← signalbureau.ai

INDIVIDUAL MCP TOOL

top_accelerating

The entities/topics accelerating most across the information environment right now, ranked by cross-domain attention.

signalbureau.ainone authenticationAvailability not checked

LIVE ENDPOINT

https://api.signalbureau.ai/api/mcp

No auth detected

Connect to this endpoint to inspect the live schema for top_accelerating and invoke it with your own arguments.

Indexed input schema

{}

Risk classification

Inferred read-only · medium confidence · heuristic, not a guarantee.

  • No write-capable action terms were found; this is not proof that invocation has no side effects.

Parent server

signalbureau.ai

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.signal-bureau]
url = "https://api.signalbureau.ai/api/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "signal-bureau": {
      "type": "http",
      "url": "https://api.signalbureau.ai/api/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: signal-bureau
Remote MCP URL: https://api.signalbureau.ai/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "signal-bureau": {
      "url": "https://api.signalbureau.ai/api/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "signal-bureau": {
      "type": "http",
      "url": "https://api.signalbureau.ai/api/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "signal-bureau",
  "transport": "streamable-http",
  "url": "https://api.signalbureau.ai/api/mcp"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

Related tools

  • search_entities — Find tracked entities/topics by name or vertical (e.
  • get_entity — Full dossier for one entity: signal count, verticals it's spreading across, and why it's surfacing.
  • get_truth_object — The complete public truth object for a topic — the SAME record the /exhibit page renders, with every layer kept apart and labeled: primary operational sources (verified-as-of dates stated), attributed reporting, our coverage metric, market expectation with the maintained event arc, our derived judgment, the reporting-consensus ledger, and the state-change history.
  • ask — Ask about FUTURE or unfolding events (geopolitics, markets, tech, health — will X happen, and what the tracked record shows).
  • get_answer — Collect an async answer by ticketId (from ask).
  • get_signals — START HERE for browsing — the cheap read (500/day, no model work).
  • get_record — The correction record: the flagged-vs-control repricing regression at population level (estimate, 95% CI, cohort sizes, window, as-of), plus the dated retirement object for the case-study track record we withdrew in 2026 when re-measurement put it under our own publication bar.
  • get_calibration — The calibration scorecard — published probabilities graded against how reality resolved (Brier score, log loss, skill vs base rate, 95% CIs).