Skip to main content

₿RS Signals — MCP Server

mcp-name: io.github.brssignals/brs-signals-mcp

Live Bitcoin market regime for AI agents: three independent sensors read pre-price data — fee curves, funding velocity, whale flows, absence — every 30s and reject almost everything. When they converge, you get a directional call with the evidence attached. The data doesn't exist in history; it exists right now and can't be reconstructed. Public track record your agent can audit in one call. MCP + REST + x402. Free tier, no card.

Use it in 30 seconds — remote, no install

The public endpoint is live at https://brs-signals.com/mcp (streamable-http · keyless free tier). Any MCP client can use it — no package install, no local process.

Cursor (MCP requires Cursor's paid Pro tier) — Settings → Features → MCP → + Add New MCP Server → Type http, URL https://brs-signals.com/mcp. Or add .cursor/mcp.json:

{
  "mcpServers": {
    "brs-signals": { "type": "http", "url": "https://brs-signals.com/mcp" }
  }
}

OpenClaw — run in your terminal:

openclaw mcp add brs-signals --transport streamable-http --url https://brs-signals.com/mcp

(or OpenClaw Web UI → /settings/mcp → add an HTTP/SSE endpoint at that URL)

Claude Desktop (MCP is free) — Settings → Developer → Edit Config:

{
  "mcpServers": {
    "brs-signals": { "type": "http", "url": "https://brs-signals.com/mcp" }
  }
}

Then just ask your agent: "What's the current Bitcoin regime and convergence score?"

Or install locally (stdio, self-host)

pip install brs-signals-mcp
export BRS_API_KEY=va_yourkey_here   # get one at https://brs-signals.com
brs-mcp                                # starts the MCP server (stdio)

Claude Desktop (stdio) — add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows), then restart:

{
  "mcpServers": {
    "brs-signals": {
      "command": "brs-mcp",
      "env": { "BRS_API_KEY": "va_yourkey_here" }
    }
  }
}

Cursor (stdio) — Settings → Features → MCP → Add New MCP Server: Type command · Command python3 -m mcp_brs · Env BRS_API_KEY.

OpenClaw (stdio):

openclaw mcp add brs-signals --command python3 --arg -m --arg mcp_brs

Don't trust us — query us

The full public track record is an endpoint, not a PDF. Point your agent at it and let it reach its own conclusion:

"BRS Signals claims it rejects almost every read. Pull its public track
record (get_signal_history) and today's rejection funnel
(GET /api/v2/health/funnel), and tell me: does the data support the claim,
and what happened after each call at +4h and +24h?"

What You Get

Three independent sensors running every 30 seconds, fused into one convergence score:

Sensor Data Source What It Detects
X-Ray On-chain mempool fee curves FLAT_WIDE (accumulation) vs STEEP_TALL (panic)
Pulse Cross-exchange funding velocity Squeeze probability + direction
Shadow Stablecoin whale flows (Tron + Solana) Buying/selling intent before price moves

When all three agree → conviction. When they disagree → silence.

MCP Tools

  • get_convergence — All three engine verdicts + convergence score
  • get_directional_bias — bullish/bearish/WAIT with confidence
  • get_signal_history — Recent decoder decisions
  • get_regime_current — Market regime + active events
  • get_fee_histogram — Mempool fee curve shape analysis
  • get_funding_divergence — Cross-exchange funding squeeze
  • get_stablecoin_flows — Whale stablecoin transfers
  • get_gamma_exposure — Dealer gamma + flip level
  • get_dashboard — Bundled regime + signal + funding
  • get_system_health — Quick health check

Pricing

  • Free tier — Regime classification + convergence score (5 req/min). No card.
  • Pro tier ($50/mo) — Full directional bias + raw streams + unlimited requests
  • x402 — Agents with wallets pay per access in USDC; no signup, no human
  • Founding rate — Use code FOUNDING50 at checkout: $30/mo for 3 months (first 50 subscribers only)

Get your API key at brs-signals.com.

Links

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

brs_signals_mcp-0.1.3-py3-none-any.whl (16.5 kB view details)

Uploaded Python 3

File details

Details for the file brs_signals_mcp-0.1.3-py3-none-any.whl.

File metadata

File hashes

Hashes for brs_signals_mcp-0.1.3-py3-none-any.whl
Algorithm Hash digest
SHA256 dc8f5b22892430eddd5728bd0953d2ea366b27490ee46fcd9426e4036c8a6c54
MD5 1e8279fed5ecd5f72a1044d6c1a2e128
BLAKE2b-256 13e0aa6bc431f267ababee2b40df296043c1922dcb80eb21cd2d79d914c034f1

See more details on using hashes here.

Release history Release notifications | RSS feed

0.1.4

2 files

This release

0.1.3 This release

1 file

0.1.2

2 files

0.1.1

2 files

0.1.0

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page