Polymarket Predictions MCP
Enables real-time access to Polymarket prediction market odds, allowing AI agents to retrieve events, markets, and search for predictions with formatted outputs.
README
Polymarket Predictions MCP
An MCP server that delivers real-time market odds from Polymarket, enabling AI agents and analysts to access, compare, and act on decentralized prediction data.
Features
- Event Retrieval: Fetch Polymarket events with details (
title,description,endDate,volume) and associated markets in a tabulated format. - Market Retrieval: Retrieve markets with key fields (
question, zippedoutcomesandoutcomePrices,endDate,volume,closed) in a table. - Event Search: Search for events using Polymarket's
/public-searchendpoint with comprehensive query parameters. - Prompt Support: Includes a prompt template for analyzing specific markets.
- Formatted Outputs: Uses
tabulatefor clean, readable table outputs and handles JSON parsing for outcomes and prices.
Installation
Prerequisites
- Python 3.10 or higher
- uv (recommended) or
pipfor dependency management
Setup
-
Clone the Repository:
git clone https://github.com/kukapay/polymarket-predictions-mcp.git cd polymarket-predictions-mcp -
Install Dependencies: Using
uv:uv syncOr using
pip:pip install mcp[cli] httpx tabulate -
Install to Claude Desktop:
Install the server as a Claude Desktop application:
uv run mcp install main.py --name "Polymarket Predictions"Configuration file as a reference:
{ "mcpServers": { "Polymarket Predictions": { "command": "uv", "args": [ "--directory", "/path/to/polymarket-predictions-mcp", "run", "main.py" ] } } }Replace
/path/to/polymarket-predictions-mcpwith your actual installation path.
Usage
The server exposes three tools and one prompt:
Tools
-
get_events: Fetches a list of Polymarket events with details and their associated markets.- Parameters:
limit: Number of events (default: 10)offset: Pagination offset (default: 0)order: Fields to order by (e.g.,volume,markets.volume)ascending: Sort order (default:False)id: List of event IDsslug: List of event slugstag_id: Tag ID filterclosed: Filter for closed events (default:False)
- Output: Formatted string with event details (
title,description,endDate,volume) and a table of markets (question,closed,volume,outcomes,outcomePrices).
Example:
-
Prompt
Show me the top 2 Polymarket events by volume, including only open events, with their market details.
-
Sample Output:
## US Presidential Election 2024 Closed: False | End Date: 2024-11-05 | Volume: $1000000 Predict the outcome of the 2024 US Presidential Election... Markets: +--------------------------------------------------+----------+-----------+-------------------+-------------------+ | Question | Closed | Volume | Outcomes | Outcome Prices | +==================================================+==========+===========+===================+===================+ | Who will win the 2024 US Presidential Election? | False | $500000 | Biden, Trump | 0.45, 0.55 | +--------------------------------------------------+----------+-----------+-------------------+-------------------+ | Will Biden win the 2024 election? | False | $200000 | Yes, No | 0.40, 0.60 | +--------------------------------------------------+----------+-----------+-------------------+-------------------+ ## Super Bowl LVIII Closed: True | End Date: 2024-02-11 | Volume: $500000 Predict outcomes related to Super Bowl LVIII... Markets: +--------------------------------------------------+----------+-----------+-------------------+-------------------+ | Question | Closed | Volume | Outcomes | Outcome Prices | +==================================================+==========+===========+===================+===================+ | Who will win Super Bowl LVIII? | True | $300000 | Chiefs, 49ers | 0.60, 0.40 | +--------------------------------------------------+----------+-----------+-------------------+-------------------+
- Parameters:
-
get_markets: Fetches a list of Polymarket markets with specified fields.- Parameters:
limit: Number of markets (default: 10)offset: Pagination offset (default: 0)order: Fields to order by (e.g.,volume)ascending: Sort order (default:False)id: List of market IDsslug: List of market slugscondition_ids: List of condition IDsclosed: Filter for closed markets (default:False)
- Output: Table with
question,options(zippedoutcomesandoutcomePrices),endDate,volume, andclosed.
Example:
-
Prompt:
List the top 2 Polymarket markets by trading volume, showing only open markets with their outcomes and prices.
-
Sample Output:
+--------------------------------------------------+-------------------------+---------------------+-----------+----------+ | Question | Options | End Date | Volume | Closed | +==================================================+=========================+=====================+===========+==========+ | Who will win the 2024 US Presidential Election? | {"Biden": 0.45, "Trump": 0.55} | 2024-11-05 | $500000 | False | +--------------------------------------------------+-------------------------+---------------------+-----------+----------+ | Will Bitcoin reach $100K by end of 2024? | {"Yes": 0.30, "No": 0.70} | 2024-12-31 | $200000 | False | +--------------------------------------------------+-------------------------+---------------------+-----------+----------+
- Parameters:
-
search_events: Searches for events using the/public-searchendpoint.- Parameters:
q: Search query (required)cache: Use cached resultsevents_status: Filter by event statuslimit_per_type: Results per type (default: 10)page: Page number for paginationevents_tag: List of event tagskeep_closed_markets: Number of closed marketssort: Field to sort byascending: Sort ordersearch_tags: Include tags in searchsearch_profiles: Include profiles in searchrecurrence: Filter by recurrence typeexclude_tag_id: List of tag IDs to excludeoptimized: Use optimized search
- Output: Formatted string with event details and markets tables, similar to
get_events.
Example:
-
Prompt:
Search for Polymarket events about 'Bitcoin', filtering for active events with the 'crypto' tag, sorted by volume in ascending order.
-
Sample Output: (Similar format to
get_eventsoutput, with Bitcoin-related events and markets)
- Parameters:
Prompt
-
analyze_market: A prompt template for analyzing a specific market by slug, encouraging use of tools to fetch details and provide insights on probabilities, volume, and outcomes.Example:
-
Prompt:
Analyze the Polymarket prediction market for 'us-presidential-election-2024' and provide insights on its probabilities, trading volume, and potential outcomes.
-
Command:
analyze_market(market_slug="us-presidential-election-2024")
-
License
This project is licensed under the MIT License. See the LICENSE file for details.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.