mcpbeat Sign in

Seiche — world-markets evidence terminal MCP Server

answering

Seiche — world-markets evidence terminal is answering right now. Last checked 14 min ago. 1 868 installs a week from pypi. It exposes 14 tools. Last commit 15 Sep 2026.

Money, FX, capital-market and metadata-only China macro evidence with source clocks and limits.

Installs per day peak 1 186 · avg 130 · +96% w/w
a month agotoday
Uptime history 48 days of history · worst day 71%
48 days agonow
100.0%
Uptime 24h
91 of 91 checks
14
Tools
read from the server
311 ms
Response time
average over 24h
1 868
Installs / week
npm and PyPI

What changed 32

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 8 August 2026. No other catalogue keeps this.

14 Sep a tool changed version
13 Sep a tool changed version
9 Sep a tool changed version2 times that day
9 Sep a tool appeared market_workbench
8 Sep a tool changed version
8 Sep a tool appeared research_network
5 Sep a tool changed version3 times that day
5 Sep a tool description was rewritten money_market_context
5 Sep a tool changed the parameters it asks for money_market_context
2 Sep a tool appeared trade_safety_risk_context
and 22 more, back to 8 August 2026

What the code does

We read the source, 19 min ago · tools taken from the live server · rules 3dff92dd89df

Evidence

Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.

Runs commands and sends data out [пакет] seiche/alerts.py:53
        subprocess.run(
Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

In the project's build, not in the package

Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.

Builds a file path from a variable bot/rissaga.py:737, bot/seiche_bot.py:487
    return os.path.join(STATE_DIR, name)
Image runs as root Dockerfile:34
# The pinned distroless base includes CPython's package bootstrap module even
# though it includes no pip executable. Remove that bootstrap as root during
# the image build; the final process user remains the unprivileged UID below.
USER 0

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

We found things in this code

Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Seiche — world-markets evidence terminal and you get told the day something new turns up.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 14 min ago.

run in your terminal
claude mcp add seiche --transport http https://api.seiche.info/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "seiche": {
      "url": "https://api.seiche.info/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.seiche]
url = "https://api.seiche.info/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "seiche": {
      "url": "https://api.seiche.info/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "seiche": {
      "url": "https://api.seiche.info/mcp"
    }
  }
}

This one needs environment variables set before it will start: SEICHE_MCP_PUBLIC (Set to 1 to expose the fourteen free public tools shipped by seiche 0.13.3 over stdio: latest_article, funding_stress_now, trade_safety_risk_context, historical_analogs, proof_backtest, data_health, crypto_stress_record, institutional_flows, oil_funding_context, fx_materials_passage, money_market_context, world_markets_context, research_network, market_workbench.). The author declared them in the registry entry; get the values from the project itself.

Available tools 14

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

crypto
crypto_stress_record
Labelled crypto stress episodes (Black Thursday 2020, Terra, FTX, the SVB/USDC weekend, the Oct-2025 liquidation cascade, the Ethena unwind) replayed with causal truncation but final/current-vintage inputs 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.
data
data_health
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.
funding
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 faults. Ask this whenever an analysis touches US dollar funding, repo, reserves, the Fed's balance sheet, or liquidity conditions.
historical
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.
institutional
institutional_flows
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.
latest
latest_article
The exact full-text Seiche editorial published today: current funding analysis when the evidence moved, or a clearly labelled historical replay on a quiet day. Returns the canonical headline, dek, Markdown, evidence clock, generation mode and passing publication receipt. Use this for 'what did Seiche write today?' and quote it without regenerating facts.
market
market_workbench
Read cached official FX reference histories and same-date currency crosses, with native units, provenance, age and observed-interval changes. Inspect owner-accepted Palimpsest China annual economic series and revision-aware history beside the CNY reference. Daily fixings, annual context and licensed gaps remain distinct. No collection, model fitting, executable quotes or scoring.
materials
fx_materials_passage
The live upstream FX and physical-material pressure read versus funding already priced in SOFR and commercial paper, with the Passage's discovery/holdout ledger, de-clustered analogs, dollar-system context and settlement scenarios. Use for currency weakness, commodity working capital, FX settlement, or whether trade-flow cash pressure is reaching money markets. Context only; an earned link is stable association, not causation.
money
money_market_context
Granular, descriptive USD money-market context from the already assembled desk: policy corridor and overnight spreads; SOFR/TGCR/BGCR distributions and tails; repo-segment rates and volumes; CP-Treasury spreads; bills and cash curve; liquidity buffers and Fed facilities; and MMF repo plumbing. Use optional `section` to request a compact summary, one named desk section, diagnostics, sources, methodology, or all context. Diagnostics count funding persistence, compare secured/unsecured benchmarks and show calendar cohorts with sample limits, without changing any score. Returns exact-date alignment, native-cadence changes, empirical own-history statistics, freshness, coverage, formulas, sources, and caveats as applicable. Chart history is always omitted. Reads only an already completed cached or persisted snapshot; it never triggers collection or engine recomputation, while freshness is re-evaluated at response time. Context only: no causal, predictive, probability, or trade claim.
oil
oil_funding_context
Observed WTI/Brent, commercial-paper and SOFR−IORB evidence; Ballast's WTI/Henry Hub CFTC positioning, gross mark-displacement proxy, paying-side concentration and EIA inventory ledger; live Cushing stocks and the Brent−WTI spread kept separate from dated capacity, benchmark and chokepoint references; the change-on-change oil/CP association; plus explicitly scenario-only cargo-credit, margin and India cash arithmetic. Use when a question asks how oil or energy futures can transmit cash pressure into dollar funding. Ballast is not an observed margin call; dated structure is not live transit data; nothing here is a forecast, trade signal, or Seiche composite input.
proof
proof_backtest
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.
research
research_network
Explore every Palimpsest dataset by topic, with source clocks, rights, freshness and pagination. Includes Seiche's separately completed funding context and explicit research steps into institution filings, exit liquidity and NarcoScope's granular global data. Source metadata and funding interpretations stay distinct. No source collection, score changes, causal joins or trading authority.
trade
trade_safety_risk_context
A deterministic, bounded projection of the last completed Seiche board: funding regime, 0-100 stress index, coverage, source staleness counts, snapshot clock, and conservative evidence clock. It repeats the rights check and never collects, fits, calls a network source, reads a notary ledger, or contacts a broker. This is metadata-only derived context, not order-bound, non-executable, never real-money eligible, and it does not evaluate stream attestations or treat them as per-order authority.
world
world_markets_context
Unified, chartless context for broad financial-market questions. It projects only completed/public state into money_markets, forex, macro-capital transmission, China macro evidence, official references, methodology, or a compact summary. Every response carries snapshot/as-of clocks, canonical Seiche citation URLs, and explicit observed, derived, structural, restricted, and unavailable boundaries. The China structural catalog is unsigned; only status=restricted represents a verified Seiche owner-attested revision; both states keep NBS values, raw evidence, and history withheld. A separately operator-accepted economic_context may publish licensed World Bank WDI values with annual/structural freshness, distinct release, Palimpsest collection, and Seiche acceptance clocks. Those values are context only and never a live print, score, gauge, forecast, or signal. The sources selector is reference-only; use all when verified China context and its NBS source linkage must appear together. Coverage is curated and partial rather than exhaustive or uniformly live. It never triggers collection, repository history reads, or model fitting. Its named-field whitelist omits chart and history arrays for data minimization; that is not a per-record licensing audit. Capital coverage is limited to public positioning proxies, Treasury primary-market absorption, market stress, official liquidity and global dollar credit—not a security master, issuer-data service or consolidated tape. Use Undertow instead when the question is specifically about executable depth, liquidity-provider concentration, or position-sized exit cost.

Tools removed

Tools this server used to expose. Anything built against them stopped working on the day they went.

ask_desk
removed 4 Aug 2026
desk_brief
removed 4 Aug 2026
funding_stress_forecast
removed 4 Aug 2026
positioning_book
removed 4 Aug 2026
replay_asof
removed 4 Aug 2026

Endpoints

URLTransportStateLatencyChecked
https://api.seiche.info/mcp streamable-http answering 271 ms 14 min ago

Alternatives to Seiche — world-markets evidence terminal

same job, measured the same way
Wudao A-Share Stock Data MCP
by jcdreamjc

Read-only China A-share data for AI agents: market, limit-up, capital flow and disclosures.

answering
Quanttogo MCP
by quanttogo

Macro-factor quantitative signal source for US and China stock markets via MCP.

local only
Arkolith
by wikatar

Evidence-backed capital-change intelligence and sourced financial data for AI agents

answering
Shingou
by shingou

Hourly crypto news sentiment and typed market events, with sources on every signal.

18 installs/wk 4 tools answering
Monk
by labstack

Research stocks and futures with quotes, charts, news, scans, and source-backed evidence.

answering
Talking Heads on Markets
by strickland84

Source-backed market views by talking head, topic, ticker, and horizon, with original links.

9 tools answering
Ozma
by swerve-hoe

Agentic API marketplace — search, provision, and call data sources with one Ozma key

answering
SourceActs
by sourceacts

Official EUR-Lex, UK, US, and gazette search, metadata fetch, and change-only watches.

answering

Seiche — world-markets evidence terminal — questions

Answers built from our own checks of this server.

What can Seiche — world-markets evidence terminal do?
It exposes 14 tools, read directly from the server on our last check. Among them: crypto_stress_record, data_health, funding_stress_now, fx_materials_passage, historical_analogs, institutional_flows and 8 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Seiche — world-markets evidence terminal working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 311 ms. The bar chart above shows every period we have measured.
Did Seiche — world-markets evidence terminal ever remove tools?
Yes. ask_desk, desk_brief, funding_stress_forecast, positioning_book and 1 more are no longer exposed — we recorded the date each one disappeared. A tool vanishing usually means a breaking change for anything that depended on it.
How do I connect Seiche — world-markets evidence terminal?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Seiche — world-markets evidence terminal need an API key?
No. Seiche — world-markets evidence terminal completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 14 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Seiche — world-markets evidence terminal?
It answers our handshake in 311 ms on average, which is faster than 49% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
How many people use Seiche — world-markets evidence terminal?
The pypi package seiche was installed 1 868 times in the last week. Week over week that is +96%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Seiche — world-markets evidence terminal open source?
Yes — it is published under the AGPL-3.0 licence, written in Python, 1 stars on GitHub and 1 open issue. The source link is on this page, so you can read exactly what it does with your data before you connect it.