Skip to main content
Build a Pydantic AI agent that can search tweets, look up users, post tweets, and run extractions — connected to Xquik’s MCP server with 3 lines of config.

​
Prerequisites

  • Python 3.10+
  • Xquik API key (xq_...)
  • An LLM API key (Anthropic, OpenAI, or any Pydantic AI-supported provider)

​
Install

pip install "pydantic-ai[mcp]"

​
Full Example

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

server = MCPServerStreamableHTTP(
    "https://xquik.com/mcp",
    headers={"x-api-key": "xq_YOUR_KEY_HERE"},
)

agent = Agent(
    "anthropic:claude-sonnet-4-20250514",
    toolsets=[server],
    system_prompt="You help users interact with X (Twitter) via the Xquik API.",
)


async def main():
    result = await agent.run("Search for tweets about AI agents")
    print(result.output)


asyncio.run(main())
The agent auto-discovers all Xquik tools and can call any of the 122 API endpoints.

​
Reusing Connections

Wrap multiple calls in async with agent to keep the MCP connection open across requests: 
async def main():
    async with agent:
        result1 = await agent.run("Look up @elonmusk's profile")
        result2 = await agent.run("Get their latest 5 tweets")
    print(result1.output)
    print(result2.output)

​
Deferred Tool Loading

For large tool sets, use DeferredLoadingToolset to hide tools from the model until they’re discovered via tool search. This reduces prompt token usage: 
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

server = MCPServerStreamableHTTP(
    "https://xquik.com/mcp",
    headers={"x-api-key": "xq_YOUR_KEY_HERE"},
)

agent = Agent(
    "anthropic:claude-sonnet-4-20250514",
    toolsets=[server.defer_loading()],
)

​
Loading from JSON Config

If you manage MCP servers via a config file:
mcp_config.json
{
  "xquik": {
    "transport": "streamable-http",
    "url": "https://xquik.com/mcp",
    "headers": {
      "x-api-key": "xq_YOUR_KEY_HERE"
    }
  }
}

from pydantic_ai import Agent
from pydantic_ai.mcp import load_mcp_servers

servers = load_mcp_servers("mcp_config.json")
agent = Agent("anthropic:claude-sonnet-4-20250514", toolsets=servers)

​
Tool Prefixes

Avoid naming conflicts when connecting multiple MCP servers: 
from pydantic_ai.mcp import MCPServerStreamableHTTP

xquik = MCPServerStreamableHTTP(
    "https://xquik.com/mcp",
    headers={"x-api-key": "xq_YOUR_KEY_HERE"},
    tool_prefix="xquik",
)
# Tools become: xquik_explore, xquik_xquik, etc.

​
Environment Variables

.env
XQUIK_API_KEY=xq_YOUR_KEY_HERE
ANTHROPIC_API_KEY=sk-ant-...

import os
from pydantic_ai.mcp import MCPServerStreamableHTTP

server = MCPServerStreamableHTTP(
    "https://xquik.com/mcp",
    headers={"x-api-key": os.environ["XQUIK_API_KEY"]},
)

​
Package Versions

PackageVersion
pydantic-ai1.78.0+
mcp1.25.0+