How to Use the AddSearch MCP in Pydantic AI

Q: How do I add AddSearch to Pydantic AI?

Initialize MCPToolset with your HTTP endpoint URL. You then pass this unified toolset into your Agent constructor using the toolsets array. Remember that MCPServerHTTP is deprecated.

Q: Can Pydantic AI agents delete AddSearch documents?

They can execute the deletedocument tool if you provide the required Secret Key. The framework validates the document ID format before the request ever leaves your server.

Q: Does this AddSearch MCP Server support pagination?

Your agent pulls specific pages using the searchpagination tool. This keeps the JSON payloads small and ensures the runtime validation happens quickly on manageable chunks of data.

Q: How does Pydantic AI handle AddSearch autocomplete?

The autosuggest tool returns an array of string predictions. Your framework validates this array instantly, ensuring your agent only works with actual text suggestions instead of hallucinated objects.

Bring strict runtime validation to your AddSearch operations. Pydantic AI agents fail loudly if search data or analytics deviate from your schemas.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AddSearch MCP to Pydantic AI

Create your Vinkius account to connect AddSearch 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 AddSearch with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Indexing for Pydantic AI

The `index_document` tool forces your agent to structure new content perfectly before pushing it to the search database. If the payload misses a required field, the framework throws a validation error immediately. Listing current records works the same way. When your agent calls `list_documents`, the returned dataset must match your strict Pydantic models, preventing silent corruption in downstream processing.

Validated Search MCP Server Queries

Precision matters when pulling data into your application. The `search_filtered` tool executes complex queries against custom fields, and Pydantic AI guarantees the results match the expected types. Sorting requires exact parameters. Your agent uses `search_sorted` to order the output, knowing that any hallucinated sorting keys will trigger an immediate crash rather than returning garbage data.

Analytics with Strict Schemas

Raw metric extraction happens via the `stats_queries` tool. Your agent pulls search volume data and validates every integer and string before passing the numbers to your reporting dashboard. Click tracking gets the same rigorous treatment. The `stats_clicks` tool retrieves engagement stats, ensuring your model-agnostic setup receives clean, verified metrics regardless of which LLM you use.

Setup guide

Set up AddSearch 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": {
        "addsearch-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent AddSearch 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 AddSearch. 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 AddSearch 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 AddSearch MCP in Pydantic AI

Initialize `MCPToolset` with your HTTP endpoint URL. You then pass this unified toolset into your Agent constructor using the `toolsets` array. Remember that `MCPServerHTTP` is deprecated.

They can execute the `delete_document` tool if you provide the required Secret Key. The framework validates the document ID format before the request ever leaves your server.

Your agent pulls specific pages using the `search_pagination` tool. This keeps the JSON payloads small and ensures the runtime validation happens quickly on manageable chunks of data.

The `autosuggest` tool returns an array of string predictions. Your framework validates this array instantly, ensuring your agent only works with actual text suggestions instead of hallucinated objects.

Your search queries and click-through analytics pass through an isolated V8 sandbox. Authentication is handled entirely by the endpoint token, meaning your credentials never leak into the LLM context.

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