Polytoolhub logoPolytoolhubSearch tools
← SDKs & libraries

SDK

dr-manhattan

Use a common Python interface for prediction-market discovery, orders, positions and streaming, with optional MCP access.

3.5/ 5Editorial rating0 user reviews
View repositorygithub.com
Available on
Python, MCP, WebSocket
Pricing
The repository can be installed and run locally without a listed software subscription

Screenshots and interface

Product preview1 / 2

Unified exchange interface and adapter architecture.

What is dr-manhattan?

Dr. Manhattan is a CCXT-style integration library for Polymarket, Kalshi, Opinion, Limitless and Predict.fun. It standardizes common models and methods while retaining venue-specific configuration. A strategy base class, order tracking and MCP server sit above the exchange adapters.

Who it is for

  • Python developers integrating multiple prediction venues
  • Teams building their own strategy and order services
  • Technical users connecting market tools to an MCP client

Features and coverage

Available on
Python, MCP, WebSocket
Markets & venues
Polymarket, Kalshi, Opinion, Limitless, Predict.fun
  • Common exchange interface

    Fetch markets, balances, positions and books through shared abstractions.

  • Order methods

    Create and cancel orders with venue-specific parameters.

  • Real-time transport

    Use supported WebSocket adapters.

  • Typed models

    Work with market, order, position and order-book objects.

  • Strategy base class

    Implement a recurring strategy around the exchange client.

  • Order tracking

    Log order events and handle standardized errors.

  • MCP deployment

    Run the local server or use the separately configured hosted route.

Workflows with dr-manhattan

Build a cross-venue reader

Create public exchange instances, fetch a small market set and retain the native identifiers inside the common model.

Add a strategy

Implement the strategy callback, configure one venue and use explicit order parameters and tracking.

Expose tools to an AI client

Install the MCP dependencies, configure a local server and choose the credentials appropriate to the operations required.

Pricing and total cost

The repository can be installed and run locally without a listed software subscription. Venue access, credentials, infrastructure and third-party services have separate requirements.

Getting started

Before you start: The factory key for Predict.fun is predictfun, while its low-level venue ID is predict.fun.

  1. Create a Python environment and install the repository’s supported dependencies.
  2. Start with a public exchange instance or factory validation disabled.
  3. Fetch markets before configuring private methods.
  4. Set venue-specific credentials for account actions.
  5. For MCP, install the extra dependencies and point the client to the correct environment.

Useful links

    What to check

    • The factory key for Predict.fun is predictfun, while its low-level venue ID is predict.fun.
    • The remote MCP route documents Polymarket trading only; its other venues are read-only.
    • Shared method names do not remove venue-specific signing and account configuration.
    • Legacy examples may use collateral or client conventions that need checking against current official venue documentation.

    A closer look

    Ratings & reviews

    Write a review
    Editorial rating
    3.5/ 5
    0 user reviews
    Polytoolhub editorial

    Our take on dr-manhattan

    A common Python interface can reduce repeated venue integration work. Signing, execution support and some legacy examples still require venue-specific verification.

    Based on documented features, setup and access terms. How we rate

    User reviews 0

    The main score switches to user ratings after 5 published reviews.

    Be the first to share your experience

    A specific example helps the next person choose the right tool.

    Write a review

    How was your experience with dr-manhattan?

    Share what you used, what worked and what could be better. We confirm your email and review the submission before publishing.

    To submit a review, email info@polytradingbot.com with the tool name, your rating and your experience. Enable JavaScript to prepare a draft here.

    Related tools

    Browse category
    Polymarket Python SDK: Official Python SDK installation and quickstart.
    Polymarket Python SDK
    SDK4.0Editorial

    The official Python client for typed Polymarket data, sync or async account workflows, streaming and notebook-friendly analysis.

    • Language Python

    The official Python integration.

    PMXT open-source SDK: PMXT repository overview and supported venue families.
    PMXT open-source SDK
    SDK3.5Editorial

    Use Python or TypeScript clients with a common prediction-market interface, targeting hosted PMXT or a locally run backend.

    • Language Python · TypeScript

    Another common client layer across venues.

    CloddsBot: Project overview with the provider’s embedded WebChat preview.
    CloddsBot
    Research tool3.0Editorial

    Run a self-hosted conversational trading terminal with Polymarket discovery, strategy tools, messaging integrations and configurable account access.

    • Access Web · Telegram · Discord · MCP

    A broader conversational terminal.

    Frequently asked questions about dr-manhattan

    Can I read public markets without a private key?

    Yes. Public exchange instances and the documented read-only factory path support discovery.

    Is every venue available for remote MCP trading?

    No. The remote server documents Polymarket trading and read-only access elsewhere.

    Can I add an exchange?

    The repository provides an Exchange base class and registration pattern.

    Does it include a strategy abstraction?

    Yes. The Strategy base class works with the exchange client and order tracker.