Koskamo

Paceva MCP

A read-only MCP server that connects endurance athletes' watch data from Intervals.icu to AI apps like Claude and ChatGPT. It provides race predictions, training readiness, HRV, sleep data, and workout analysis via OAuth 2.1 authentication.

Endpoint and access

OAuth sign-in: the first time you connect, your client opens the vendor's own authorization prompt in a browser.

Paceva MCP logo, by PacevaCommunity listingStreamable HTTPOAuth sign-inEndpoint checked 2026-11-01Published by Paceva
MCP endpoint (Streamable HTTP)
https://paceva.app/api/mcp
Vendor documentation

What you can do with it

  • Check training readiness and HRV status
  • Get race predictions for swimming, biking, or running
  • Analyze recent workout blocks
  • Review sleep and recovery metrics

Source and maintenance

Community listingRegistry 1.0.0
Maintenance checked

Tools

Reported by the attributed source; not independently observed by Koskamo.

No tool definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
496 ms
95th percentile latency
496 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 496 ms · metadata changed · refuses unauthenticated initialize (HTTP 401)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http paceva-mcp https://paceva.app/api/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add paceva-mcp --url https://paceva.app/api/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable paceva-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "paceva-mcp": {
      "url": "https://paceva.app/api/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "paceva-mcp": {
      "type": "streamableHttp",
      "url": "https://paceva.app/api/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start paceva-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "paceva-mcp": {
      "type": "http",
      "url": "https://paceva.app/api/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http paceva-mcp https://paceva.app/api/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "paceva-mcp": {
      "url": "https://paceva.app/api/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "paceva-mcp": {
      "serverUrl": "https://paceva.app/api/mcp"
    }
  }
}

Let your agent find its tools

Find servers like Paceva MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.