Rundida MCP Server

MCP server for AI agents: compute paces, HR zones and race predictions; query 300+ marathons and 99 running calculators. Zero-config, no API key. The rundida mcp mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 10 defined tools rather than through you.

What it actually does

MCP server for RunDida — running expertise for AI agents.

RunDida (跑滴答) is a free running tools platform for runners of all levels:

Adding it to your client

@rundida/mcp-server on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Its toolset

Everything the assistant can do here goes through one of these:

• list_tools — Data
• get_tool — Data
• list_guides — Data
• get_guide — Data
• list_marathons — Data
• get_marathon — Data
• calculate_pace — Compute
• predict_race — Compute
• heart_rate_zones — Compute
• marathon_countdown — Compute

Configuration

• Node.js >= 18 - Internet connection (data tools fetch from rundida.com)

Caveats

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• With 10 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Rundida MCP.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the rundida mcp mcp server does with a few real requests.

When to reach for it

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Rundida MCP's toolset — list_tools, get_tool, list_guides and 7 more — is a fair guide to whether it matches your workflow. It is maintained by xweaponx7; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.