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.
npx skills add PaulieB14/predictfun-subgraphs --skill mcp-servergit clone --depth 1 https://github.com/PaulieB14/predictfun-subgraphsWrote 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/skills/paulieb14/predictfun-subgraphs/mcp-server)<a href="https://agentmods.dev/skills/paulieb14/predictfun-subgraphs/mcp-server"><img src="https://agentmods.dev/badge/skills/paulieb14/predictfun-subgraphs/mcp-server.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.01498 |
| Opus 5 | $0.00018 | $0.00749 |
| Sonnet 5 | $0.00007 | $0.00300 |
| Haiku 4.5 | $0.00004 | $0.00150 |
Grade A, and why
predictfun-mcp 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Predict.fun MCP
Structured access to Predict.fun prediction market data on BNB Chain — platform stats, market analysis, trader profiling, yield mechanics, and behavioral meta-tools.
Tools
- get_platform_stats — Full platform overview: volume, OI, yield, sync status
- get_top_markets — Rank markets by volume, open interest, or trade count. OI mode flags zombie OI. NegRisk markets show human-readable names (e.g., "Will Spain win the 2026 FIFA World Cup?")
- get_market_details — Deep dive: OI, resolution, top holders (User/Bot/EOA/Protocol labels), orderbook stats, oracle contract identification, zombie OI detection with redemption context
- get_trader_profile — Full P&L: trades, positions, payouts, yield rewards. Distinguishes Privy smart wallet users from bots and protocol contracts
- get_recent_activity — Latest trades, splits, merges, redemptions, or yield claims
- get_yield_overview — Venus Protocol yield stats with context: on-chain claims are protocol-level settlements, per-user yield accrues via position value snapshots
- get_whale_positions — Largest holders with % of market OI, market names, User/Bot/EOA labels (protocol contracts filtered at query level)
- get_leaderboard — Top traders by volume, payouts, or trade count with User/Bot/EOA labels (protocol contracts filtered at query level)
- get_resolved_markets — Recently settled markets with outcomes and condition IDs
- query_subgraph — Custom GraphQL against any of the three subgraphs
- find_trader_persona — Classify a trader: whale, yield farmer, arbitrageur, early mover, sniper
- scan_trader_personas — Find traders matching a behavioral archetype (protocol contracts excluded from whale scan)
- tag_market_structure — Tag a market by type (standard, neg_risk, ct_yield, bond), resolution latency, liquidity, oracle type with contract identification, tail risk with zombie OI flags
- scan_markets_by_structure — Find markets by structural filter
What ships with it
9 files beside SKILL.md 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 First seen · 94 lines · 36 tokens per session scan A 8bc791c095a3
predictfun-mcp is a skill published in the GitHub repository PaulieB14/predictfun-subgraphs (0 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 1,498 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-31.
Other skills, from other repositories
mpp-agent
Pay HTTP 402 APIs via Machine Payments Protocol (MPP).
crypto-market-rank
Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…
trading-signal
Subscribe and retrieve on-chain Smart Money signals. Monitor trading activities of smart money addresses, including buy/sell signals, trigger price, current price, max gain, and exit rate. Use this skill when users are looking for investment opportunities — smart money signals can serve as valuable references for…
cobie-cycle-filter
Use when evaluating crypto decisions through a Cobie-style cycle filter: common-sense risk, narrative traps, leverage humility, and avoiding obvious stupid trades.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.
hyperliquid
Hyperliquid L1 perps DEX (69% market share).