MCP.Market

COROS MCP server

online · 100% uptime
by coroslab·io.github.coroslab/coros-mcp·v1.0.1·74 stars

Access COROS activity, training and health data, and manage training plans and workouts.

A95/100grade A
What users say
No reviews yet
Be the first
Safety scan
A95/100

full report

Adoption
Growing

74 stars

Reviews

Write one

Nobody has reviewed COROS yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

COROS tools

Tool list not cached yet. `describe` through the gateway fetches it live.

Public scan report

scanner v0.1.10 · 2026-10-25 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 291ms (auth required)20/20
  • –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
  • Auth qualityOAuth resource metadata advertised on 40115/15
  • Maintenancelast push 6 days ago15/15
  • Maintainer identityregistry namespace matches repository owner7/10
Overall 95/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How COROS compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
95/100
higher than 97% of 48,255 servers
Uptime
100%
of our recent checks; the typical remote server answers 100%
Response time
1,056 ms
faster than 10% of 30,031 servers
GitHub stars
74
more than 95% of 28,688 servers

Install COROS in Claude Code, Cursor or VS Code

claude mcp add --transport http coros-mcp https://mcpus.coros.com/mcp
Add to Cursor

What the publisher says

From the COROS repository's README, as published. We do not edit it. Read it on GitHub

English | 中文 | Setup Guide | Tool Guide | FAQ | Changelog

COROS MCP

Connect COROS with AI. Put your training data to work.

COROS MCP lets you use your preferred AI assistant to query activity and health data, review performance, and create or adjust training plans and workouts—all through conversation.

COROS believes athletes should own their data and be free to choose how they use it. Through MCP (Model Context Protocol), you can authorize an AI platform of your choice to access your COROS data and explore new ways to use it.

What you can do

Review your training and see what has changed

From laps in a single run to months of training trends, let AI answer your questions using your actual records.

“Compare my last two long runs. How did my pace and heart rate differ in the second half?”

Understand your body's response

Review sleep, HRV, heart rate, stress, and activity records together to understand recent changes and how they relate to your training.

“Summarize my sleep and HRV trends over the past two weeks alongside my training volume. What has changed?”

Turn training ideas into a schedule

Build a plan around your current fitness and race goals and save it to COROS. You can also create individual workouts or adjust sessions already on your schedule.

“I'm preparing for a half marathon in 8 weeks. Review my recent training and fitness data, draft a plan, and save it to COROS after I confirm.”

Find your own ways to use your data

Create an annual activity map, generate a personal training report, or build your own training assistant. Combined with your AI platform's other capabilities, you can also research routes, organize race information, and bring COROS data into more of what you do.

These are just starting points. How you use your activity data is up to you.

Quick start

COROS is available in the following official plugin or connector directories. Add it directly without configuring an MCP URL.

Follow the prompts to add COROS, sign in, and authorize access. Then start a conversation.

For other platforms, manual MCP setup, or Skill access, see the Setup Guide.

Capabilities

For full tool descriptions, parameters, and usage limits, see the Tool Guide.

Frequently asked questions

Which AI platforms are supported?

In addition to the platforms listed above, COROS MCP supports compatible MCP clients and Skill access. Availability depends on the platform's connection and authentication capabilities.

See the Setup Guide for connection options.

Does COROS MCP cost anything?

COROS MCP itself is free to use. Your AI platform may require a subscription or impose usage limits for connectors, models, or tool calls. Check that platform's policies for details.

For more questions, see the full FAQ.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

COROS: common questions

Is COROS MCP server safe?
Yes, by our scan: it is graded A (95/100). Read the COROS safety report
How do I install COROS?
It runs remotely at mcpus.coros.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does COROS need an API key?
No key to paste: it signs you in with OAuth when your client connects.
Is COROS maintained?
The last commit was 16 days ago (2026-10-19). The latest release is v1.0.1.
Is COROS up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
How does COROS compare with other MCP servers?
safety score 95/100 (higher than 97% of 48,255 servers); uptime 100% (of our recent checks; the typical remote server answers 100%); response time 1,056 ms (faster than 10% of 30,031 servers). Full comparison.