Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.xquik.com/llms.txt

Use this file to discover all available pages before exploring further.

Build a Pydantic AI agent that can search tweets, hand off IDs and cursors, post tweets, and run extraction jobs - 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 pathlib import Path
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():
    prompt = (
        "Search for the latest tweets about AI agents. Return compact JSON "
        "with query, route_used, tweets[{tweet_id,text,author_username,created_at}], "
        "has_more, next_cursor, and key influencers."
    )
    result = await agent.run(prompt)
    Path("xquik-pydantic-ai-handoff.json").write_text(
        result.output,
        encoding="utf-8",
    )


asyncio.run(main())
The agent auto-discovers all Xquik tools and can call any of the 120 API endpoints. Pydantic AI registers MCPServerStreamableHTTP as an agent toolsets entry. The MCP runtime returns normalized snake_case fields through xquik.request(), so keep prompts aligned with tweet_id, has_more, next_cursor, and returned job IDs.

​
Handoff Checklist

Tweet search rows

Store tweet_id, text, author_username, created_at, has_more, next_cursor, and the original q.

User profile rows

Store source id as user_id, plus username, name, followers, verified, profile_picture, has_more, next_cursor, and the source lookup or search query.

Trend rows

Store each trend name, rank, query, and description. Keep response count, woeid, and the requested region with the run checkpoint.

Monitor and webhook setup

Store the returned monitor id as monitor_id, event_types, next_billing_at, the returned webhook id as webhook_id, url, and the one-time secret in a secret manager. On production deliveries, store delivery_id for receiver retry de-dupe and stream_event_id when one monitor event should process once across endpoint changes.

Extraction jobs

Store extraction_id, status, poll, and export_after_complete; poll before loading CSV, JSON, or XLSX rows.

Writes

Store tweet_id or write_action_id, reply_to_tweet_id, status, charged_credits, and poll; do not resend pending writes.

​
Reusing Connections

Wrap multiple calls in async with agent to keep the MCP connection open across requests: 
from pathlib import Path

async def main():
    async with agent:
        profile = await agent.run("Look up @xquikcom's public profile")
        tweets = await agent.run(
            "Get @xquikcom's latest 5 tweets. Return compact JSON with "
            "tweet_id, author_username, text, created_at, has_more, next_cursor, "
            "and route_used."
        )

    Path("xquik-pydantic-ai-profile.json").write_text(
        profile.output,
        encoding="utf-8",
    )
    Path("xquik-pydantic-ai-tweets.json").write_text(
        tweets.output,
        encoding="utf-8",
    )

​
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
{
  "mcpServers": {
    "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+
Last modified on May 18, 2026