A professional-grade MCP server providing structured access to Predict.fun prediction market data, yield mechanics, and trader behavioral analysis via The Graph.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install predictfun-mcp
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install predictfun-mcp using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Predict.fun MCP?
Predict.fun MCP is a powerful extension for AI agents that bridges the gap between LLMs and real-time decentralized finance data on the BNB Chain. By leveraging this Openclaw Skills integration, developers can equip their agents with the ability to query complex subgraphs for market analysis, liquidity depth, and risk assessment.
The skill provides a specialized interface to interact with the Predict.fun ecosystem, including orderbook data, position tracking, and Venus Protocol yield stats. It goes beyond simple data fetching by offering behavioral meta-tools that can classify traders into archetypes like whales or yield farmers, making it an essential tool for automated market research and DeFi strategy development.
Predict.fun MCP Use Cases
- Monitor real-time platform metrics such as total volume and open interest across the BNB Chain.
- Perform deep-dive trader profiling to analyze P&L, payout history, and risk tolerance.
- Identify high-conviction whale movements and track significant position changes in specific markets.
- Audit yield generation mechanics via Venus Protocol deposits and redemption tracking.
- Automate market structural analysis to find opportunities based on resolution latency and tail risk.
How Predict.fun MCP Works
- The user or AI agent triggers a tool call within the Openclaw Skills environment using the Predict.fun MCP.
- The server authenticates with The Graph Gateway using the provided
GRAPH_API_KEY. - Depending on the request, the server routes the query to one of three specialized subgraphs: predictfun-orderbook, predictfun-positions, or predictfun-yield.
- Raw GraphQL data is fetched and processed into a structured, LLM-friendly format.
- The AI agent interprets the data to provide insights, generate reports, or execute further logic based on the market conditions.
Predict.fun MCP Setup
To get started with this skill, you must have Node.js (version 18 or higher) installed and an API key from The Graph Studio.
# Set your environment variable and run the server via npx
export GRAPH_API_KEY=your-api-key-here
npx predictfun-mcp
For persistent usage, ensure GRAPH_API_KEY is added to your local environment configuration.
Predict.fun MCP Data Schema & Taxonomy
The Predict.fun MCP organizes data through three primary subgraph entities to ensure comprehensive coverage of the prediction market lifecycle:
| Subgraph | Data Focus |
|---|---|
| predictfun-orderbook | Market metadata, bid/ask spreads, trade counts, and volume. |
| predictfun-positions | Trader balances, individual P&L, open interest, and holder rankings. |
| predictfun-yield | Venus Protocol integration stats, redemptions, and yield rewards. |
All tools return JSON objects optimized for token efficiency in AI conversations.
Predict.fun MCP Advanced Features
- Behavioral Archetype Scanning: Use
find_trader_personato automatically categorize addresses as snipers, arbitrageurs, or early movers. - Structural Market Filtering: Query markets based on specific technical characteristics like oracle type or liquidity depth.
- Custom GraphQL Support: The
query_subgraphtool allows power users to bypass pre-defined tools and execute direct, complex queries. - Multi-Transport Support: Supports both standard MCP communication and local HTTP server mode via SSE for custom integrations.
SKILL.md
Loading
Related Openclaw Skills
Open Ontologies
A professional-grade toolkit for AI-native ontology engineering, enabling automated generation, validation, and lifecycle management of RDF and OWL knowledge graphs.
LlamaParse
LlamaParse is a state-of-the-art document parsing skill designed to transform complex PDFs, images, and spreadsheets into structured, LLM-ready data.
Search Bot
A high-performance real-time web search skill that delivers ranked results and AI-generated summaries for up-to-date information retrieval.
Git Workflows Pro
An expert-level git management skill designed to handle complex history surgery, repository architecture, and emergency recovery with a safety-first philosophy.
Karma Funding Program Finder
A professional-grade search skill for discovering grants, bounties, and funding opportunities via the Karma registry.
AI Merchant Search Optimizer
A professional optimization skill that helps local businesses appear in AI-driven search recommendations through high-quality content generation.
Featured*
