# Seiche — funding-stress terminal (remote · api.seiche.info)

Funding stress early warning for US money markets from free public data, with an honest backtest.

- Trust score: 79/100 (medium)
- Change this week: +14
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `api.seiche.info`: 79/100 (this document), [markdown](https://verifymcp.io/servers/beepboop2025-seiche/api.md), [page](https://verifymcp.io/servers/beepboop2025-seiche/api)
- pypi · `seiche`: 10/100, [markdown](https://verifymcp.io/servers/beepboop2025-seiche/seiche.md), [page](https://verifymcp.io/servers/beepboop2025-seiche/seiche)

## Channel facts

- Endpoint: `https://api.seiche.info/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.8.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 83/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 85/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1238 tokens (~112/item across 11 items; 11 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http beepboop2025-seiche https://api.seiche.info/mcp
```

### Codex

```toml
[mcp_servers.beepboop2025-seiche]
url = "https://api.seiche.info/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "beepboop2025-seiche": {
      "type": "remote",
      "url": "https://api.seiche.info/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add beepboop2025-seiche --url https://api.seiche.info/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  beepboop2025-seiche:
    url: "https://api.seiche.info/mcp"
```

### Other

```json
{
  "mcpServers": {
    "beepboop2025-seiche": {
      "type": "http",
      "url": "https://api.seiche.info/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 79, 0)

- [functional regression] Schema quality: 1106 → 1238
- [functional] New tool “institutional_flows”

### 2026-08-02 (score 79, +9)

- [security improvement] Authorization: unverified → partial
- [functional] The server now declares the “prompts” capability
- [functional] First check of Schema quality: 100
- [functional] New prompt “is_now_dangerous”
- [functional] New prompt “funding_stress_briefing”
- [functional] New prompt “crisis_replay”
- [functional] Server version: 0.7.1 → 0.8.0

### 2026-08-01 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 69, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 68, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 68, +2)

- [security] Tool “historical_analogs” rewrote its description, which is the text the model reads
- [security] Tool “funding_stress_forecast” rewrote its description, which is the text the model reads
- [security] Tool “positioning_book” rewrote its description, which is the text the model reads
- [security] Tool “ask_desk” rewrote its description, which is the text the model reads
- [security] Tool “replay_asof” rewrote its description, which is the text the model reads
- [security] Tool “desk_brief” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional] Schema quality: good → excellent

### 2026-07-28 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 65, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

## MCP tools (11)

### `funding_stress_now` (~82 tokens)

Current funding-stress read

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 faults. Ask this whenever an analysis touches US dollar funding, repo, reserves, the Fed's balance sheet, or liquidity conditions.

### `funding_stress_forecast` (~99 tokens)

Forward odds of a funding-stress event

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, gradient boosting) and three stochastic scenarios on the index (regime-transition Markov, OU plus jump analytic marginal, Monte Carlo path fan). Agreement across views is the signal. Built from free public data. Use for any forward-looking liquidity-risk question.

### `historical_analogs` (~60 tokens)

Nearest 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. Use to ground a 'what usually happens from here' question in real history.

### `replay_asof` (~108 tokens)

Time Machine: the board on a past date

Reconstruct the entire funding-stress board as it read on a historical date, point-in-time with no lookahead: the composite, the regime, the per-component decomposition and the crunch windows for that date. Use to test whether Seiche would have flagged a past liquidity episode, or to align a backtest with what was knowable then. Built from free public data.

Input parameters:

- `date` (string, required): Calendar date as YYYY-MM-DD (e.g. 2019-09-17).

### `proof_backtest` (~60 tokens)

PROOF: the honest track record

The 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_health` (~46 tokens)

Data freshness & provenance

Freshness, 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_record` (~96 tokens)

Wrecks: crypto episodes vs the funding board

Labelled 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.

### `institutional_flows` (~132 tokens)

Institutional flows: who is positioned where

Hedge-fund / pension / sovereign positioning nowcast from public prints: the Treasury basis-trade size proxy (CFTC leveraged-fund net short, with a funding-fragility flag), asset-manager duration demand, foreign-official custody flows (H.4.1), a mixed-frequency fused positioning index with uncertainty bands, and how self-exciting stress events currently are (Hawkes branching ratio). Weekly cadence, point-in-time. Ask this when a question involves hedge fund leverage, the basis trade, pension duration bids, or sovereigns buying/selling Treasuries. Built from free public data.

### `positioning_book` (~62 tokens)

The Book: implied stance & positions

The stance (risk_on / risk_off / neutral) and positions implied by the stress read, with the walk-forward Sharpe, the live as-published record, and the ensemble event odds. Not investment advice, a codified reading. Built from free public data.

### `desk_brief` (~49 tokens)

This morning's desk note (markdown)

The full human-readable desk brief for today as markdown, a narrative summary of the whole board. Good when you want prose to quote or summarise rather than structured fields. Built from free public data.

### `ask_desk` (~68 tokens)

Ask the desk assistant (grounded)

Ask a natural-language question about funding conditions, answered strictly from the live board with the grounding cited. Requires an LLM endpoint configured on the server; if none is configured the tool says so instead of guessing.

Input parameters:

- `question` (string, required): Your question about funding conditions (1-600 chars).

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/beepboop2025-seiche/api#diagnostics

## Score history

- 2026-08-03: 79
- 2026-08-02: 79
- 2026-08-01: 70
- 2026-07-31: 69
- 2026-07-30: 68
- 2026-07-29: 68
- 2026-07-28: 66
- 2026-07-27: 65
- 2026-07-26: 64

## Links

- Remote endpoint: https://api.seiche.info/mcp
- Repository: https://github.com/beepboop2025/seiche
- Website: https://seiche.info/
- Changelog RSS feed: https://verifymcp.io/servers/beepboop2025-seiche/api/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/beepboop2025-seiche/api/changelog.json
- HTML version of this page: https://verifymcp.io/servers/beepboop2025-seiche/api