Agent skill

Prediction Markets

by BlockRunAI in BlockRunAI/blockrun-mcp

Install Prediction Markets

skills CLI

$ npx skills add BlockRunAI/blockrun-mcp --skill prediction-markets -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install BlockRunAI/blockrun-mcp prediction-markets --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/BlockRunAI/blockrun-mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/prediction-markets .claude/skills/prediction-markets && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "prediction-markets" agent skill from https://github.com/BlockRunAI/blockrun-mcp/tree/main/skills/prediction-markets into .claude/skills/prediction-markets/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prediction-markets", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/BlockRunAI/blockrun-mcp/tree/main/skills/prediction-markets

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add BlockRunAI/blockrun-mcp --skill prediction-markets -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install BlockRunAI/blockrun-mcp prediction-markets --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/BlockRunAI/blockrun-mcp.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/prediction-markets .agents/skills/prediction-markets && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "prediction-markets" agent skill from https://github.com/BlockRunAI/blockrun-mcp/tree/main/skills/prediction-markets into .agents/skills/prediction-markets/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prediction-markets", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add BlockRunAI/blockrun-mcp --skill prediction-markets -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install BlockRunAI/blockrun-mcp prediction-markets --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/BlockRunAI/blockrun-mcp.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/prediction-markets .cursor/skills/prediction-markets && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "prediction-markets" agent skill from https://github.com/BlockRunAI/blockrun-mcp/tree/main/skills/prediction-markets into .cursor/skills/prediction-markets/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prediction-markets", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/BlockRunAI/blockrun-mcp.git --path skills/prediction-markets

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add BlockRunAI/blockrun-mcp --skill prediction-markets -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install BlockRunAI/blockrun-mcp prediction-markets --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/BlockRunAI/blockrun-mcp.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/prediction-markets .gemini/skills/prediction-markets && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "prediction-markets" agent skill from https://github.com/BlockRunAI/blockrun-mcp/tree/main/skills/prediction-markets into .gemini/skills/prediction-markets/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prediction-markets", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install BlockRunAI/blockrun-mcp prediction-markets

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add BlockRunAI/blockrun-mcp --skill prediction-markets -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/BlockRunAI/blockrun-mcp.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/prediction-markets .github/skills/prediction-markets && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "prediction-markets" agent skill from https://github.com/BlockRunAI/blockrun-mcp/tree/main/skills/prediction-markets into .github/skills/prediction-markets/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prediction-markets", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add BlockRunAI/blockrun-mcp --skill prediction-markets -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install BlockRunAI/blockrun-mcp prediction-markets --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/BlockRunAI/blockrun-mcp.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/prediction-markets .opencode/skills/prediction-markets && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "prediction-markets" agent skill from https://github.com/BlockRunAI/blockrun-mcp/tree/main/skills/prediction-markets into .opencode/skills/prediction-markets/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prediction-markets", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: prediction-markets
GitHub stars: 391
Token cost: ~3.7k tokens
SKILL.md length: 1,123 words
Files: 1
Skills in repo: 17
Repo updated: Oct 8, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Works in 9 steps: "What are people betting on right now?" → "What's the market saying about the 2028… → "Show me this market's price history"… → …
The user asks about event probabilities
SKILL.md covers How to Call from MCP, Two Pricing Tiers, Quick Decision Table — "User… and Worked Examples, plus 4 more sections
Calls pip

What it does

Prediction Markets is an agent skill from BlockRunAI/blockrun-mcp. Use when the user asks about event probabilities, prediction market odds, what people are betting on, Polymarket/Kalshi prices, sports markets — or about the things you CANNOT get from a public API: historical price/volume/orderbook time series, smart-money positioning, whale leaderboards, wallet P&L, wallet identity and on-chain clustering, and canonical IDs matching the same question across venues. 55 endpoints over Polymarket, Kalshi, Limitless, Opinion, Predict.Fun, Binance Futures, sports, and the UMA…

Its SKILL.md is about 3.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Data & Analytics, covering Smart contracts and Forecasting and time series. It works with Polymarket, Kalshi, x402 and Binance. The repository describes itself as: Live data for AI agents — search, research, markets, crypto, X/Twitter. Pay-per-call via x402 micropayments. The licence is MIT.

When your agent uses it

The user asks about event probabilities
Prediction market odds
What people are betting on
Polymarket/Kalshi prices

Example prompts

“/prediction-markets”

Workflow steps

9 steps, taken from the step headings in SKILL.md.

"What are people betting on right now?"
"What's the market saying about the 2028 election?"
"Show me this market's price history" (impossible from a free API)
"Who's smart money betting on in this market?" ← compound
"This whale is up 400% — who are they really?" ← compound
"Find me something to copy-trade" ← compound
"Is the same bet cheaper on another venue?" ← arbitrage
"Who's ahead in tonight's NBA games?"
"Is this market about to resolve?"

What it can do on your machine

Read from SKILL.md and the folder at commit e9b2bd5. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- pip
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Prediction Markets loads about 3.7k tokens when it runs. Until then it costs about 151 tokens; SKILL.md has 1,123 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~151
When it runs · the whole SKILL.md, loaded when a task matches: ~3.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from BlockRunAI/blockrun-mcp at commit e9b2bd5, republished under its MIT licence (© BlockRunAI). 1,123 words, ~3,709 tokens.

Download SKILL.mdSave it as .claude/skills/prediction-markets/SKILL.md (or your agent's skills folder).

name: prediction-markets
description: Use when the user asks about event probabilities, prediction market odds, what people are betting on, Polymarket/Kalshi prices, sports markets — or about the things you CANNOT get from a public API: historical price/volume/orderbook time series, smart-money positioning, whale leaderboards, wallet P&L, wallet identity and on-chain clustering, and canonical IDs matching the same question across venues. 55 endpoints over Polymarket, Kalshi, Limitless, Opinion, Predict.Fun, Binance Futures, sports, and the UMA oracle. Pay-per-call in USDC via x402 — no Predexon account, no API key.
triggers: polymarket, kalshi, limitless, predict.fun, predexon, prediction market, event probability, betting odds, implied probability, what are people betting on…

Prediction Markets (Predexon)

55 endpoints across Polymarket, Kalshi, Limitless, Opinion, Predict.Fun, Binance Futures, sports, and the UMA oracle — one x402 gateway, no Predexon account or API key.

What is worth paying for. Current market lists are free from public APIs. These are not, and cannot be backfilled after the fact:

History — candlesticks, orderbook snapshots, volume charts, open interest, trade history. Built from continuous ingestion; nobody can reconstruct it retroactively.
Smart money — leaderboards, cohort stats, top holders, which wallets are positioned where, and which markets high-performing wallets just entered.
Wallet intelligence — profiles, P&L time series, identity metadata, and on-chain clustering (find the other wallets behind one address).
Cross-venue canonical IDs — one question, matched across five venues. The basis for arbitrage and consensus.

How to Call from MCP

One tool, three params. Method auto-routes: POST when body is set, GET otherwise.

blockrun_markets({ path: "polymarket/events", params: { limit: "10" } })

blockrun_markets({ path: "polymarket/candlesticks/0xCONDITION_ID", params: { interval: "1440" } })

blockrun_markets({ path: "polymarket/wallet/identities", body: {
  addresses: ["0xabc...", "0xdef..."]
}})

Paths are relative — no /api/v1/pm/ prefix. Use agent_id to bill a child agent's budget.

Paid calls can run in parallel on Base: each EIP-3009 authorization carries its own random nonce, so concurrent calls from one wallet cannot collide. The Solana payload has no nonce field — distinctness comes from the SDK (@blockrun/llm >= 3.8.4), so keep that floor if you fan out on Solana.

Current parameter contracts that prevent paid 4xx responses:

Discover with markets/search (its search term is q), then resolve the selected market with polymarket/markets/keyset + condition_id.
On polymarket/markets{,/keyset} the free-text filter is search, not q. Use status:"open" rather than Gamma's active/closed, and sort rather than order/ascending. end_after/end_before are supported (Unix seconds).
Candlestick interval is integer minutes (1440, not 1h) and is optional — the server has a default. Which intervals a market can serve varies: 1440 may work where 60 returns a paid 400. Optional start_time/end_time are Unix seconds.
polymarket/orderbooks requires token_id, start_time, and end_time; the times are Unix milliseconds.
Smart-money needs a smart-wallet criterion: min_trades, min_volume, min_roi, min_realized_pnl, min_total_pnl, min_win_rate, or min_profit_factor. window only scopes the time range and is not sufficient alone (verified: window-only returns a paid 400). Use { window: "30d", min_trades: "100" }; narrower cohorts are fine.
markets/listings is retired upstream (410 Gone) — the MCP blocks it before payment. The rest of the canonical layer went with it on 2026-08-04: bare markets, outcomes/{predexon_id}, matching-markets and matching-markets/pairs all return 404 Unknown Predexon endpoint before payment (verified live 2026-09-08). Only markets/search survived. No live /v1/pm route accepts a league param.

Two Pricing Tiers

Tier	Price	What
All endpoints	$0.0085 on Base ($0.0075 + the $0.001 network fee; Solana quotes $0.0075)	Market data, events, history, candles, orderbooks, trades, leaderboard, UMA, wallet analytics, smart money, identity + clustering, cross-venue search, Binance (`sports/*` is degraded upstream — see below; the gateway releases the payment on the upstream 500)

Pass-through pricing, 0% BlockRun margin — settles straight to Predexon's Base treasury.

Quick Decision Table — "User asks about X"

User wants…	path	Tier
Same question across venues / search every venue at once	`markets/search` (`q`)	2
Active Polymarket events	`polymarket/events`	1
Polymarket markets	`polymarket/markets`	1
Large result sets (stable paging)	`polymarket/markets/keyset`	1
Crypto up/down markets	`polymarket/crypto-updown`	1
Current/historical price of a token	`polymarket/market-price/{token_id}`	1
Price history (OHLCV)	`polymarket/candlesticks/{condition_id}`	1
OHLCV for one outcome	`polymarket/candlesticks/token/{token_id}`	1
Volume over time (YES/NO split)	`polymarket/volume-chart/{condition_id}`	1
Historical orderbook snapshots	`polymarket/orderbooks`	1
Historical trades	`polymarket/trades`	1
Merges / splits / redeems for a user	`polymarket/activity`	1
Cumulative volume for a market	`polymarket/markets/{token_id}/volume`	1
Open interest history	`polymarket/markets/{condition_id}/open_interest`	1
Positions (filterable)	`polymarket/positions`	1
Global smart-wallet leaderboard	`polymarket/leaderboard`	1
Leaderboard for one market	`polymarket/leaderboard/market/{condition_id}`	1
Cohort performance by trading style	`polymarket/cohorts/stats`	1
Top holders of a market	`polymarket/market/{condition_id}/top-holders`	1
Smart money on a market	`polymarket/market/{condition_id}/smart-money`	2
Markets smart wallets just entered	`polymarket/markets/smart-activity`	2
Full smart-wallet profile	`polymarket/wallet/{wallet}`	2
Per-market breakdown for a wallet	`polymarket/wallet/{wallet}/markets`	2
Wallets with similar portfolios	`polymarket/wallet/{wallet}/similar`	2
Wallet P&L + realized series	`polymarket/wallet/pnl/{wallet}`	2
Wallet open/historical positions	`polymarket/wallet/positions/{wallet}`	2
Wallet volume by BUY/SELL side	`polymarket/wallet/volume-chart/{wallet}`	2
Batch wallet profiles	`polymarket/wallets/profiles`	2
Filter wallets by markets traded	`polymarket/wallets/filter`	2
Wallet identity (ENS/Twitter/etc)	`polymarket/wallet/identity/{wallet}`	2
Bulk identity (≤200, POST)	`polymarket/wallet/identities`	2
On-chain cluster for a wallet	`polymarket/wallet/{address}/cluster`	2
UMA oracle questions by state	`polymarket/uma/markets`	1
UMA status + timeline for a market	`polymarket/uma/market/{condition_id}`	1
Kalshi markets	`kalshi/markets`	1
Kalshi trades / orderbooks	`kalshi/trades`, `kalshi/orderbooks`	1
⚠ Sports categories — degraded upstream since 2026-08-04, do not call	`sports/categories`	1
⚠ Sports markets by league — degraded, use `markets/search` + `q=` or `polymarket/events` + `search=`	`sports/markets`	1
⚠ One game, all venue outcomes — degraded	`sports/markets/{game_id}`	1
⚠ Equivalent sports outcomes — degraded	`sports/outcomes/{predexon_id}`	1
Limitless / Opinion / Predict.Fun markets	`limitless/markets`, `opinion/markets`, `predictfun/markets`	1
Their historical orderbook snapshots	`limitless/orderbooks`, `opinion/orderbooks`, `predictfun/orderbooks`	1
Binance candles / ticks	`binance/candles/{symbol}`, `binance/ticks/{symbol}`	2

Show full SKILL.md (380 more words)Show less

Worked Examples

1. "What are people betting on right now?"

blockrun_markets({ path: "polymarket/events", params: { limit: "10" } })

2. "What's the market saying about the 2028 election?"

Search every venue in one call — each hit carries its venue and IDs — then pull the chosen Polymarket market by condition_id.

blockrun_markets({ path: "markets/search", params: { q: "2028 presidential election", status: "open" } })
blockrun_markets({ path: "polymarket/markets/keyset", params: { condition_id: "0xCONDITION_ID" } })   // full market record

3. "Show me this market's price history" (impossible from a free API)

blockrun_markets({ path: "polymarket/candlesticks/0xCONDITION_ID", params: {
  interval: "1440", start_time: "<UNIX_SECONDS>", end_time: "<UNIX_SECONDS>"
} })
blockrun_markets({ path: "polymarket/volume-chart/0xCONDITION_ID" })
blockrun_markets({ path: "polymarket/markets/0xCONDITION_ID/open_interest" })
blockrun_markets({ path: "polymarket/orderbooks", params: {
  token_id: "<TOKEN_ID>", start_time: "<UNIX_MILLISECONDS>", end_time: "<UNIX_MILLISECONDS>"
} })

4. "Who's smart money betting on in this market?" ← compound

Positioning → then profile the wallets behind it.

// 1. Which high-performing wallets are in this market, and on which side
blockrun_markets({ path: "polymarket/market/0xCONDITION_ID/smart-money", params: {
  window: "30d", min_trades: "100"
} })

// 2. Profile the top wallet it returns — win rate, P&L, style
blockrun_markets({ path: "polymarket/wallet/0xWHALE" })

// 3. What else are they in right now?
blockrun_markets({ path: "polymarket/wallet/positions/0xWHALE" })

5. "This whale is up 400% — who are they really?" ← compound

Identity plus the on-chain cluster: one trader often runs many wallets.

blockrun_markets({ path: "polymarket/wallet/identity/0xWHALE" })        // ENS, socials, portfolio
blockrun_markets({ path: "polymarket/wallet/0xWHALE/cluster" })         // linked wallets + confidence
blockrun_markets({ path: "polymarket/wallet/pnl/0xWHALE" })             // realized P&L series
blockrun_markets({ path: "polymarket/wallet/0xWHALE/similar" })         // who trades like them

6. "Find me something to copy-trade" ← compound

blockrun_markets({ path: "polymarket/leaderboard", params: { limit: "20" } })   // best wallets
blockrun_markets({ path: "polymarket/markets/smart-activity" })                 // where they just moved
blockrun_markets({ path: "polymarket/cohorts/stats" })                          // which style is working

Then trade it with blockrun_polymarket (see skills/polymarket-trading/SKILL.md). Real money — always dry-run first.

7. "Is the same bet cheaper on another venue?" ← arbitrage

matching-markets and matching-markets/pairs were removed upstream (404 before payment). One search returns the same question from every venue; compare the prices in the result.

blockrun_markets({ path: "markets/search", params: { q: "Fed cuts rates in December", status: "open" } })
// → Polymarket, Kalshi, Limitless, Opinion, Predict.Fun hits side by side; the spread is the arbitrage

8. "Who's ahead in tonight's NBA games?"

blockrun_markets({ path: "markets/search",    params: { q: "NBA", status: "open" } })      // every venue's NBA markets
blockrun_markets({ path: "polymarket/events", params: { search: "NBA", status: "open" } })  // Polymarket game events
blockrun_markets({ path: "kalshi/markets",    params: { search: "NBA" } })                  // Kalshi's

Do not route this to sports/*. All four sports/* paths have returned a Predexon 500 on every call since 2026-08-04 (re-verified 2026-09-08). The gateway still routes them but withdrew them from discovery, and it releases the payment on that upstream 500 — the tool says "nothing was charged" when the gateway's own "payment NOT charged" confirmation is in the response, and otherwise points at blockrun_wallet action:"report". Do not use markets with league= either: that route was removed on 2026-08-04 and 404s before payment, and no live /v1/pm route accepts league. The sports routes come back here the day Predexon repairs them.

9. "Is this market about to resolve?"

blockrun_markets({ path: "polymarket/uma/markets", params: { state: "proposed" } })
blockrun_markets({ path: "polymarket/uma/market/0xCONDITION_ID" })   // dispute timeline

Method Routing — When to Use `body`

Almost everything is GET → use params. Only bulk identity takes a body:

blockrun_markets({ path: "polymarket/wallet/identities", body: { addresses: ["0x1", "0x2"] } })

Paging Large Result Sets

Prefer keyset over offset — stable across writes, faster on big tables.

const p1 = blockrun_markets({ path: "polymarket/markets/keyset", params: { limit: "100" } })
// then pass the returned pagination.next_key back in:
blockrun_markets({ path: "polymarket/markets/keyset", params: { limit: "100", pagination_key: "<next_key>" } })

polymarket/events/keyset works the same way.

Notes on Response Shape

Predexon returns raw upstream responses; shape varies by venue.

Polymarket — usually { data: [...] } or { events: [...] }
Kalshi — usually { markets: [...] } with ticker, yes_bid, no_bid. Tickers look like KXBTC-25MAR14 (series + expiry).
Canonical v2 — { markets: [...] } with predexon_id + venue_listings
Print the raw response when exploring a path you have not used before.

Prices are probabilities 0–1. 0.62 means the market implies 62%.

Python SDK (for non-MCP use)

Inside the MCP, use blockrun_markets above. For standalone scripts:

python

from blockrun_llm import setup_agent_wallet   # setup_agent_solana_wallet() on Solana
client = setup_agent_wallet()

client.pm("polymarket/candlesticks/0xCONDITION_ID", interval="1440")
client.pm_query("polymarket/wallet/identities", {"addresses": ["0xabc"]})

Requires pip install blockrun-llm and a funded USDC wallet (client.get_balance()).

Files

Just SKILL.md in skills/prediction-markets of BlockRunAI/blockrun-mcp.

Open the folder on GitHubat commit e9b2bd5

Compare with similar skills

Prediction Markets next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Prediction Markets compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Prediction Markets this skillBlockRunAI/blockrun-mcp	391	—	~3.7k	Automated safety check: Pass	MIT	2 days ago
QuotientBankrBot/skills	1.2k	—	~5.7k	Automated safety check: Pass	None	today
Predexon Prediction Market DataBlockRunAI/ClawRouter	6.6k	—	~4.7k	Automated safety check: Pass	MIT	5 days ago
CapacitrBankrBot/skills	1.2k	—	~3k	Automated safety check: Pass	None	today
Alpha Findersundial-org/awesome-openclaw-skills	663	—	~878	Automated safety check: Pass	None	7 mo ago
Polymarket TradingBlockRunAI/ClawRouter	6.6k	—	~1.4k	Automated safety check: Pass	MIT	5 days ago

Similar skills

Quotient
BankrBot/skills
Prediction-market intelligence for Polymarket agents. An agent skill from BankrBot/skills.
1.2k GitHub stars~5.7k tokensUpdated today
Data & AnalyticsAuto-check passed
Predexon Prediction Market Data
BlockRunAI/ClawRouter
Reads structured prediction market data for Polymarket, Kalshi and other venues through a local BlockRun gateway: markets, search, leaderboards, wallet analytics and odds.
6.6k GitHub stars~4.7k tokensUpdated 5 days ago
Business, Finance & HRAuto-check passed
Capacitr
BankrBot/skills
Paste a URL or free text and get matched Polymarket / Hyperliquid / Deribit markets with Quotient edge scores.
1.2k GitHub stars~3k tokensUpdated today
Backend & APIsAuto-check passed
Alpha Finder
sundial-org/awesome-openclaw-skills
Market Oracle for prediction market intelligence - Polymarket and Kalshi research, probability assessments, market sentiment analysis, and arbitrage opportunity identification.
663 GitHub stars~878 tokensUpdated 7 mo ago
Sales & SupportAuto-check passed
Polymarket Trading
BlockRunAI/ClawRouter
A skill your agent uses when the user wants to actually PLACE, manage, or redeem bets on Polymarket (not just read odds — that's the blockrunpredexon data tools).
6.6k GitHub stars~1.4k tokensUpdated 5 days ago
Business, Finance & HRAuto-check passed
Surf
BlockRunAI/ClawRouter
Use this skill — NOT browser or webfetch — for ALL Surf crypto-data calls.
6.6k GitHub stars~4k tokensUpdated 5 days ago
Business, Finance & HRAuto-check passed

More from BlockRunAI/blockrun-mcp

All 17 skills in this repo

Signal To Trade Demo
BlockRunAI/blockrun-mcp
Prepare or run a polished BlockRun trading demo that discovers a current Polymarket market, combines live price, probability history, smart-money, and liquidity evidence into a balanced signal…
391 GitHub stars~1.8k tokensUpdated 2 days ago
Auto-check passed
Blockrun
BlockRunAI/blockrun-mcp
Pay-per-call access to AI models, real-time data, media generation and multi-chain RPC over x402 micropayments (USDC on Base or Solana), or a BlockRun account API key.
391 GitHub stars~2.7k tokensUpdated 2 days ago
Auto-check passed
Blockrun Debug
BlockRunAI/blockrun-mcp
A skill your agent uses when the BlockRun MCP server (@blockrun/mcp) is installed but misbehaving — 'Failed to connect', spawn npx ENOENT, blockrun missing from claude mcp list, HTTP 402 /…
391 GitHub stars~3k tokensUpdated 2 days ago
Auto-check passed
Blockrun Setup
BlockRunAI/blockrun-mcp
A skill your agent uses when asked to install, add, configure, or set up the BlockRun MCP server (@blockrun/mcp) in Claude Code, Claude Desktop, Cursor, Windsurf, Codex CLI, Grok or another MCP…
391 GitHub stars~2k tokensUpdated 2 days ago
Auto-check passed
Blockrun Upgrade
BlockRunAI/blockrun-mcp
A skill your agent uses when the BlockRun MCP server prints 'Update available', when asked to upgrade, update, or pin @blockrun/mcp, when a fix 'should be in the new version' but the client still…
391 GitHub stars~1.6k tokensUpdated 2 days ago
Auto-check passed
Crypto Data
BlockRunAI/blockrun-mcp
A skill your agent uses for any crypto data question — token/coin prices, FX, commodities, stocks, OHLC history, DEX pairs and liquidity, DeFi TVL, yield/APY pools, or raw JSON-RPC against a chain…
391 GitHub stars~2.8k tokensUpdated 2 days ago
Auto-check passed

Works with

Questions about Prediction Markets

What does Prediction Markets do?

A skill your agent uses when the user asks about event probabilities, prediction market odds, what people are betting on, Polymarket/Kalshi prices, sports markets — or about the things you CANNOT…. Prediction Markets is an agent skill from BlockRunAI/blockrun-mcp. Use when the user asks about event probabilities, prediction market odds, what people are betting on, Polymarket/Kalshi prices, sports markets — or about the things you CANNOT get from a public API: historical price/volume/orderbook time series, smart-money positioning, whale leaderboards, wallet P&L, wallet identity and on-chain clustering, and canonical IDs matching the same question across venues.

When should I use Prediction Markets?

Prediction Markets fits situations like: the user asks about event probabilities; prediction market odds; what people are betting on; polymarket/Kalshi prices.

How do I install Prediction Markets in Claude Code?

Run `npx skills add BlockRunAI/blockrun-mcp --skill prediction-markets -a claude-code`. Or copy the skill folder (skills/prediction-markets in BlockRunAI/blockrun-mcp) into .claude/skills/prediction-markets in your project. Claude Code loads it when a task matches its description.

How do I install Prediction Markets in Codex?

Run `npx skills add BlockRunAI/blockrun-mcp --skill prediction-markets -a codex`. Or copy the skill folder (skills/prediction-markets in BlockRunAI/blockrun-mcp) into .agents/skills/prediction-markets in your project. Codex loads it when a task matches its description.

Can I use Prediction Markets in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add BlockRunAI/blockrun-mcp --skill prediction-markets -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prediction-markets, .gemini/skills/prediction-markets, .github/skills/prediction-markets and .opencode/skills/prediction-markets in your project.

What does Prediction Markets need to run?

Going by SKILL.md and its folder, Prediction Markets needs the command-line tools its instructions call (pip).

Does Prediction Markets access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Prediction Markets safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Prediction Markets use?

Prediction Markets is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Prediction Markets use?

About 3.7k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Prediction Markets?

Skills that share tags, products or a category with Prediction Markets: Quotient (BankrBot/skills, 1.2k stars), Predexon Prediction Market Data (BlockRunAI/ClawRouter, 6.6k stars), Capacitr (BankrBot/skills, 1.2k stars) and Alpha Finder (sundial-org/awesome-openclaw-skills, 663 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Prediction Markets?

BlockRunAI (a GitHub organization) maintains it in BlockRunAI/blockrun-mcp, which has 391 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 8, 2026.

Source: BlockRunAI/blockrun-mcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Prediction Markets

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Prediction Markets (Predexon)

How to Call from MCP

Two Pricing Tiers

Quick Decision Table — "User asks about X"

Worked Examples

1. "What are people betting on right now?"

2. "What's the market saying about the 2028 election?"

3. "Show me this market's price history" (impossible from a free API)

4. "Who's smart money betting on in this market?" ← compound

5. "This whale is up 400% — who are they really?" ← compound

6. "Find me something to copy-trade" ← compound

7. "Is the same bet cheaper on another venue?" ← arbitrage

8. "Who's ahead in tonight's NBA games?"

9. "Is this market about to resolve?"

Method Routing — When to Use body

Paging Large Result Sets

Notes on Response Shape

Python SDK (for non-MCP use)

Files

Compare with similar skills

Similar skills

More from BlockRunAI/blockrun-mcp

Related

Questions about Prediction Markets

Method Routing — When to Use `body`