Strava Training MCP Server for LlamaIndex 12 tools — connect in under 2 minutes
LlamaIndex specializes in data-aware AI agents that connect LLMs to structured and unstructured sources. Add Strava Training as an MCP tool provider through Vinkius and your agents can query, analyze, and act on live data alongside your existing indexes.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
mcp_client = BasicMCPClient("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
mcp_tool_spec = McpToolSpec(client=mcp_client)
tools = await mcp_tool_spec.to_tool_list_async()
agent = FunctionAgent(
tools=tools,
llm=OpenAI(model="gpt-4o"),
system_prompt=(
"You are an assistant with access to Strava Training. "
"You have 12 tools available."
),
)
response = await agent.run(
"What tools are available in Strava Training?"
)
print(response)
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 Strava Training MCP Server
Connect Strava Training to any AI agent and unlock deep performance analysis from your Strava data — activity details, time-series streams, heart rate/power zones, segment efforts, lap splits, and lifetime athlete statistics.
LlamaIndex agents combine Strava Training tool responses with indexed documents for comprehensive, grounded answers. Connect 12 tools through Vinkius and query live data alongside vector stores and SQL databases in a single turn. ideal for hybrid search, data enrichment, and analytical workflows.
What you can do
- Activity Details — Full metrics: distance, time, elevation, HR, power, speed, weather, gear
- Activity Streams — Raw GPS, heart rate, power, cadence, altitude, speed, temperature, grade data
- Activity Zones — Heart rate and power zone distribution for training intensity analysis
- Activity Laps — Auto-split lap data with pace, distance, and elevation per split
- Segment Efforts — Find, compare, and analyze all efforts on any segment with detailed metrics
- Segment Streams — Elevation and grade profiles along segments for previewing difficulty
- Segment Details — Distance, elevation, grade, effort count, and personal records
- Athlete Statistics — Lifetime and recent totals for runs, rides, and all activities
- Athlete Zones — Personal heart rate and power zone configurations
- Gear Tracking — Equipment mileage, models, and primary gear assignments
The Strava Training MCP Server exposes 12 tools through the Vinkius. Connect it to LlamaIndex 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 Training to LlamaIndex via MCP
Follow these steps to integrate the Strava Training MCP Server with LlamaIndex.
Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai
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 Strava Training
Why Use LlamaIndex with the Strava Training MCP Server
LlamaIndex provides unique advantages when paired with Strava Training through the Model Context Protocol.
Data-first architecture: LlamaIndex agents combine Strava Training tool responses with indexed documents for comprehensive, grounded answers
Query pipeline framework lets you chain Strava Training tool calls with transformations, filters, and re-rankers in a typed pipeline
Multi-source reasoning: agents can query Strava Training, a vector store, and a SQL database in a single turn and synthesize results
Observability integrations show exactly what Strava Training tools were called, what data was returned, and how it influenced the final answer
Strava Training + LlamaIndex Use Cases
Practical scenarios where LlamaIndex combined with the Strava Training MCP Server delivers measurable value.
Hybrid search: combine Strava Training real-time data with embedded document indexes for answers that are both current and comprehensive
Data enrichment: query Strava Training to augment indexed data with live information before generating user-facing responses
Knowledge base agents: build agents that maintain and update knowledge bases by periodically querying Strava Training for fresh data
Analytical workflows: chain Strava Training queries with LlamaIndex's data connectors to build multi-source analytical reports
Strava Training MCP Tools for LlamaIndex (12)
These 12 tools become available when you connect Strava Training to LlamaIndex via MCP:
get_activity
The activityId is the numeric ID from Strava activity URLs (e.g., strava.com/activities/12345678 → 12345678). Use this for deep analysis of any workout, ride, or run. Get detailed information about a specific Strava activity
get_activity_laps
Each lap includes distance, moving time, average speed, elevation gain, and pace. GPS devices and Strava auto-split activities into laps (typically ~1km or ~1mi). Use this to analyze pace consistency, identify fast/slow sections, and compare splits within a single activity. Get lap/split data for a Strava activity
get_activity_streams
The "types" parameter is comma-separated stream types: "time", "distance", "latlng", "altitude", "velocity_smooth", "heartrate", "cadence", "watts", "temp", "moving", "grade_smooth". Example: "heartrate,watts,velocity_smooth" for HR, power, and speed data. Each stream returns an array of values with corresponding timestamps. Use this for detailed performance analysis, visualization, or export. Get raw time-series data streams from a Strava activity (GPS, heart rate, power, cadence, altitude, speed, etc)
get_activity_zones
Requires activity ID. This data helps understand training intensity and whether the workout targeted the correct zones. Only available for activities with heart rate or power data. Summit/subscription feature. Get heart rate and power zone distribution for a Strava activity
get_athlete_stats
Use the athlete's Strava numeric ID. Returns recent_run_totals, recent_ride_totals, all_run_totals, all_ride_totals. Great for performance overview and progress tracking. Get consolidated activity statistics for any Strava athlete
get_athlete_zones
Requires profile:read_all scope. Use this to understand training zones for zone-based analysis of activities and efforts. Get the authenticated athlete's custom heart rate and power zones
get_gear
The gear ID is found in activity data or athlete profile. Use this to track equipment mileage, plan maintenance, or analyze performance with specific gear. Get details about a piece of equipment (bike, shoes) tracked in Strava
get_segment
The segment ID is found in Strava segment URLs. Use this to discover segment characteristics before attempting it or to compare segments. Get details of a Strava segment including distance, elevation, grade, and leaderboards
get_segment_effort
Includes elapsed time, distance, average speed, heart rate, power, start date, and activity reference. The effort ID is found in segment effort listings or activity details. Use this to analyze specific KOM/QOM attempts and compare efforts on the same segment. Get details of a specific segment effort (KOM/QOM/PR attempt)
get_segment_effort_streams
Same format as activity streams but limited to the segment portion. The "types" parameter is comma-separated: "time", "distance", "latlng", "altitude", "velocity_smooth", "heartrate", "cadence", "watts". Use this for granular analysis of segment performance. Get time-series data streams for a specific segment effort
get_segment_streams
Useful for previewing a segment's difficulty profile before attempting it. The "types" parameter accepts "distance", "altitude", "grade_smooth". Use this to understand elevation changes and steepness patterns along a segment. Get time-series data streams for a Strava segment (elevation profile, grade, etc)
list_segment_efforts
Filter by athlete_id (required), optionally segment_id to get efforts on a specific segment, and date range with start_date_local and end_date_local (ISO 8601 format). Use this to find PRs, analyze progress on segments over time, or compare multiple efforts on the same segment. List all segment efforts for an athlete, optionally filtered by segment and date range
Example Prompts for Strava Training in LlamaIndex
Ready-to-use prompts you can give your LlamaIndex agent to start working with Strava Training immediately.
"Show my athlete statistics."
"Get activity streams for activity 12345678 with heart rate, power, and speed."
"Show my segment efforts on segment 22978."
Troubleshooting Strava Training MCP Server with LlamaIndex
Common issues when connecting Strava Training to LlamaIndex through the Vinkius, and how to resolve them.
BasicMCPClient not found
pip install llama-index-tools-mcpStrava Training + LlamaIndex FAQ
Common questions about integrating Strava Training MCP Server with LlamaIndex.
How does LlamaIndex connect to MCP servers?
Can I combine MCP tools with vector stores?
Does LlamaIndex support async MCP calls?
Connect Strava Training 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 Strava Training to LlamaIndex
Get your token, paste the configuration, and start using 12 tools in under 2 minutes. No API key management needed.