Server data from the Official MCP Registry
Analyse activities, build training plans and sync structured workouts to your sports watch.
Analyse activities, build training plans and sync structured workouts to your sports watch.
Remote endpoints: streamable-http: https://www.tredict.com/api/mcp/v2 sse: https://www.tredict.com/api/mcp/v2
Valid MCP server (1 strong, 1 medium validity signals). No known CVEs in dependencies. Imported from the Official MCP Registry.
Endpoint verified · Requires authentication · 1 issue found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Remote Plugin
No local installation needed. Your AI client connects to the remote endpoint directly.
Add this to your MCP configuration to connect:
{
"mcpServers": {
"com-tredict-mcp-server": {
"url": "https://www.tredict.com/api/mcp/v2"
}
}
}From the project's GitHub README.
Official Model Context Protocol (MCP) server for Tredict, the planning and analytics platform for endurance sports athletes and coaches. Connect your preferred AI assistant to your complete training history across running, cycling, swimming and more. Analyse activities, determine capacity values, create fully structured training plans inside Tredict, synced directly to your watch.
Tredict also ships interactive MCP App UI widgets that visually render activity details and training plans directly in the LLM chat of hosts such as Claude.ai or ChatGPT.
| Name | Tredict MCP Server |
| MCP Server URL | https://www.tredict.com/api/mcp/v2 |
| Transport | Streamable HTTP and SSE |
| Protocol | MCP 2025-06-18 |
| Authentication | OAuth 2.1 with PKCE / Personal API Token |
Full technical documentation: Tredict MCP Server Documentation.
You: "How did my long run on Sunday go?"
Claude: [Shows pace, heart rate, cadence, elevation and zone distribution.
Flags the last 5 km where HR drifted into threshold]
You: "Build me a 10-week half marathon plan based on my recent training"
Claude: [Analyses last 8 weeks of running history, creates a structured
multi-week plan in My Plans, pushes workouts to your Garmin]
You: "What is my current running FTP?"
Claude: [Derives FTPace from recent efforts, compares to last revision,
suggests updated training zones]
You: "How many kilometres do my current running shoes have?"
Claude: [Lists active shoes with distance logged,
flags gear approaching typical replacement range]
You: "How does my 2025 training compare to 2024?"
Claude: [Compares total volume, zone distribution, long run progression
and peak weeks across both years]
You: "Am I ready for tomorrow's threshold session?"
Claude: [Reads HRV trend, resting heart rate and recent training load.
Gives a clear go or back-off recommendation]
You: "Am I actually hitting my training zones as planned?"
Claude: [Shows prescribed vs actual time in each zone per sport,
highlights where execution is drifting from the plan]
You: "What does my HRV trend tell me about my current fitness?"
Claude: [Analyses rMSSD baseline, flags suppression periods,
links dips to high-load weeks in training history]
You: "Is my sub-4 marathon goal realistic given my current training?"
Claude: [Derives pace capacity from recent long runs and threshold efforts,
compares to goal pace, outlines what needs to improve]
Officially supported: Anthropic Claude (Web, Desktop, Code), OpenAI ChatGPT, OpenAI Codex, Mistral Le Chat, Mistral Vibe.
Compatible: any MCP client that supports OAuth 2.1 or bearer-token authentication, including local LLM setups.
Setup guides per platform:
Settings → Connectors → Add custom connector:
Tredicthttps://www.tredict.com/api/mcp/v2OAuth is handled automatically on first use.
{
"mcpServers": {
"tredict": {
"url": "https://www.tredict.com/api/mcp/v2",
"transport": { "type": "http" }
}
}
}
For clients without OAuth support, create an access token in Tredict at "Settings → Personal API / MCP" and pass it as a bearer token:
Authorization: Bearer <your-personal-api-token>
The server supports two methods:
activityRead, activityWrite, bodyvaluesRead.See the OAuth2 documentation for full details.
All tool names, descriptions and schemas can be listed by the MCP client. Scope annotations in parentheses.
| Tool | Description | Scope |
|---|---|---|
activity-list | List executed activities for a date range | activityRead |
activity | Activity details, metrics and time series | activityRead |
activity-update | Update title and notes of an activity (non-destructive) | activityWrite |
equipment-list | List all user equipment (bikes, shoes, swimming, misc) | activityRead |
| Tool | Description | Scope |
|---|---|---|
plan-creation | Create a reusable training plan in "My Plans" | activityWrite |
add-plan-training | Add a single structured workout to an existing plan | activityWrite |
planned-workout-list | List planned / scheduled workouts | activityRead |
planned-workout | Details and structure of a single planned workout | activityRead |
planned-workout-change-date | Reschedule a planned workout to a new date | activityWrite |
training-effort-list | Training effort over time across all sportTypes | activityRead |
| Tool | Description | Scope |
|---|---|---|
bodyvalues | Weight, body fat, resting HR, body height and more | bodyvaluesRead |
capacity | Capacity values (HRmax, HRlth, FTP, FTPace) per sportType | bodyvaluesRead |
hrv-list | Heart rate variability data with baseline | bodyvaluesRead |
sleep-list | Sleep data with baseline | bodyvaluesRead |
zones | Zone revisions per sportType and zoneType | bodyvaluesRead |
zones-distribution | Aggregated zones distribution per sportType and month | bodyvaluesRead |
| Tool | Description | Scope |
|---|---|---|
show-activity-ui | Render activity details, metrics, laps and map in the chat | activityRead |
show-plan-ui | Render a reusable training plan with calendar view in the chat | activityRead |
Predefined, parameterised tasks the host can offer as templates:
better-names : find recent activities with poor titles and suggest meaningful ones.coolest-training (year) : find the most interesting session of a given year.compare-years (firstYear, otherYear) : in-depth year-over-year comparison.create-plan (monthsBack?, durationInWeeks?, workoutsPerWeeks?, sportTypes?, targetZonesTypes?) : build a full training plan from recent history.determine-ftp (sportType?) : derive current FTP from training history.indepth-analysis : 2-year in-depth training status assessment.recreate-structured-workout (activityId) : rebuild an executable structured workout from an executed activity.| URI | Description |
|---|---|
mcp://tredict/assets/logo.svg | Tredict rectangular logo (light / dark themes) |
mcp://tredict/assets/logo-slogan.svg | Tredict logo with "Analytics for Endurance Athletes" slogan |
ui://widget/activity-ui-100.html | Activity details UI widget (MCP App) |
ui://widget/plan-ui-100.html | Training plan UI widget (MCP App) |
activity-update stores previous titles and notes in the mcpUpdatedFields array, so any change can be rolled back at any time.Some responses, in particular from plan-creation, ask the LLM to surface health and liability notices. By registering with Tredict, the user accepts responsibility for health-related applications of the data as defined in the Terms of Use. LLMs make mistakes and are not a substitute for a qualified coach or your own judgement.
An external MCP client has no access to Tredict data until the user explicitly configures it. Read and write permissions can be restricted per scope at token creation. Tredict is fully GDPR compliant; see the Privacy Policy. Review the privacy policy of the connected AI provider for what happens to data sent through it, or use a local LLM to keep everything on-device.
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Web content fetching and conversion for efficient LLM usage
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.