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

PolySignals.net

Live crypto Buy/Sell/Hold readings from prediction markets and options, plus daily trend calls.

Checks passed
13 / 22

1 failed · 8 not measured

Median response
514 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
10

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 514 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name net.polysignals/polysignals.

  • Pass
    Lists tools

    tools/list returned 10 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 514 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 514 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

    12 of 15 parameters have a description (80%). 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 2026-10-28T13:58:56.208343Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using PolySignals.net

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 polysignals-net https://polysignals.net/api/mcp

Capabilities

Tools 10

get_coin_signal

One coin in full: the overall call, each window running now (5m, 15m, 1h, 4h, 1d) blended across venues with score, up probability, confidence and the move since the window opened, the next windows, each venue's own reading, the daily regime call, the Cryptohopper markets that get its signals and its latest delivery, the live backtest, and the newest headlines that name it. Pass timeframe to narrow it to one window.

Discovered
get_history

The blended reading of one coin's window over the last hours (up to 48), thinned to about 36 rows: time, up probability, score and confidence.

Discovered
get_methodology

The methodology document: what the score is, confidence, window matching, options readings, the backtest and the daily regime rule. Without a section: the list of sections and the introduction; with one: that section.

Discovered
get_news

The latest crypto headlines from CoinArticle, newest first, each with the live overall Buy/Sell/Hold call of every tracked coin it names. Pass coin to keep only headlines that name it.

Discovered
get_overview

Every tracked coin in one table: spot price, the overall Buy/Sell/Hold call with score and confidence, the 1 hour window, and the daily regime call (long or flat).

Discovered
get_regime

The daily regime (trend) rule relayed to Cryptohopper: long while the Coinbase daily close is more than one 20-day sigma above its 50-day average, flat once more than one below. Without a coin: the board for every coin; with a coin: its call, distance, days in state and the close that would change it.

Discovered
get_results

What following the calls would have returned, trading the coin against USD on Coinbase with fees, next to buy and hold: net and gross return, round trips, win rate, drawdown and the current position. Without a coin: one strategy (default: the daily regime) for every coin; with a coin: all eight strategies.

Discovered
get_signal_markets

Which exchange markets on Cryptohopper receive the daily trend signals (buy when a coin turns long, sell when it turns flat), in each exchange's own market format such as BTCUSDT, XBT/EUR or BTC-USD. Without arguments: every exchange with its coin and market counts; with exchange: its markets per coin; with coin: that coin's markets on every exchange; with both: that one list.

Discovered
get_trend_changes

The coins whose daily trend (regime) call changed, newest decision first: turned long (sent to Cryptohopper as a buy signal) or turned flat (a sell), decided at 00:05 UTC on the daily close, plus the next decision time, the coins whose live price is closest to the level that would change their call, how many Cryptohopper markets accepted each recent signal, and how many coins were long after each daily close over the last 90 days. A coin's starting call is not listed as a change. Give a coin for that coin alone: its current call, since when, whether it began as a change, and its calls over the last 90 closes.

Discovered
list_coins_and_venues

Which coins have venue readings, the windows, and each venue with its type and how many coins it covers.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected514 ms10