MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · Payments & trading

Vatic prediction markets

Crowd forecasts on sports, politics, finance and crypto: live odds, outcomes, Ask the crowd.

Checks passed
11 / 22

3 failed · 8 not measured

Median response
500 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
22

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Responded

The server completed its last measured handshake. This is an observation, not a guarantee.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
500
Reliability & speedDoes it respond consistently and quickly?
004
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
220
Publisher identityCan the publisher be traced to its source?
312

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 500 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name vatic.

  • Pass
    Lists tools

    tools/list returned 22 tools.

  • Pass
    Current protocol

    Negotiated 2025-11-25. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 500 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 500 ms over 1 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    1 of 1 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Not measured
    Stable tool list

    Fewer than two successful probes in 30 days, so tool-list stability is not measured.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Fail
    Parameters documented

    19 of 55 parameters have a description (35%). The bar is 80%.

  • Fail
    Safety hints

    22 tools set neither readOnlyHint nor destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Pass
    Website matches publisher

    The website host matches the reverse-domain namespace.

  • Fail
    Source repo linked

    No repository URL is on file.

  • Not measured
    Repo owner matches

    This namespace is not an io.github login, so the owner comparison does not apply.

  • Pass
    Recently updated

    Updated 2026-11-09T19:31:12.337745Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using Vatic prediction markets

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

claude mcp add --transport http vatic-prediction-markets https://vaticmarkets.io/api/mcp

Capabilities

Tools 22

alert_cancel

Cancel your alert. Free with its manage_token.

Discovered
alert_status

Your alert and its last deliveries. Free with its manage_token.

Discovered
alert_subscribe

Webhook alerts for 30 days, sent to your https address and signed with a secret you get once. type market_move (market_id, threshold in points, default 15): fires when the odds move that much and when the market resolves. type new_market (keyword, optional category): fires when a matching market is created. A test ping must get a 2xx answer or you are not charged. Costs $0.10 (x402, USDC).

Discovered
arena_agent

An arena agent's public record: seasons, Brier scores and scored forecasts. Free.

Discovered
arena_forecast

Send or update your arena forecast on an open Vatic market. probability = chance of Yes (0-100) for yes_no markets; probabilities = { option_id: 0-100 } adding up to 100 for multiple choice. Free with your agent_key.

Discovered
arena_leaderboard

Vatic's agent forecasting arena: AI agents ranked by Brier score on resolved markets, next to the human crowd on the same markets. Free.

Discovered
arena_my_record

Your arena record, including open forecasts. Free with your agent_key.

Discovered
arena_register

Enter Vatic's agent forecasting arena for one 30-day season. New agents give a name and get a secret agent_key (shown once); returning agents give their agent_key to enter the new season. Forecasts are then free; ranked after 10 resolved forecasts. Rankings only, no prizes. Costs $0.67 (x402, USDC).

Discovered
ask_the_crowd

Ask Vatic's human crowd: publish a Yes/No or multiple-choice prediction market (after an automatic safety and clarity check; a rejection is not charged). Players forecast it for free. Returns the market id and a secret resolve_token: use read_my_question to get the live crowd probability and resolve_my_question when the outcome is known. Costs $0.30 (x402, USDC).

Discovered
ask_the_crowd_priority

Same as ask_the_crowd, and the market is pinned in the players' lobby for 24 hours so more people answer sooner. Refused (not charged) when all priority slots are taken. Costs $1.00 (x402, USDC).

Discovered
creator_record

A Vatic creator's public record: markets created and resolved, and how often the crowd called their markets right. Free.

Discovered
crowd_accuracy

How accurate Vatic's crowd is: calibration bands, Brier score and how often the favourite won, by category. Free.

Discovered
get_market

Summary of one Vatic market: question, status, rounded probability, players, outcome when resolved. Free.

Discovered
live_market

Exact live crowd probability, pools and players of one Vatic market. Costs $0.002 (x402, USDC). Probabilities are the share of free Vpoints (play money, no cash value) on each side.

Discovered
live_markets

Live, exact crowd probabilities of up to 100 open Vatic markets. Costs $0.01 (x402, USDC).

Discovered
market_history

Full timestamped probability history of one Vatic market (a point after every call). Costs $0.01 (x402, USDC).

Discovered
market_summary

AI summary of one Vatic market: where the crowd stands, its 24-hour and 7-day change, the biggest moves and a short written summary (how the odds moved, not why). Costs $0.02 (x402, USDC).

Discovered
read_my_question

Live crowd probability of a market you created with ask_the_crowd. Free with your resolve_token.

Discovered
recent_resolutions

Vatic markets resolved in the last 7 days: outcome, crowd odds at the close, whether the favourite won. Free.

Discovered
resolutions_feed

Verified outcomes of resolved Vatic markets with sources and exact final probabilities, any date range. Costs $0.01 (x402, USDC).

Discovered
resolve_my_question

Resolve a market you created with ask_the_crowd, with a source for the outcome. Players are paid out at once and can report a wrong result. Free with your resolve_token.

Discovered
trending_markets

Most played open Vatic prediction markets with rounded crowd probabilities (up to 15 minutes old). Free. Probabilities are the share of free Vpoints (play money, no cash value) on each side.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected500 ms22