Taranis MCP Server for Pydantic AI 12 tools — connect in under 2 minutes
Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Taranis through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
agent = Agent(
model="openai:gpt-4o",
mcp_servers=[server],
system_prompt=(
"You are an assistant with access to Taranis "
"(12 tools)."
),
)
result = await agent.run(
"What tools are available in Taranis?"
)
print(result.data)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About Taranis MCP Server
Connect your Taranis AI Scouting API to any AI agent and take full control of AI-powered crop threat detection, ultra-high-resolution imagery analysis, field scouting recommendations, and precision agriculture decision-making through natural conversation.
Pydantic AI validates every Taranis tool response against typed schemas, catching data inconsistencies at build time. Connect 12 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
What you can do
- Organizations — List all agricultural organizations and farms in your Taranis account
- Field Management — View all monitored fields with crop types, boundaries, and growth stages
- Flight History — Review all drone and aircraft flight missions with imagery acquisition dates
- Flight Imagery — Access ultra-high-resolution orthomosaics, DSMs, and NDVI maps from each flight
- All Detections — Get comprehensive AI-detected threats (weeds, diseases, pests, nutrients) in any field
- Threat Summary — View consolidated threat severity assessments and trend analysis per field
- Scouting Recommendations — Receive AI-powered action plans for targeted field scouting missions
- Multispectral Analysis — Access NDVI, NDRE, and GNDVI vegetation indices for vigor assessment
- Weed Detection — Identify specific weed species with coverage estimates and herbicide recommendations
- Disease Detection — Detect crop diseases with severity levels and fungicide treatment suggestions
- Nutrient Analysis — Identify nutrient deficiencies with variable rate fertilization recommendations
The Taranis MCP Server exposes 12 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect Taranis to Pydantic AI via MCP
Follow these steps to integrate the Taranis MCP Server with Pydantic AI.
Install Pydantic AI
Run pip install pydantic-ai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the agent
Save to agent.py and run: python agent.py
Explore tools
The agent discovers 12 tools from Taranis with type-safe schemas
Why Use Pydantic AI with the Taranis MCP Server
Pydantic AI provides unique advantages when paired with Taranis through the Model Context Protocol.
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Taranis integration code
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
Dependency injection system cleanly separates your Taranis connection logic from agent behavior for testable, maintainable code
Taranis + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the Taranis MCP Server delivers measurable value.
Type-safe data pipelines: query Taranis with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple Taranis tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query Taranis and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock Taranis responses and write comprehensive agent tests
Taranis MCP Tools for Pydantic AI (12)
These 12 tools become available when you connect Taranis to Pydantic AI via MCP:
get_detections
Returns detection locations (GPS coordinates), threat types (weeds, diseases, pests, nutrient deficiencies), severity levels, confidence scores, affected area estimates, and recommended actions. Detections are classified by AI models trained on millions of field images for sub-millimeter accuracy. Essential for early threat identification, targeted scouting, and precision treatment planning. AI agents should use this when users ask "show me all detections in my field", "what threats were detected in field X", or need comprehensive threat analysis before planning field operations. Optional threatType filters detections by specific threat category. Get all AI-detected crop threats (weeds, diseases, pests, nutrient deficiencies) in a field
get_disease_detections
Returns disease locations, pathogen identification where possible, severity levels (early, moderate, advanced), affected plant parts, and recommended fungicide treatments. Essential for early disease intervention, fungicide planning, and yield loss prevention. AI agents should reference this when users ask "what diseases are in my soybean field", "show disease progression over time", or need disease-specific analysis for crop protection decisions. Get crop disease detections and severity assessments for a field
get_field_details
Essential for understanding field context before analyzing detections, planning scouting missions, or generating management recommendations. AI agents should reference this when users ask "tell me about this field", "what crop is planted in field X", or need detailed field metadata for context-aware analysis. Get detailed information about a specific agricultural field
get_fields
Returns field names, IDs, boundaries (GeoJSON polygons), area in hectares/acres, crop type, planting dates, and monitoring status. Essential for farm management overview, field inventory, and selecting target fields for threat detection and scouting analysis. AI agents should use this when users ask "show me all fields in my organization", "list monitored fields", or need to identify available fields for detection or flight queries. Optional orgId filters fields by specific organization. List all agricultural fields monitored by Taranis for an organization
get_flight_imagery
Returns orthomosaic mosaics, digital surface models (DSM), digital terrain models (DTM), normalized difference vegetation index (NDVI) maps, and true-color RGB composites. Essential for visual crop assessment, change detection between flights, and downloading high-resolution imagery for GIS analysis. AI agents should reference this when users ask "show me the latest imagery from this flight", "get the NDVI map for flight X", or need specific imagery products for field analysis. Get ultra-high-resolution imagery products from a specific flight mission
get_flights
Returns flight dates, times, aircraft type, imagery resolution, weather conditions during flight, coverage percentage, and processing status. Essential for understanding imagery acquisition history, assessing data quality, and selecting specific flights for detailed analysis. AI agents should use this when users ask "show me all flights over my corn field", "what imagery was captured last week", or need flight metadata before accessing specific imagery products. List all drone or aircraft flights that captured imagery for a specific field
get_multispectral_imagery
Supports indices including NDVI (Normalized Difference Vegetation Index), NDRE (Normalized Difference Red Edge), GNDVI (Green NDVI), and custom band combinations. Returns imagery layers, statistical summaries (mean, min, max, std), and zone classifications. Essential for crop vigor assessment, variable rate application planning, and growth stage monitoring. AI agents should reference this when users ask "show me NDVI map for my field", "get multispectral analysis", or need vegetation index data for precision agriculture planning. Get multispectral imagery and vegetation indices (NDVI, NDRE, GNDVI) for a field
get_nutrient_detections
Returns deficiency locations, severity estimates, affected growth stages, and variable rate fertilization recommendations. Essential for precision nutrient management, yield optimization, and cost-efficient fertilization planning. AI agents should use this when users ask "does my field have nutrient deficiencies", "where do I need to apply nitrogen", or need nutrient-specific analysis for variable rate application planning. Get nutrient deficiency detections and fertilization recommendations for a field
get_organizations
Returns organization names, IDs, contact information, and field counts. Essential for multi-account management, selecting target organizations for field analysis, and understanding the scope of monitored agricultural operations. AI agents should use this when users ask "show me all my organizations", "list farms I have access to", or need to identify available organizations before querying fields or detections. List all organizations available to the user in Taranis platform
get_scouting_recommendations
Returns specific action items including ground truth verification locations, recommended scouting patterns, treatment suggestions, timing recommendations, and priority levels. Essential for field team coordination, targeted scouting missions, and data-driven treatment decisions. AI agents should use this when users ask "what should I scout for in my field this week", "give me scouting recommendations", or need AI-generated action plans based on latest imagery analysis. Get AI-powered scouting recommendations and action plans for a field
get_threats
Returns threat categories, overall severity ratings (low, medium, high, critical), affected area percentages, trend analysis (increasing, stable, decreasing), and priority rankings. Essential for quick field health assessment, prioritizing scouting missions, and making informed treatment decisions. AI agents should reference this when users ask "what is the overall threat level in my field", "summarize field health status", or need a high-level threat overview before diving into individual detections. Get consolidated threat summary and severity assessment for a field
get_weed_detections
Returns weed locations, estimated coverage area, species classification, growth stage, and herbicide resistance indicators. Essential for targeted spot spraying, herbicide selection, and resistance management. AI agents should use this when users ask "where are the weeds in my field", "what weed species were detected", or need weed-specific analysis for precision herbicide application. Get specific weed species detections and infestation maps for a field
Example Prompts for Taranis in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with Taranis immediately.
"Show me all AI-detected threats in my corn field from the latest flight."
"Generate scouting recommendations for my soybean field this week."
"What is the overall threat level and NDVI trend for my wheat field this season?"
Troubleshooting Taranis MCP Server with Pydantic AI
Common issues when connecting Taranis to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiTaranis + Pydantic AI FAQ
Common questions about integrating Taranis MCP Server with Pydantic AI.
How does Pydantic AI discover MCP tools?
MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.Does Pydantic AI validate MCP tool responses?
Can I switch LLM providers without changing MCP code?
Connect Taranis with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect Taranis to Pydantic AI
Get your token, paste the configuration, and start using 12 tools in under 2 minutes. No API key management needed.