How to Use the KeepTrack Space Intelligence MCP in Pydantic AI

Q: How do I configure KeepTrack Space Intelligence with Pydantic AI?

Instantiate MCPToolset with the HTTP URL of your server, then pass it to your Agent via the toolsets parameter. Your Pydantic AI agent will automatically discover the MCP Server tools.

Validate orbital telemetry and launch data at runtime with KeepTrack Space Intelligence and Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect KeepTrack Space Intelligence MCP to Pydantic AI

Create your Vinkius account to connect KeepTrack Space Intelligence 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 KeepTrack Space Intelligence with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate orbital details with `get_satellite_details`

The `get_satellite_details` tool fetches exact orbital parameters, including inclination, period, and catalog identifiers. When integrated with Pydantic AI, every single telemetry field is validated against strict Python type schemas at runtime. If the space catalog returns malformed data, your agent raises a loud validation error instead of silently passing bad coordinates. This strict check prevents downstream calculations from using corrupted orbital positions.

Search payloads safely using `search_satellites`

The `search_satellites` tool finds active payloads and debris clouds matching your search criteria. Your Pydantic AI agent processes these search results through type-safe models, ensuring that satellite names and catalog numbers match expected string formats. This type safety prevents your LLM client from hallucinating fields that do not exist in the live registry. You get clean, predictable JSON objects that fit perfectly into your existing orbital tracking databases.

Parse launch schedules with this MCP Server

The `get_recent_space_launches` tool retrieves the latest launch events, rocket configurations, and payload descriptions. Your Pydantic AI agent uses this tool to parse newly deployed hardware into structured Python classes for immediate analysis. You connect to this MCP Server using the unified `MCPToolset` constructor over HTTP. The setup is model-agnostic, meaning you can validate these space launch records whether you use local models or commercial APIs.

Setup guide

Set up KeepTrack Space Intelligence 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": {
        "keeptrack-space-intelligence-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent KeepTrack Space Intelligence 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 KeepTrack. 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 KeepTrack Space Intelligence 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 KeepTrack Space Intelligence MCP in Pydantic AI

Instantiate `MCPToolset` with the HTTP URL of your server, then pass it to your `Agent` via the `toolsets` parameter. Your Pydantic AI agent will automatically discover the MCP Server tools.

The framework immediately raises a validation error. Pydantic AI ensures that fields like inclination or catalog ID conform strictly to your defined schemas before your agent acts.

Yes, the setup is completely model-agnostic. You can run a local model to analyze the output of `get_recent_space_launches` while relying on Pydantic AI for strict type enforcement.

No, that transport is deprecated. You should use the unified `MCPToolset` over HTTP or SSE to connect your agent to the orbital tracking MCP Server.

All queries passing through the MCP Server are isolated in a secure V8 sandbox. Your satellite telemetry coordinates and launch manifests parameters are processed ephemerally and never written to persistent storage.

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