How do I export a route to my GPS device?

First, use list_routes to find your route ID. Then use export_route_gpx or export_route_tcx with that route ID. The GPX file can be downloaded and loaded onto Garmin, Wahoo, or other GPS devices for turn-by-turn navigation during your workout.

Can I log activities that Strava doesn't automatically track?

Yes! Use create_activity to manually log any workout — gym sessions, yoga, swimming, hiking, cross-training. Provide the name, type (e.g., "Workout", "Yoga", "Swim"), start date, elapsed time, and optionally distance and description. This keeps all your training in one place.

How do I track my bike and shoe mileage?

Use get_gear with the gear ID to see total accumulated distance. Gear IDs are found in your athlete profile or assigned to activities. You can assign gear to activities using update_activity with the gear_id parameter. Track mileage to know when to replace chains, tires, or running shoes.

Strava Planning MCP Server for Pydantic AI 14 tools — connect in under 2 minutes

Name: Strava Planning
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 14 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Strava Planning through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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 Strava Planning "
            "(14 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Strava Planning?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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 Strava Planning MCP Server

Connect Strava Planning to any AI agent and manage your training logistics — route creation, GPX/TCX export, manual activity logging, gear tracking, segment favoriting, and profile management.

Pydantic AI validates every Strava Planning tool response against typed schemas, catching data inconsistencies at build time. Connect 14 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

Route Management — List, view, and analyze all your saved routes with distance, elevation, and descriptions
Route Streams — Get GPS coordinates, elevation profiles, and distance data for any route
Route Export — Export routes to GPX and TCX formats for GPS devices (Garmin, Wahoo, etc.)
Manual Activity Creation — Log activities not recorded by Strava (gym, yoga, cross-training) with full details
Activity Updates — Edit activity names, descriptions, assign gear, mark commutes or indoor sessions
File Uploads — Upload FIT, TCX, or GPX files for processing by Strava with status tracking
Segment Management — Star (favorite) or unstar segments for quick training access
Athlete Profile — View and update your profile information including weight for accurate power-to-weight ratios
Athlete Zones — Review your heart rate and power zone configurations
Gear Details — Track equipment mileage, models, and primary gear assignments

The Strava Planning MCP Server exposes 14 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 Strava Planning to Pydantic AI via MCP

Follow these steps to integrate the Strava Planning 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 14 tools from Strava Planning with type-safe schemas

Why Use Pydantic AI with the Strava Planning MCP Server

Pydantic AI provides unique advantages when paired with Strava Planning 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 Strava Planning integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Strava Planning connection logic from agent behavior for testable, maintainable code

Strava Planning + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Strava Planning MCP Server delivers measurable value.

Type-safe data pipelines: query Strava Planning with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Strava Planning tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Strava Planning and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Strava Planning responses and write comprehensive agent tests

Strava Planning MCP Tools for Pydantic AI (14)

These 14 tools become available when you connect Strava Planning to Pydantic AI via MCP:

create_activity

Required: name (activity name), type (activity type like "Run", "Ride", "Swim", "Walk", "Hike"), startDate (ISO 8601 format), elapsedTime (seconds). Optional: description, distance (meters). Use this to log activities recorded outside of Strava (gym workouts, yoga, cross-training, etc.). Activity types must match Strava's valid types list. Create a manual activity in Strava

export_route_gpx

GPX files can be downloaded and loaded onto GPS devices (Garmin, Wahoo, etc.) for navigation. The routeId is from Strava route URLs. Use this to export routes to your GPS device for guided training. Get the GPX export URL for a Strava route

export_route_tcx

TCX files include route data with additional training metadata. Compatible with Garmin Training Center and other fitness platforms. Use this to export routes with training metadata. Get the TCX export URL for a Strava route

get_athlete

Use this to review personal profile details, check equipment assignments, or verify account settings. Get the authenticated athlete's profile information

get_athlete_zones

Required for zone-based training analysis. Use this to review training zones, ensure zones are correctly set, or use zone data for activity analysis. Get the athlete's custom heart rate and power zones

get_gear

The gearId is found in activity data or athlete profile. Use this to check equipment mileage for maintenance planning or to analyze performance with specific gear. Get details about a piece of equipment (bike, shoes) tracked in Strava

get_route

The routeId is found in Strava route URLs. Use this to review route characteristics before training or to plan similar routes. Get detailed information about a specific Strava route

get_route_streams

The "types" parameter is comma-separated: "latlng", "altitude", "distance". Use this to preview a route's elevation profile, understand the terrain, or export GPS data for navigation. Get elevation and GPS data streams for a Strava route

get_upload_status

Status values: "Your activity is ready" (success), "Your activity is still processing" (wait and retry), or error messages. The uploadId is returned by upload_activity. Poll this endpoint every 5-10 seconds after upload until ready. Check the status of a Strava activity upload

list_routes

Each route includes: name, distance, elevation gain, type (ride/run), description, and whether it's private. Use this to review saved routes, plan upcoming workouts, or export route data for GPS devices. List all routes created by the authenticated athlete

star_segment

Set starred=true to favorite, starred=false to unfavorite. The segmentId is from Strava segment URLs. Use this to manage your favorite segments for quick access and training focus. Star (favorite) or unstar a Strava segment

update_activity

The activityId is the numeric ID. Updatable fields: name, description, sport_type, gear_id (to assign equipment), commute (mark as commute: "true"/"false"), trainer (mark as indoor: "true"/"false"). Use this to correct activity details, assign gear, or add descriptions after the fact. Update an existing Strava activity

update_athlete

Currently only "weight" (in kg) is supported by the API. Accurate weight is important for power-to-weight ratio calculations and performance analysis. Use this when your weight changes to keep performance metrics accurate. Update the authenticated athlete's profile information

upload_activity

Supported data_type: "fit", "fit.gz", "tcx", "tcx.gz", "gpx", "gpx.gz". Returns an upload ID to check status with get_upload_status. Note: Actual file upload requires multipart/form-data with the file content. This endpoint initiates the process. Check upload status periodically — processing takes 10-60 seconds. Upload an activity file (FIT, TCX, GPX) to Strava for processing

Example Prompts for Strava Planning in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Strava Planning immediately.

"List all my saved routes."

"Export route 12345 to GPX format."

"Create a manual activity for today's gym session."

Troubleshooting Strava Planning MCP Server with Pydantic AI

Common issues when connecting Strava Planning to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Strava Planning + Pydantic AI FAQ

Common questions about integrating Strava Planning MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an 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?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Strava Planning MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.