Mantis

io.github.Alfred768Published by GitHub account Alfred768v1.1.4Updated Oct 24, 2026

Cross-venue prediction market routing for AI agents with arbitrage, quotes, history, and signals.

VerifiedStreamable HTTPWeb executableFinance

Overview

AI-generated overview

Lets an assistant find and compare prediction markets across venues, check arbitrage, and get trade links.

What you can do
Provides cross-venue prediction-market tools: it maps a natural-language question to the best matching market and returns probability, liquidity and any arbitrage between venues. It also offers live quotes with order-book depth and size-aware slippage, historical OHLCV candles exportable as CSV or Parquet, and a search for demand with no existing market.
When to use it
Use it when an assistant needs prediction-market probabilities, price comparisons across venues such as Polymarket and Kalshi, or cross-venue arbitrage checks. Also useful for spotting topics users search for that have no market yet.
Requirements
Remote HTTP endpoint; nothing to install locally. An Authorization header is required, though the input does not describe the credential itself. Network access is needed.
Before you install
The trade link from execute_url embeds a referral code, so the platform earns commission; disclose this to the user. The server only returns links, and the actual trade happens on an external venue, so money is at stake. An Authorization header credential must be supplied and kept private.

Installation

In SourceWeft

  1. Open Mantis in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.Alfred768%2Fmantis/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "mantis": {
      "type": "http",
      "url": "https://mantiss.store/mcp"
    }
  }
}

README

This repository has no README.

Tools

6

route_market

Find the best prediction market for a natural-language question or trading intent. Returns the best cross-venue match, current probability, liquidity, and any arbitrage opportunity between venues.

Parametersqrequired

get_arbitrage

Find live cross-venue arbitrage opportunities — markets where the same event trades at different prices on Polymarket vs Kalshi vs other venues. Can also estimate fee-normalized net spread for a position size.

Parametersvenue_avenue_binclude_feesposition_sizemin_spread_pct

execute_url

Get a deep link URL to place a trade on the best venue for a given market. The URL has a referral code embedded so the platform earns commission. Call this to get the URL, then direct the user to open it.

Parameterssideamountsourcemarket_idroute_querycanonical_id

get_quote

Get the live probability, liquidity, and volume for a prediction market across all venues. Can also return venue order book depth and size-aware VWAP/slippage estimates.

Parameterssizemarket_idcanonical_id

get_history

Get historical OHLCV-style prediction market candles over a time range, including the latest stored depth snapshot within each bucket when available. Can also export CSV text or base64-encoded Parquet.

Parameterstorequiredfromrequiredvenueformatmarket_idgranularitycanonical_id

get_unmet_demand

Find questions that users are searching for but no prediction market exists. Useful for discovering new market creation opportunities or identifying emerging topics with real trading interest.

Parametersdayslimit

Version history

1
  1. v1.1.4LatestSep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.