SentimentFX

Last 30 days

Uptime

100%

Response time

325 ms typical, 325 ms slowest 5%

Last check

55 min ago

Next check

in 6 h

How to call it

Add it to any MCP client that supports remote servers.

{
  "mcpServers": {
    "sentimentfx": {
      "type": "http",
      "url": "https://api.sentimentfx.org/mcp"
    }
  }
}

6 tools

• list_tickers

  List every asset SentimentFX tracks. Cheap (free — doesn't hit the billing meter). Returns two groups: `primary` (5 crypto + 7 FX pairs — the ones with full sentiment coverage across the primary RSS feeds), and `background` (US equities, ETFs, commodity futures

• get_usage

  Introspect your API key: included allowance, remaining credits, and when they refill. Free keys get 1,000 calls per 30-day window starting at their first billable call (`resets_at` is null when no window is running); paid plans refill on the 1st of each month. F

• get_sentiment

  Return the most recent FinBERT-scored headlines for `ticker`. Each headline has a `sentiment_score` in [-1, +1] (positive_prob - negative_prob) and a categorical `sentiment_label`. Costs 1 API credit per 25 headlines actually returned — same billing as GET /v1/s

• get_summary

  Return daily aggregated sentiment for `ticker` over the last `days`. Each entry has `avg_sentiment` (unweighted mean of that day's scores), `article_count`, and a directional `label` (positive / negative / neutral, thresholded at ±0.1). Costs 1 API credit per day ac

• get_prices

  Return daily close prices for `ticker` over the last `days`, in the ticker's native currency -- see the `currency` field on the response. Costs 1 API credit per day actually returned — same as GET /v1/prices/{ticker}. Prices come back reverse-chronological. Cry

• get_correlation

  180-day Pearson correlation between daily sentiment shifts and next-day price returns for `ticker`. Returns Pearson `r`, `p_value`, `n_days` overlapping, a 95% confidence interval (Fisher z), and a categorical `strength` (strong / weak / inconclusive). Costs 1 A

Security scan

• No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks