orcalayer-mcp
OfficialThis MCP server provides read-only Polymarket smart-money and whale analytics from OrcaLayer for use inside MCP clients.
Rank smart-money whales by P&L, win rate, volume, or trade count, optionally filtered by market category.
Analyze a wallet’s profile, lifetime P&L, win rate, profit factor, volume, and activity.
List a wallet’s largest open positions by current value.
Search markets and track smart-money flows, including whale counts on each side, volume, and time left.
Compare smart-money consensus on a market against its current price using head-count and capital-weighted views.
Get real-time smart-whale trade alerts, with Premium API key required.
Use ready-made prompts for wallet analysis, smart-money/price divergence, hedge checks, and territorial market review.
Read methodology, glossary, and API reference resources.
Run locally via stdio or use the hosted Streamable HTTP server; all tools are read-only.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@orcalayer-mcp Show me the current whale leaderboard on Polymarket."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
orcalayer-mcp
MCP server for the OrcaLayer Polymarket smart money and whale analytics API, inside Claude, Cursor and other MCP clients.
OrcaLayer is an analytics layer on top of Polymarket's free Data API: the official API returns raw trades, positions and P&L, and OrcaLayer returns what you would otherwise compute from them: win rate per resolved market, smart money, farmer and bot flags, smart money consensus on each market, and whale alerts. What it adds over the official API.
Two ways to use it:
Hosted, nothing to install:
https://orcalayer.com/mcp(Streamable HTTP). Add it as a connector in Claude (Settings → Connectors → Add custom connector, paste the URL) or in any client that supports remote MCP servers.Local (stdio):
uvx orcalayer-mcp, for Claude Desktop and other local clients.
Either way it is a thin wrapper over the orcalayer
Python SDK and exposes eight read-only tools:
Tool | What it does | Key |
| Rank wallets from the Smart Money set by P&L, win rate, volume or trade count | No |
| Wallet profit tracking: profile, P&L, market win rate, profit factor, rankings | No |
| A wallet's largest open positions | No |
| Track smart money flows: search markets and see how many Smart Money wallets hold each side | No |
| Smart-money consensus on one market vs its price (head-count + capital-weighted) | No |
| Real-time alerts on profitable wallets: live feed of smart-whale trades | Premium |
| Wallets ranked by realized P&L over the last 7 or 30 days (any window since June 2026) | Premium |
| Markets just proposed, disputed, resolved (with the winner) or reopened | Premium |
Public tools work anonymously. whale_alerts, pnl_leaderboard and resolution_events need a Premium API key
(get one): on the hosted server send it as the
Authorization: Bearer <key> request header (clients that support request
headers for a connector), on the local server set the ORCALAYER_API_KEY
environment variable. Without a key the tool answers with a short notice, not
an error.
Every tool carries readOnlyHint: true: nothing is created, changed or
deleted on your behalf. Data is read from the OrcaLayer API only.
Each result carries a short notes block that defines its fields, so a model
comparing two tools never meets two different numbers under one name:
market_win_rate (share of resolved markets won) has the same basis in
leaderboard and wallet_overview; profit_factor is capped at 99.99 on the
leaderboard (profit_factor_capped) and uncapped net in the overview;
indexed_volume_usd is the volume of fills in OrcaLayer's index, not
Polymarket's figure; Smart Money counts are wallets, whatever their size.
New (2026-07-22): the Premium SSE stream (
/api/public/v1/live/trades) now carriessettlement_type(MINT/MERGE/COMPLEMENTARY/null) on every event — live-derived settlement mechanics, shadow-verified 100.000% accurate on MINT/MERGE. It describes how the match settled, not trader intent (~80% of all fills settle as MINT;null= honest refusal, not "not a mint"). Details: theorcalayer://api-referenceresource or orcalayer.com/docs/api.
Prompts
Ready-to-use prompts for common analytics scenarios:
Prompt | What it does |
| Full wallet analysis — smart money or farmer? |
| Markets where smart money disagrees with the current price |
| Whether a wallet's profit was real alpha or a hedge structure |
| Ukraine territorial markets with ISW frontline overlay |
In Claude Desktop, pick a prompt from the prompt menu (the + / slash-command
picker) — each one orchestrates the tools above for you.
Related MCP server: Polymarket MCP Server
Resources
Read-only context the model can pull directly — no tool call needed:
Resource URI | Content |
| How smart money is filtered from farmers, hedgers and market-makers |
| Prediction-markets glossary |
| OrcaLayer REST API reference (endpoints, auth, rate limits) |
Use with Claude Desktop
Add this to your claude_desktop_config.json
(%APPDATA%\Claude\claude_desktop_config.json on Windows,
~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"orcalayer": {
"command": "uvx",
"args": ["orcalayer-mcp"]
}
}
}The public tools work as-is. For the Premium tools (whale_alerts, pnl_leaderboard, resolution_events), add your
API key (get one):
{
"mcpServers": {
"orcalayer": {
"command": "uvx",
"args": ["orcalayer-mcp"],
"env": { "ORCALAYER_API_KEY": "sk_orca_your_key_here" }
}
}
}Restart Claude Desktop after editing the config.
Use the hosted server
The same eight tools, prompts and resources are served at
https://orcalayer.com/mcp over Streamable HTTP. No account is needed for the
public tools. In Claude: Settings → Connectors → Add custom connector → paste
the URL. For the Premium tools, send your Premium key as the
Authorization: Bearer <key> request header where your client supports
connector headers; keys are never accepted in the URL.
Self-host over HTTP
pip install orcalayer-mcp
orcalayer-mcp --http --host 127.0.0.1 --port 8020 --path /mcpThe server is stateless and answers plain JSON, so any reverse proxy with TLS
in front of it will do (forward POST /mcp to 127.0.0.1:8020/mcp). The
ORCALAYER_MCP_HTTP=1, ORCALAYER_MCP_HOST, ORCALAYER_MCP_PORT and
ORCALAYER_MCP_PATH environment variables are equivalent to the flags.
ORCALAYER_MCP_ANON_BASE_URL optionally routes anonymous calls to a different
API host (the hosted server points it at its local backend); calls that carry
a key always go to https://orcalayer.com. Put your own per-client rate limit
in the proxy: the server itself does not limit callers.
License
MIT. See LICENSE.
Data is provided for informational purposes only and is not financial advice.
mcp-name: io.github.orcalayer/orcalayer-mcp
Available Tools
6 toolsleaderboardAInspect
Rank the most successful Polymarket whales (smart-money traders).
Use this to find top traders by realized profit, win rate, or volume — optionally narrowed to one market category. Returns each whale's wallet, name, total P&L, win rate, profit factor and resolved-market count.
Args: sort: Ranking key — "pnl" (default), "win_rate", "volume" or "trades". category: Restrict to one category, e.g. "Crypto", "Sports", "Politics", "Geopolitics", "Economics", "Tech/AI". None = all. filter: "smart" (curated profitable whales, default) or "all". limit: How many whales to return (1–100).
Inputs: sort, limit, filter, category.
market_consensusAInspect
Smart-money consensus on one Polymarket market versus its current price.
Shows where smart money stands on a market: how many profitable smart-money whales hold YES vs NO, how much capital each side has invested, the current market price, and the divergence between smart-money positioning and that price. Use it to answer "what does smart money think about this market?" and to spot markets where smart money disagrees with the crowd.
Two consensus reads are returned side by side and can disagree:
head_count (one whale = one vote) and capital_weighted (dollars
invested per side). Head-count is the weaker signal — a $5 wallet counts
the same as a $500K one — so when the two disagree, trust the capital
split more. On cheap longshots (YES under ~15 cents) head-count skews
YES structurally. Divergence from price is positioning information, not
proof the market is mispriced; never present it as "the market is wrong".
Args: market: Market id, Polymarket slug or URL, or 0x condition id.
Inputs: market (required).
marketsAInspect
Search Polymarket markets, optionally where smart whales are clustering.
Use this to track smart money flows: find markets by topic and surface where smart money is accumulating right now. Returns each market's question, YES price, smart-whale counts on each side, volume and days left.
Args: q: Free-text query; also accepts a Polymarket URL or slug. "" browses. category: One of "Crypto", "Geopolitics", "Sports", "Politics", "Economics", "Tech/AI". None = all. min_volume: Minimum market volume in USD. min_whales: Minimum number of smart whales active in the market. limit: How many markets to return (1–100).
Inputs: q, limit, category, min_volume, +1 more.
wallet_overviewAInspect
Summarize one wallet's trading profile and performance.
Wallet profit tracking for any Polymarket address: lifetime P&L, win rate, ROI-style stats (profit factor), volume and activity. Accepts a 0x wallet address or an OrcaLayer nickname. Returns a compact summary — identity, lifetime activity, and P&L stats — rather than the full raw record, so it stays readable for heavy wallets.
If the wallet's stats are still being computed server-side, this returns
a {"status": "computing", "retry_after_seconds": N} notice instead of
data — call the tool again after that delay.
Args: address: 0x wallet address or OrcaLayer nickname.
Inputs: address (required).
wallet_positionsAInspect
List a wallet's largest open positions by current value.
Accepts a 0x wallet address or an OrcaLayer nickname. Returns the positions with the largest current value first, in a compact form, plus a count of how many more are not shown.
Args: address: 0x wallet address or OrcaLayer nickname. limit: How many positions to return (1–50). The wallet may hold more; the response reports how many were omitted.
Inputs: address (required), limit.
whale_alertsAInspect
Recent trades by smart-money whales — real-time alerts on profitable wallets (Premium).
Returns whale trades in the last minutes over min_usd in size:
who traded, buy/sell, side, amount, price and the market. Use it to get
alerts when profitable Polymarket wallets open or close positions.
Requires a Premium API key set via the ORCALAYER_API_KEY environment variable. Without a key this returns a short notice on how to get one (it does not call the API and is not an error).
Args: minutes: Lookback window in minutes (max 1440 = 24h). min_usd: Minimum trade size in USD. category: Restrict to one market category. None = all. limit: How many alerts to return (1–100).
Inputs: limit, min_usd, minutes, category.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool targets a clearly distinct slice of the domain: ranking whales, summarizing a wallet, listing positions, searching markets, reading market consensus, and streaming whale trades. Even the two wallet-focused tools are cleanly separated by performance summary versus open positions.
All tool names follow the same lowercase snake_case noun-phrase pattern, e.g. wallet_overview, wallet_positions, market_consensus, whale_alerts. There is no mixing of verb styles or casing conventions, so an agent can predict related tool names.
Six tools is a well-scoped size for a Polymarket smart-money analytics server. Each tool covers a meaningful capability without redundancy, and the count is comfortably within the ideal range.
The set covers the core analytics workflow: discovering top whales, inspecting a wallet, seeing current positions, finding markets with whale activity, checking consensus on a single market, and following live whale trades. A minor gap is the lack of a wallet-level historical trade or a per-market price history tool, but agents can work around those with the provided surface.
Maintenance
Related MCP Connectors
Polymarket wallet intelligence for AI agents: scored wallets, insider signals, whale flow.
Live Polymarket data for agents: markets, insider-scored whale trades, leaderboards, wallet P&L
Polyrank MCP server: rank Polymarket traders by forecasting skill (calibration, Brier score, edge vs. market price) and check any wallet's record from Claude, Cursor or any MCP client. 17 tools free with no key. Sign in (OAuth) for the rest; the Ranking Builder, full metrics and the AI Lab (backtest, paper-trade copy strategies) need a paid plan.
Polymarket & Kalshi live prediction market odds aggregator and cross-venue arbitrage scanner MCP.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol (MCP) server for Polymarket prediction markets, providing real-time market data, prices, and AI-powered analysis tools for Claude Desktop integration.48MIT
- AlicenseBqualityBmaintenanceEnables Claude to autonomously trade, analyze, and manage positions on Polymarket prediction markets with 45 comprehensive tools including market discovery, real-time monitoring, portfolio management, and AI-powered trading recommendations with enterprise-grade safety features.25752MIT
- AlicenseNot gradedqualityDmaintenanceEnables Claude to autonomously trade, analyze, and manage positions on Polymarket prediction markets with 45 comprehensive tools covering market discovery, analysis, trading execution, portfolio management, and real-time monitoring with enterprise-grade safety features.MIT
- AlicenseAqualityDmaintenancePolymarket prediction markets for Claude — market search, order books, price history, and a liquidity-rewards scanner. Credential-free.630 npmMIT