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 · AI / LLM tooling

CrystlQuant

Sports win chances before every game, next to the market's, graded after. NFL, NBA, soccer, UFC.

Checks passed
13 / 22

1 failed · 8 not measured

Median response
628 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
5

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?
400
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 628 ms.

  • Pass
    Valid handshake

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

  • Pass
    Lists tools

    tools/list returned 5 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 628 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 628 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.

  • Pass
    Parameters documented

    9 of 9 parameters have a description (100%). The bar is 80%.

  • Pass
    Safety hints

    Every tool sets readOnlyHint or 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 2026-11-04T01:45:42.374341Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using CrystlQuant

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 crystlquant https://crystlquant.com/mcp

Capabilities

Tools 5

biggest_gaps

The three upcoming games where CrystlQuant and the market disagree most, biggest gap first, including games where they back different winners. Each row links to the game's page; every other disagreement is on crystlquant.com (the link comes with the answer).

Discovered
find_game

CrystlQuant's pick and win chance for one upcoming game (today or tomorrow), found by a team or fighter name, for example 'Chiefs', 'Arsenal' or 'Pereira', with a link to the game's page, where the market's chance and the gap are.

Discovered
rankings

CrystlQuant's team ratings for the NFL, NBA, MLB or NHL, or its UFC rankings by division and pound for pound, with movement since the last update. The limit is per list (each UFC division is its own list).

Discovered
todays_board

The games on CrystlQuant's board today and tomorrow, in start order: each matchup, its start time and CrystlQuant's pick, with a link to each game's page. The board carries no chances; each game's CrystlQuant chance, the market's chance and the gap are on the game's page.

Discovered
who_wins_it_all

Title chances: each league's likeliest champions from CrystlQuant's season forecasts, with the change since the last update and a link to the league's page. A row with no CrystlQuant number yet shows the CQ blind model's chance and says so. The limit is per league.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected628 ms5