Polymarket Intel
@aemery13
About Polymarket Intel
An MCP server and REST API that classifies Polymarket wallets as human or bot, scores their trading edge from 0–10, and streams their current open positions. Built for AI agents on copy-trading and signal-following stacks.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"polymarket-intel": {
"command": "python",
"args": [
"-m",
"venv",
".venv",
"&&",
"source",
".venv/bin/activate"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Polymarket Intel?
Polymarket Intel is an MCP server and REST API that classifies Polymarket wallets as human or bot, scores their trading edge from 0–10, and streams their current open positions. It is built for AI agents on copy-trading and signal-following stacks.
How to use Polymarket Intel?
Install via pip install polymarket-intel-mcp then run polymarket-intel-mcp, or call the hosted REST API directly with curl https://polymarket-intel-production.up.railway.app/.... You can also clone the repo, install dependencies, and use the CLI (python scripts/analyze_wallet.py), the FastAPI REST API (uvicorn api.main:app --reload), or the MCP server (python mcp_server/server.py). The MCP server exposes four tools: score_polymarket_wallet, score_polymarket_user, get_polymarket_leaderboard, and get_open_positions.
Key features of Polymarket Intel
- Classifies wallets as human, bot, or insufficient_data with confidence score
- Scores trading edge from 0–10 gated on net realised PnL
- Streams current open positions refreshed every 30 seconds
- Provides historical score time series via daily snapshots
- Distributed as MCP server, REST API, and hosted MCP endpoint
- Includes PnL reconstruction from raw trade and redeem activity
Use cases of Polymarket Intel
- AI agents filtering which Polymarket wallets to copy-trade
- Signal-following stacks evaluating trader edge over time
- Dashboards or analytics tools querying wallet classification and position history
- Research projects analyzing leaderboard wallet behaviour and bot detection
FAQ from Polymarket Intel
How does Polymarket Intel compare to other Polymarket MCP servers?
Polymarket Intel focuses on wallet intelligence (human vs bot, edge score, open positions) for deciding whose signals to follow, whereas other servers provide market data, pricing/slippage, or autonomous trading.
What are the runtime requirements?
Python via pip install polymarket-intel-mcp. A Postgres-compatible database (Supabase) is optional; without it the API uses an in-memory repository and history endpoints return empty results.
Where are scores and history stored?
By default in memory. For persistence, set up Supabase with the provided schema and the snapshot job writes wallet scores, open position snapshots, and leaderboard snapshots daily at 08:00 UTC.
What are the known limits on data freshness?
Open positions refresh every 30 seconds; polling below 10 seconds does not return fresher data due to Polygon block time (~2s) and Polymarket activity index lag. Score endpoint writes to history at most once per wallet per hour.
What transports and authentication are supported?
MCP uses stdio transport; the REST API serves HTTP. No authentication or API keys are mentioned in the README.
Frequently asked questions
How does Polymarket Intel compare to other Polymarket MCP servers?
Polymarket Intel focuses on wallet intelligence (human vs bot, edge score, open positions) for deciding whose signals to follow, whereas other servers provide market data, pricing/slippage, or autonomous trading.
What are the runtime requirements?
Python via `pip install polymarket-intel-mcp`. A Postgres-compatible database (Supabase) is optional; without it the API uses an in-memory repository and history endpoints return empty results.
Where are scores and history stored?
By default in memory. For persistence, set up Supabase with the provided schema and the snapshot job writes wallet scores, open position snapshots, and leaderboard snapshots daily at 08:00 UTC.
What are the known limits on data freshness?
Open positions refresh every 30 seconds; polling below 10 seconds does not return fresher data due to Polygon block time (~2s) and Polymarket activity index lag. Score endpoint writes to history at most once per wallet per hour.
What transports and authentication are supported?
MCP uses stdio transport; the REST API serves HTTP. No authentication or API keys are mentioned in the README.
Basic information
More Other MCP servers
Inbox Zero AI MCP
elie222The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.
Codelf
unbugA search tool helps dev to solve the naming things problem.
🪟 Windows-MCP
CursorTouchMCP Server for Computer Use in Windows
IDA Pro MCP
mrexodiaAI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.
Peekaboo MCP – lightning-fast macOS screenshots for AI agents
steipetePeekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.
Comments