What model does this MCP use for predictions?

The MCP uses the Riegel fatigue model to estimate race performance across different distances.

Can I use this with Claude or Cursor?

Yes, you can connect this MCP to any compatible client including Claude, Cursor, and Windsurf.

Does it support distances in miles?

Yes, the capability includes a validation step that normalizes mile measurements into meters for accurate processing.

What kind of pacing strategies can it generate?

It can generate segmented strategies including Even Split, Negative Split, and Conservative Start approaches.

How do I get started?

You subscribe through Vinkius, which hosts the MCP for you. Once connected, you just talk to your AI agent about your running goals.

How accurate are the race predictions?

Predictions use the Riegel model, which is highly effective for standard distances. For ultra-endurance distances exceeding a marathon, the system applies an adjusted fatigue exponent to maintain accuracy.

What pacing strategies are available?

You can choose from EVEN_SPLIT for constant speed, NEGATIVE_SPLIT to finish faster than you started, or CONSERVATIVE_START to conserve energy early in the race.

Can I use my own distance measurements?

Yes. You can provide distances in meters, kilometers, or miles. The validate_race_input capability will automatically normalize them to meters for precise calculation.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect Running Race Predictor to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Turn recent race results into precise pacing plans.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 3 capabilities

We ship only the actions that matter.

Capability set01 / 01

01-03

3 capabilities in this set.

Part of 3 available through Running Race Predictor.

01
Generate segment strategy
This capability builds a segmented pacing plan for your target race. It can output specific splits for even, negative, or conservative pacing approaches.
02
Predict race times
This capability estimates your performance for standard race distances. It uses the Riegel model to project times based on your recent results.
03
Validate race input
This capability checks and normalizes your race distance data. It ensures all measurements are converted to meters before the model processes them.

Real work

What teams actually run

Goal Setting

Predict your marathon time after finishing a successful 5K or 10K.

Race Day Planning

Create a negative split strategy to ensure you don't burn out too early in a race.

Data Cleaning

Normalize mixed distance inputs to ensure the model receives correct metric data.

Training Validation

Check if your recent race improvements translate to better projected times for longer distances.

One connector, every AI

Running Race Predictor works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put Running Race Predictor to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

681ms average. Fast in production.

Running Race Predictor is checked daily against the live service.

Daily averagePeak 1002ms

Oct 3Today

Fastest day: 528ms
Slowest day: 1002ms
14-day trend: Improving-10%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 3 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Running Race Predictor, so you can see the experience inside your AI.

It does not authenticate your account with Running Race Predictor. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Running Race Predictor Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_dEd6lJVkz6lOxZ2kc47EqtF7OBIihzT9hdzvOXmD/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — Running Race Predictor capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "running-race-predictor-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_dEd6lJVkz6lOxZ2kc47EqtF7OBIihzT9hdzvOXmD/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Running Race Predictor in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Running Race Predictor owners hand off.

This MCP is built for endurance athletes and coaches who want to move away from guesswork and toward mathematical modeling.

01
Runners
Use the capability to set realistic goals for upcoming races based on current fitness.
02
Running Coaches
Hand off the math to your agent to generate structured pacing plans for clients.
03
Data-driven Athletes
Use the Riegel model to validate if your training is actually improving your projected race times.

FAQ

Questions Running Race Predictor owners ask.

01
What model does this MCP use for predictions?
The MCP uses the Riegel fatigue model to estimate race performance across different distances.
02
Can I use this with Claude or Cursor?
Yes, you can connect this MCP to any compatible client including Claude, Cursor, and Windsurf.
03
Does it support distances in miles?
Yes, the capability includes a validation step that normalizes mile measurements into meters for accurate processing.
04
What kind of pacing strategies can it generate?
It can generate segmented strategies including Even Split, Negative Split, and Conservative Start approaches.
05
How do I get started?
You subscribe through Vinkius, which hosts the MCP for you. Once connected, you just talk to your AI agent about your running goals.
06
How accurate are the race predictions?
Predictions use the Riegel model, which is highly effective for standard distances. For ultra-endurance distances exceeding a marathon, the system applies an adjusted fatigue exponent to maintain accuracy.
07
What pacing strategies are available?
You can choose from EVEN_SPLIT for constant speed, NEGATIVE_SPLIT to finish faster than you started, or CONSERVATIVE_START to conserve energy early in the race.
08
Can I use my own distance measurements?
Yes. You can provide distances in meters, kilometers, or miles. The validate_race_input capability will automatically normalize them to meters for precise calculation.

Explore

More in Productivity

Connect Running Race Predictor to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-03

Generate segment strategy

Predict race times

Validate race input

What teams actually run

Goal Setting

Race Day Planning

Data Cleaning

Training Validation

Building your own app? The connector is yours to use.

Running Race Predictor Connector

Claude Desktop

Runners

Running Coaches

Data-driven Athletes

What model does this MCP use for predictions?

Can I use this with Claude or Cursor?

Does it support distances in miles?

What kind of pacing strategies can it generate?

How do I get started?

How accurate are the race predictions?

What pacing strategies are available?

Can I use my own distance measurements?

Running Pace & Race Calculator AI Connector

Training Pace Calculator AI Connector

Running Pace Converter AI Connector

Running Pace Calculator AI Connector

Suggestions

Running Pace & Split Calculator AI Connector

Running Pace Equivalent AI Connector

Race Finish Time Calculator AI Connector

Weekly Training Load Calculator AI Connector