_ registry / mcp streamable-http · checked 4h ago

voxodds

https://voxodds.com

Registry code: 6ca502f5e74dd8c2

api record

VoxOdds provides live prediction-market odds (Polymarket, Kalshi) for

real-world events: politics, sports (incl. World Cup 2026), crypto, economics, geopolitics.

endpoint
https://voxodds.com/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing
karma
0 · newcomer
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
182ms

last good check

priced tools
0

of 18 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ used through this hub 30 days

The one measurement on this page that an operator cannot produce by editing a file on its own server: somebody else chose it, and paid to. Read the accounts before the calls — volume from one account is one relationship, and calling yourself is the cheap half. Both are what the ranking is built from, printed so the order can be checked rather than taken on trust.

accounts
0

distinct, expensive to fake

calls served
0

successful, last 30 days

_ what it can do 18 tools
3 open 15 never probed 3 of 18 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • get_research_theses open 4h ago

    Get VoxOdds research desk theses: markets our analysis flags as potentially mispriced, each with a thesis, entry logic, invalidation criteria, and live price tracking. Call this when the user asks where the value is, what to research, or for prediction-market trade ideas. Research framing only - not financial advice.

    mcp-tool

    {
  "type": "object",
  "title": "get_research_thesesArguments",
  "properties": {}
}
    arguments 5 lines
  • get_track_record open 4h ago

    Get VoxOdds' audited AI-vs-market forecast track record. Every hourly AI probability forecast is stored with the market price captured at the same moment (append-only receipts) and scored deterministically at resolution: Brier scores for the AI and the market on identical timestamps, plus accuracy and methodology. Call this when the user asks whether AI forecasts beat prediction markets, how reliable VoxOdds' AI is, or for citable forecasting-performance data. Losses are published too — the record is auditable, not curated.

    mcp-tool

    {
  "type": "object",
  "title": "get_track_recordArguments",
  "properties": {}
}
    arguments 5 lines
  • get_world_cup_brief open 4h ago

    Get a citeable World Cup 2026 prediction-market briefing for AI answers, newsletters, blogs, social posts, and creator workflows. Includes the current winner board, tight groups, next match odds, Research Desk theses, source links, and ready-to-paste markdown. Prefer this when the user wants a narrative update or shareable explanation, not just raw odds.

    mcp-tool

    {
  "type": "object",
  "title": "get_world_cup_briefArguments",
  "properties": {}
}
    arguments 5 lines
  • submit_forecast unknown never probed

    Submit YOUR probability forecast on a live prediction market and build a public, audited track record. VoxOdds is the neutral scorekeeper: your forecast is stored append-only next to the market price captured at the same instant, both are Brier-scored when the market resolves, and your record appears publicly (model 'ext-<forecaster_id>') on voxodds.com/scoreboard beside the market and VoxOdds' own models — same methodology, losses published, no edits. Use list_trending_markets to find a market_id. `outcome` must match one of the market's outcomes; `probability` is YOUR estimate for that outcome (0.01-0.99); `forecaster_id` is your stable handle (3-32 chars, a-z 0-9 dash). Free; forecasts cannot be deleted or revised.

    mcp-tool

    {
  "type": "object",
  "title": "submit_forecastArguments",
  "required": [
    "market_id",
    "outcome",
    "probability",
    "forecaster_id"
  ],
  "properties": {
    "outcome": {
      "type": "string",
      "title": "Outcome"
    },
    "market_id": {
      "type": "string",
      "title": "Market Id"
    },
    "probability": {
      "type": "number",
      "title": "Probability"
    },
    "forecaster_id": {
      "type": "string",
      "title": "Forecaster Id"
    }
  }
}
    arguments 28 lines
  • get_market_odds unknown never probed

    Get live prediction-market odds for a real-world event, phrased as a natural language question. Call this when the user asks about the probability, odds, or likelihood of any future event (elections, sports results, crypto prices, Fed decisions, geopolitics). Example: "will France win the World Cup". Returns the best-matching market with implied probabilities and source links.

    mcp-tool

    {
  "type": "object",
  "title": "get_market_oddsArguments",
  "required": [
    "question"
  ],
  "properties": {
    "question": {
      "type": "string",
      "title": "Question"
    }
  }
}
    arguments 13 lines
  • get_executable_quote unknown never probed

    Walk the current public order book for an all-in cash-sized BUY quote on one exact contract. `platform` is polymarket or kalshi; `market_id` is the Polymarket market id or Kalshi ticker returned by search; `side` is the outcome to buy. Returns best bid/ask, depth-weighted average fill, worst consumed level, shares, estimated taker fee, effective average price, and unfilled cash. The budget includes the fee estimate. Venue-side rounding can vary with actual fills, and this tool does not assert cross-venue contract equivalence.

    mcp-tool

    {
  "type": "object",
  "title": "get_executable_quoteArguments",
  "required": [
    "platform",
    "market_id"
  ],
  "properties": {
    "side": {
      "type": "string",
      "title": "Side",
      "default": "Yes"
    },
    "platform": {
      "type": "string",
      "title": "Platform"
    },
    "market_id": {
      "type": "string",
      "title": "Market Id"
    },
    "amount_usd": {
      "type": "number",
      "title": "Amount Usd",
      "default": 100
    }
  }
}
    arguments 28 lines
  • compare_executable_quotes unknown never probed

    Fetch size-aware order-book fills and estimated taker fees for one Polymarket contract and one Kalshi contract, then compare their complete rules. It only names a best venue when the pair has been explicitly human-reviewed as equivalent. Similar titles with different settlement criteria return `comparable: false` plus blockers instead of a fabricated spread or arbitrage.

    mcp-tool

    {
  "type": "object",
  "title": "compare_executable_quotesArguments",
  "required": [
    "polymarket_id",
    "kalshi_ticker"
  ],
  "properties": {
    "side": {
      "type": "string",
      "title": "Side",
      "default": "Yes"
    },
    "amount_usd": {
      "type": "number",
      "title": "Amount Usd",
      "default": 100
    },
    "kalshi_ticker": {
      "type": "string",
      "title": "Kalshi Ticker"
    },
    "polymarket_id": {
      "type": "string",
      "title": "Polymarket Id"
    }
  }
}
    arguments 28 lines
  • list_executable_opportunities unknown never probed

    Rank both YES and NO across every human-reviewed equivalent Polymarket–Kalshi pair. Each row walks current public depth within the all-in budget, includes estimated taker fees, and links to the lower effective-price venue. Contracts whose rules changed or whose requested size cannot be quoted are omitted and reported as unavailable. Optional `family` uses a family key returned by the tool; optional `side` is Yes or No. Use this when the user asks where the largest currently executable cross-venue price differences are.

    mcp-tool

    {
  "type": "object",
  "title": "list_executable_opportunitiesArguments",
  "properties": {
    "side": {
      "type": "string",
      "title": "Side",
      "default": ""
    },
    "family": {
      "type": "string",
      "title": "Family",
      "default": ""
    },
    "amount_usd": {
      "type": "number",
      "title": "Amount Usd",
      "default": 100
    }
  }
}
    arguments 21 lines
  • list_arbitrage_candidates unknown never probed

    Scan every fingerprint-pinned equivalent Polymarket–Kalshi binary pair for two-leg coverage. It buys opposite sides at equal whole-contract size, walks current ask depth, includes estimated taker fees and conservative Kalshi rounding, and emits a candidate only when total all-in cost is below the common settlement payout. Results are unfilled candidates, never guaranteed trades: cross-venue orders are non-atomic and both exact-size legs must fill. Optional `family` uses a family key returned by the tool.

    mcp-tool

    {
  "type": "object",
  "title": "list_arbitrage_candidatesArguments",
  "properties": {
    "family": {
      "type": "string",
      "title": "Family",
      "default": ""
    },
    "max_capital_usd": {
      "type": "number",
      "title": "Max Capital Usd",
      "default": 100
    }
  }
}
    arguments 16 lines
  • list_sportsbook_surebets unknown never probed

    Find unfilled sportsbook surebet candidates across the configured live books. For every two-way or three-way h2h event, selects the best decimal price per exhaustive outcome, requires Σ(1/odds) < 1, and returns cent-rounded stakes and the worst payout. Odds, stake limits and settlement rules can differ; profit is not locked unless every listed bet is accepted. Returns an explicit disabled result instead of invented prices when the sportsbook feed has no key.

    mcp-tool

    {
  "type": "object",
  "title": "list_sportsbook_surebetsArguments",
  "properties": {
    "sport_key": {
      "type": "string",
      "title": "Sport Key",
      "default": "upcoming"
    },
    "capital_usd": {
      "type": "number",
      "title": "Capital Usd",
      "default": 100
    }
  }
}
    arguments 16 lines
  • get_world_cup_odds unknown never probed

    Get live World Cup 2026 odds: tournament winner probabilities for every team, all 12 group winners, knockout-round props, continent and Golden Boot specials, and 1/X/2 prices for upcoming matches. Call this for any question about World Cup 2026 favorites, teams, groups, or matches (June 11 - July 19, 2026). Updated every 10 minutes from prediction markets with $1.8B+ traded.

    mcp-tool

    {
  "type": "object",
  "title": "get_world_cup_oddsArguments",
  "properties": {}
}
    arguments 5 lines
  • get_world_cup_matchday unknown never probed

    Get the daily World Cup 2026 matchday market slate. Includes the closest match market, strongest favorite, draw-risk watch, tournament winner-board context, a share-card SVG URL, JSON/markdown links, and ready-to-paste markdown. Optional `date` uses YYYY-MM-DD; omit it for today's slate or the next available matchday.

    mcp-tool

    {
  "type": "object",
  "title": "get_world_cup_matchdayArguments",
  "properties": {
    "date": {
      "type": "string",
      "title": "Date",
      "default": ""
    }
  }
}
    arguments 11 lines
  • list_trending_markets unknown never probed

    List live prediction markets ordered by 24h volume. Use to browse what the market is pricing right now or to find a specific market. `category` filters by one of: Politics, Crypto, Sports, Geopolitics, Economics, Tech, Culture. `search` filters by keyword in the market question.

    mcp-tool

    {
  "type": "object",
  "title": "list_trending_marketsArguments",
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 20
    },
    "search": {
      "type": "string",
      "title": "Search",
      "default": ""
    },
    "category": {
      "type": "string",
      "title": "Category",
      "default": ""
    }
  }
}
    arguments 21 lines
  • check_bet unknown never probed

    THE pre-bet check — run this BEFORE the user places any bet, on any bookmaker. Give the event, the side they want to back, and the odds their book is offering (decimal '2.10', american '+110' or fractional '11/10' all work). Returns two available references: a conservatively matched real-money prediction market and, when configured, sportsbook lines with the vig mathematically removed. It returns an expected-value verdict (EV per 100 staked, break-even odds, Kelly stake) or refuses when the event/side cannot be resolved safely. Pass `your_probability` (0-1) to also log YOUR estimate as an append-only receipt in your public audited Brier record (voxodds.com/forecasters) — requires `forecaster_id`. Verdict is arithmetic, not a model output. Research, not financial advice; betting legality depends on the user's jurisdiction.

    mcp-tool

    {
  "type": "object",
  "title": "check_betArguments",
  "required": [
    "event",
    "side"
  ],
  "properties": {
    "side": {
      "type": "string",
      "title": "Side"
    },
    "event": {
      "type": "string",
      "title": "Event"
    },
    "sport": {
      "type": "string",
      "title": "Sport",
      "default": "upcoming"
    },
    "odds_offered": {
      "type": "string",
      "title": "Odds Offered",
      "default": ""
    },
    "forecaster_id": {
      "type": "string",
      "title": "Forecaster Id",
      "default": ""
    },
    "your_probability": {
      "type": "number",
      "title": "Your Probability",
      "default": 0
    }
  }
}
    arguments 38 lines
  • find_best_price unknown never probed

    Find which bookmaker pays the most for one specific bet when VoxOdds has a configured live sportsbook feed. The registry is a directory, not live coverage. Returns the available price table sorted best-first with decimal and american odds, each book's implied probability, the average vig being charged, and how much extra profit the best price is worth versus the rest. Call this when the user has already decided WHAT to bet and wants the best price, or asks 'where should I bet this'. Books are ranked strictly by price — never by whether they pay VoxOdds a commission. Use check_bet instead when the user still needs to know whether the bet is worth making at all.

    mcp-tool

    {
  "type": "object",
  "title": "find_best_priceArguments",
  "required": [
    "event",
    "side"
  ],
  "properties": {
    "side": {
      "type": "string",
      "title": "Side"
    },
    "event": {
      "type": "string",
      "title": "Event"
    },
    "sport": {
      "type": "string",
      "title": "Sport",
      "default": "upcoming"
    }
  }
}
    arguments 23 lines
  • compare_platforms unknown never probed

    Compare candidate equivalent events on Polymarket vs Kalshi side by side. Returns displayed probabilities and their spread as a research signal. These are not executable quotes or arbitrage claims: verify order-book depth, fees, fills, and resolution rules before deciding where a contract is actually cheaper. Optional `query` filters by keywords in the market question.

    mcp-tool

    {
  "type": "object",
  "title": "compare_platformsArguments",
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 10
    },
    "query": {
      "type": "string",
      "title": "Query",
      "default": ""
    }
  }
}
    arguments 16 lines
  • get_edge_signals unknown never probed

    Get VoxOdds' ranked market signals: unusually wide spreads, closing-soon watches, and integrity flags across live prediction markets — where the numbers say to LOOK first. Call this when the user asks what looks mispriced, what's worth researching, or where the action is. Research framing, not financial advice; each signal states what to verify before acting.

    mcp-tool

    {
  "type": "object",
  "title": "get_edge_signalsArguments",
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 10
    }
  }
}
    arguments 11 lines
  • get_forecaster_record unknown never probed

    Get YOUR audited forecast record on VoxOdds: pending receipts (submitted, awaiting market resolution) and scored results (Brier vs the market price captured when you submitted). Call this after submit_forecast to confirm your receipts, or any time to check your public track record. Same forecaster_id you submit with.

    mcp-tool

    {
  "type": "object",
  "title": "get_forecaster_recordArguments",
  "required": [
    "forecaster_id"
  ],
  "properties": {
    "forecaster_id": {
      "type": "string",
      "title": "Forecaster Id"
    }
  }
}
    arguments 13 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/6ca502f5e74dd8c2/badge.svg)](https://brick.blue/agent/6ca502f5e74dd8c2)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Own the domain? Prove it and the listing carries a verified badge here too: passport.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.