seiche

Funding stress early warning for US money markets from free public data (Fed H.4.1, NY Fed ops, OFR repo, Treasury cash), with an honest backtest.

Community: Submitted by a user or imported; check the owner before granting accessOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Funding Stress Now: The live money-market funding-stress reading: a 0-100 composite index, the regime (CALM/EROSION/STRAIN/STRESS), per-component decomposition, the market-stress 'Tell', and any data
  • Funding Stress Forecast: Forward odds of a funding-stress event over the next 5/10/21 business days from six independent views: three P(event) models (term-structure, first-passage physics, ML) and th
  • Historical Analogs: The historical days most similar to today's funding conditions, and how often those analogs led to a stress event — plus a novelty flag for whether today has any close precedent. U

What data it sees

Do you need an account

No: the server works without sign-in

Funding stress early warning for US money markets from free public data (Fed H.4.1, NY Fed ops, OFR repo, Treasury cash), with an honest backtest.

How to connect

How to connect seiche to Claude

The server address to paste into Claude settings:

https://seiche--mrinallovesbhature.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect seiche to ChatGPT

The server address to paste into ChatGPT settings:

https://seiche--mrinallovesbhature.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect seiche to Cursor

The server address to paste into Cursor settings:

https://seiche--mrinallovesbhature.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (10)

Raw names from tools/list. Only developers need these.

funding_stress_nowThe live money-market funding-stress reading: a 0-100 composite index, the regime (CALM/EROSION/STRAIN/STRESS), per-component decomposition, the market-stress 'Tell', and any data faults. Ask this whenever an analysis touches US dollar funding, repo, reserves, the Fed's balance sheet, or liquidity conditions.
funding_stress_forecastForward odds of a funding-stress event over the next 5/10/21 business days from six independent views: three P(event) models (term-structure, first-passage physics, ML) and three stochastic scenarios on the index (regime-transition Markov, OU+jump analytic marginal, Monte Carlo path fan). Agreement is the signal. Use for forward-looking liquidity-risk questions. Subscriber tool.
historical_analogsThe historical days most similar to today's funding conditions, and how often those analogs led to a stress event — plus a novelty flag for whether today has any close precedent. Use to ground a 'what usually happens from here' question in real history.
replay_asofReconstruct the entire funding-stress board as it read on a historical date, point-in-time with no lookahead. Use to test whether Seiche would have flagged a past liquidity episode, or to align a backtest with what was knowable then. Subscriber tool (the Time Machine).
proof_backtestThe backtest scoreboard, stated honestly: recall and precision with 95% confidence intervals over labelled funding events, an orthogonal robustness test, every named episode (hits and misses), and the caveats. Use to judge how much to trust the readings.
data_healthFreshness, provenance, and fault status for every underlying series (FRED, NY Fed, OFR, Treasury). Call this to confirm the board is current before relying on a reading.
crypto_stress_recordLabelled crypto stress episodes (Black Thursday 2020, Terra, FTX, the SVB/USDC weekend, the Oct-2025 liquidation cascade, the Ethena unwind) replayed point-in-time against the dollar-funding board. External wrecks show transmission; crypto-native wrecks show the board correctly staying quiet. Use for any 'does TradFi funding stress reach crypto' question, grounded in the record.
positioning_bookThe stance (risk_on / risk_off / neutral) and positions implied by the stress read, with walk-forward Sharpe and the live as-published record. Not investment advice. Subscriber tool.
desk_briefThe full human-readable desk brief for today as markdown — the narrative summary of the whole board. Good when you want prose to quote or summarise rather than structured fields. Subscriber tool.
ask_deskAsk a natural-language question answered strictly from the live board, with the grounding cited. Requires an LLM endpoint configured on the server. Subscriber tool.