Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/DanielTomaro13/sportsdata-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/danieltomaro13/sportsdata-mcp/sportsdata)<a href="https://agentmods.dev/mcp/danieltomaro13/sportsdata-mcp/sportsdata"><img src="https://agentmods.dev/badge/mcp/danieltomaro13/sportsdata-mcp/sportsdata/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/danieltomaro13/sportsdata-mcp/sportsdata"><img src="https://agentmods.dev/badge/mcp/danieltomaro13/sportsdata-mcp/sportsdata.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
sportsdata scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"sportsdata": {
"command": "uvx",
"args": [
"sportsdata-mcp",
"serve"
]
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 9 lines scan A c3c41f77de29
sportsdata is an MCP server published in the GitHub repository DanielTomaro13/sportsdata-mcp (16 stars, last pushed 5d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other mcp servers, from other repositories
sports-hub
41 sports API providers, 396 tools: scores, stats, odds, esports, chess, motorsport & more. Runs locally from the mcp-sports-hub npm package. Needs 4 environment variables to run.
prediction-markets
Prediction market odds from Polymarket. Active markets, probabilities, volume. x402. Remote server at prediction-markets.api.klymax402.com.
event-resolver
Resolve prediction market events. Price checks, claim verification, outcome confidence. Remote server at event-resolver.api.klymax402.com.
puntersedge
MCP server "puntersedge" as configured in Propertyscout001/puntersedge-mcp. Runs locally from the puntersedge-mcp npm package. Needs 2 environment variables to run.
pmq
Fail-closed execution and market-data layer for Polymarket CLOB V2: local signing, confirmed fills only, fee-correct math, working deposit-wallet (POLY1271) support. Runs locally from the pmquant Python package. Needs 11 environment variables to run.
parlay
MCP server "parlay", hosted remotely at mcp.parlay.run, as configured in parlay-run/parlay-mcp.