout_seconds=60
)

agent = Agent(model="openai/gpt-4o")
task = Task(
    description="Query the database to list all tables and their schema information to understand the database structure.",
    tools=[mcp_handler]
)
result = agent.do(task)
print(result)

​
3. MultiMCPHandler Class (Multiple Servers)

from upsonic import Agent, Task
from upsonic.tools.mcp import MultiMCPHandler

multi_handler = MultiMCPHandler(
    commands=[
        "uvx mcp-server-sqlite --db-path /tmp/db1.db",
        "uvx mcp-server-sqlite --db-path /tmp/db2.db",
    ],
    tool_name_prefixes=["users_db", "products_db"],  # Prevent tool name collisions
    timeout_seconds=60
)

agent = Agent(model="openai/gpt-4o")
task = Task(
    description="""
    Connect to both databases using prefixed tools:
    - Use 'users_db_*' tools to query the users database
    - Use 'products_db_*' tools to query the products database
    Cross-reference the data between both databases.
    """,
    tools=[multi_handler]
)
result = agent.do(task)
print(result)
Use tool_name_prefix or tool_name_prefixes when connecting to multiple servers that expose tools with the same names. This prevents collisions and makes it clear which server’s tools to use.

​
MCP Server Resources

Discover available MCP servers: