Back to Browse

Tennis MCP Server

Developer ToolsLow Risk8.0MCP RegistryLocal
Free

Server data from the Official MCP Registry

Zero-clone ATP tennis analytics: 200k+ matches since 1968, H2H, GSDI, NBI, and shot charting.

About

Zero-clone ATP tennis analytics: 200k+ matches since 1968, H2H, GSDI, NBI, and shot charting.

Security Report

8.0
Low Risk8.0Low Risk

Valid MCP server (1 strong, 3 medium validity signals). 4 known CVEs in dependencies Package registry verified. Imported from the Official MCP Registry.

4 files analyzed ยท 5 issues found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

file_system

Check that this permission is expected for this type of plugin.

What You'll Need

Set these up before or after installing:

Optional path to a local tml-data/data directory to bypass HTTPS Parquet caching.Optional

Environment variable: TML_DATA_DIR

Optional cache directory for downloaded Parquet/JSON slices (defaults to ~/.cache/tennis-mcp).Optional

Environment variable: TENNIS_MCP_CACHE_DIR

How to Install

Add this to your MCP configuration file:

{
  "mcpServers": {
    "tennis-mcp": {
      "command": "uvx",
      "args": [
        "tennis-mcp==0.1.1"
      ],
      "env": {
        "TML_DATA_DIR": "your-tml-data-dir-here",
        "TENNIS_MCP_CACHE_DIR": "your-tennis-mcp-cache-dir-here"
      }
    }
  }
}

Some servers take additional arguments. See the repository for details.

Documentation

View on GitHub

From the project's GitHub README.

๐ŸŽพ tennis-mcp

PyPI sorukumar/tennis-mcp MCP server License: MIT Python 3.11+ Data: sorukumar/tml-data Visualizations

Zero-clone Model Context Protocol (MCP) server for Open Era ATP tennis.

Query 200,105 ATP matches (1968โ€“2026), 7,622 player careers, 113,744 surface-split head-to-heads, 7,663 Match Charting Project shot/rally breakdowns, and curated dominance/drama indices (GSDI, NBI, Race to Greatness, Young Guns) directly inside Claude, Cursor, Antigravity, or VS Code โ€” without cloning the 265 MB data repo.


โšก Quick Start (Zero Clone)

tennis-mcp runs via uvx (or pip install tennis-mcp) and lazily caches only the Parquet/JSON tables your questions need into ~/.cache/tennis-mcp/.

Claude Desktop / Cursor / Antigravity (mcpServers)

{
  "mcpServers": {
    "tennis-mcp": {
      "command": "uvx",
      "args": ["tennis-mcp"]
    }
  }
}

Claude Code (CLI)

claude mcp add tennis-mcp -- uvx tennis-mcp

VS Code (.vscode/mcp.json)

{
  "servers": {
    "tennis-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": ["tennis-mcp"]
    }
  }
}

pip Install / Offline tml-data Override

If you prefer pip or already cloned sorukumar/tml-data, install from PyPI and optionally point TML_DATA_DIR at your local data directory:

pip install tennis-mcp
TML_DATA_DIR=/path/to/tml-data/data tennis-mcp

๐Ÿ›  Available MCP Capabilities

15 Tools (Powered by DuckDB + Parquet + Story JSONs)

CategoryToolWhat It Queries
Warehouseget_dataset_overviewLive row counts, date window, charting counts, and licenses
Playerssearch_playersFilter 7,622 ATP careers by name, country IOC code, or Slam champion status
Playersget_player_profileCareer W-L, surface splits, Top 10 win%, recent matches, and MCP charting profile
Rivalriesget_head_to_headSurface-by-surface H2H breakdown (113,744 pairs) + individual match logs
Matchessearch_matchesParameterized SQL search over 200,105 enriched ATP matches
Shot / Rallyget_charting_profile475 players' serve/return, rally length (1โ€“3 / 4โ€“6 / 7โ€“9 / 10+), UF rate, Serve+1, and surface splits
Shot / Rallyget_match_charting_statsPer-match winners, unforced errors, rally distributions across 7,663 charted matches
Comparecompare_playersSide-by-side comparison of 2โ€“6 players across career stats, charting, and age snapshots
Indicesget_gsdi_rankingsGrand Slam Dominance Index (231 title runs)
Indicesget_nail_bitersNail-Biter Index (687 Grand Slam Finals & Semifinals)
Indicesget_greatness_raceAge-for-age title & Slam pace: Big 3, Alcaraz, Sinner, Borg, Sampras, McEnroe, Lendl, Agassi
Indicesget_young_guns_raceFonseca, Mensik, Tien, Jodar benchmarked against Alcaraz & Sinner
Indicesget_gs_breakthroughCareer age, matches, and years before first Grand Slam title across 59 champions
Geographyget_country_profileTop 100 / Top 10 ATP evolution across 50 years by IOC code or snapshot year
Indiaget_indian_tennis_statsOpen Era Indian ATP singles milestones & histories

7 Resources (tennis://*)

  • tennis://overview, tennis://gsdi/top, tennis://nbi/top, tennis://greatness/summary, tennis://young-guns/summary, tennis://global/timeline, tennis://indian/notable

3 Prompt Templates

  • scouting_report(player_name)
  • rivalry_breakdown(player1, player2)
  • slam_campaign_audit(player_name, tournament)

๐Ÿ’ฌ Example Questions You Can Ask Your AI

  • "Compare Jannik Sinner and Carlos Alcaraz on 1st-serve won%, unforced error rate, and Clay charting metrics."
  • "Show me Novak Djokovic vs Rafael Nadal head-to-head by surface, plus their highest Nail-Biter Index Slam matches."
  • "Which players won a Grand Slam with the fewest tour matches before their first major?"
  • "How does Joao Fonseca at age 18โ€“20 track against Carlos Alcaraz in ATP wins and Top 50 wins?"
  • "List the top 5 Grass-court Grand Slam comebacks since 2000 sorted by comeback score and duration."

๐Ÿ— Architecture

Claude / Cursor / Antigravity / VS Code
            โ”‚  (stdio MCP)
            โ–ผ
       tennis-mcp  (Python + FastMCP/MCPServer + DuckDB)
            โ”‚
            โ”œโ”€โ”€ TML_DATA_DIR set? โ”€โ”€โ–ถ Local tml-data/data/*.parquet + *.json
            โ”‚
            โ””โ”€โ”€ Otherwise โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ–ถ Lazy cache (~/.cache/tennis-mcp/, 7-day TTL)
                                       fetched via HTTPS from sorukumar/tml-data

๐Ÿ“„ License & Data Attribution

Reviews

No reviews yet

Be the first to review this server!