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/predictionmarketspicks/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/plugins/predictionmarketspicks/mcp/gemini-extension)<a href="https://agentmods.dev/plugins/predictionmarketspicks/mcp/gemini-extension"><img src="https://agentmods.dev/badge/plugins/predictionmarketspicks/mcp/gemini-extension/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/plugins/predictionmarketspicks/mcp/gemini-extension"><img src="https://agentmods.dev/badge/plugins/predictionmarketspicks/mcp/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
predictionmarketspicks 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 7d 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
{
"name": "predictionmarketspicks",
"version": "1.12.2",
"description": "Live Kalshi and Polymarket market data in Gemini CLI: NFL prop prices across venues, cross-venue price gaps, Fed meeting odds, 15-minute crypto and metals markets, NHL, Senate races, and EV / Kelly / Bayes calculators. Free, no key. 47s demo: https://www.youtube.com/watch?v=VCmYQQXq2bo",
"mcpServers": {
"predictionmarketspicks": {
"httpUrl": "https://predictionmarketspicks.com/api/mcp/mcp?via=gemini",
"timeout": 30000
}
},
"contextFileName": "GEMINI.md"
}
What ships with it
3 files beside gemini-extension.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago Changed cfd2b784e4cd
- 11d ago Changed · +1 lines 235c7e1e76f7
- 13d ago First seen · 12 lines scan A 76bde6d3662b
predictionmarketspicks is a plugin published in the GitHub repository predictionmarketspicks/mcp (0 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-10-03.
Other plugins, from other repositories
mcp-server-for-ynab
Connect your AI assistant to YNAB. Read-only by default, with opt-in writes that are recorded and reversible.
flopsindex
Key-free GPU compute rental reference prices (H100, A100, H200; spot / on-demand / DePIN). Every value carries a verify URL for citation.
oddsrail
Trade Polymarket and Kalshi from Claude Code: live books, costed fills, settlement audits, guardrails, paper trading, and non-custodial order routing. Read tools need no keys.
parlay
AI-native prediction market aggregator. Live odds and arbitrage signals across Polymarket, Kalshi, and Limitless.
shingou
Shingou point-in-time crypto sentiment API skill + MCP tools.
kalshi-trader
AI-assisted research and trading workflow for Kalshi prediction markets. Includes commands for opportunity scanning, deep research, critical analysis, scoring, and position management.