How to Use the Clipboard History Searcher MCP in Pydantic AI

Q: How do I register Clipboard History Searcher in Pydantic AI?

Install the framework with the MCP extra, then instantiate MCPToolset with your Vinkius server URL. Pass this toolset directly into the toolsets argument of your Agent.

Q: How do I handle deprecated HTTP classes when setting up this server?

Do not use the deprecated MCPServerHTTP class. Use the unified MCPToolset constructor instead, which supports both Streamable HTTP and SSE transports out of the box.

Run type-safe searches on your clipboard history using Pydantic AI to guarantee structured data extraction.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Clipboard History Searcher MCP to Pydantic AI

Create your Vinkius account to connect Clipboard History Searcher to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Clipboard History Searcher with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict schema validation for this MCP Server

The `search_clipboard_history` tool ensures your agent can query local clipboard dumps while validating the returned JSON or TXT matches against strict Python models. Pydantic AI ensures that every tool response matches your exact Python models. If the clipboard parser returns unexpected data formats, the framework raises a validation error immediately. This prevents your agent from hallucinating properties or crashing halfway through a complex code generation loop.

Unified integration for clean codebases

The `search_clipboard_history` tool integrates using the unified toolset class to connect to your MCP Server over HTTP or SSE. You avoid deprecated HTTP client classes and get a clean, future-proof integration. Simply pass the toolset instance to your agent constructor. The agent automatically learns how to call the search tool and formats the query parameters according to the server schema.

Model-agnostic clipboard analysis

The `search_clipboard_history` tool operates independently of the underlying LLM provider when managed by this framework. You can use this clipboard search tool with OpenAI, Anthropic, Gemini, or even a local Ollama instance running on your machine. The framework handles the translation of the tool schema for each provider. Your agent can search your CopyQ or Ditto history files regardless of which model is driving the reasoning.

Setup guide

Set up Clipboard History Searcher MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "clipboard-history-searcher-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Clipboard History Searcher tools.",
)

result = await agent.run("List recent Clipboard History Searcher transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by clipboard-native. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Clipboard History Searcher now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Clipboard History Searcher MCP in Pydantic AI

Install the framework with the MCP extra, then instantiate `MCPToolset` with your Vinkius server URL. Pass this toolset directly into the `toolsets` argument of your `Agent`.

Yes. The search tool output is validated against strict schemas at runtime. If the clipboard data contains malformed JSON, the framework catches it before it reaches your agent.

Yes. The framework is model-agnostic, meaning you can connect this MCP tool to local models via Ollama or llama.cpp just as easily as you would connect it to cloud APIs.

Do not use the deprecated `MCPServerHTTP` class. Use the unified `MCPToolset` constructor instead, which supports both Streamable HTTP and SSE transports out of the box.

Your exported clipboard files are parsed inside a secure, zero-trust V8 sandbox on Vinkius. The raw text and JSON logs are processed in memory and never written to disk, ensuring your sensitive copied data remains completely private.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript