Seiche

Public US dollar funding research from source-dated Fed and Treasury observations. Live board: seiche.info.

Dated answers to common research questions explain the numbers, source dates and limits.

Seiche is an open-source money-, foreign-exchange, and capital-market evidence terminal, with its deepest live coverage in US-dollar funding. It joins public and official sources from the Federal Reserve, New York Fed, OFR, US Treasury, CFTC, and other authorities into a source-clocked research surface.

Every output keeps its as-of date, provenance, evidence status, known gaps, and point-in-time eligibility attached. Seiche is a research and evidence tool—not a real-time quote service, execution venue, or investment adviser.

• Live terminal: seiche.info
• Developer guide and tool runner: seiche.info/developers
• Source and full documentation: github.com/beepboop2025/seiche
• Hosted MCP server: https://api.seiche.info/mcp
• Cache-only Trade Safety context: https://api.seiche.info/api/trade-safety/risk-context

Country funding references are available through money_market_context with section="countries" (catalog) or section="countries", country="JP" (country observations). The REST equivalent is /api/v2/country-funding/JP. Coverage is partial: monthly references, daily curves, shared euro-area policy and national sovereign issuers retain their own identities and dates. See the country methodology.

Install and run

Seiche requires Python 3.12 or newer.

python3.12 -m venv .venv
.venv/bin/pip install seiche
.venv/bin/seiche pull
.venv/bin/seiche brief

Start the local REST API and terminal UI with:

.venv/bin/seiche serve

The first pull can be slower while the local cadence-aware cache is populated. Subsequent reads reuse that cache and continue to expose stale or unavailable inputs explicitly instead of silently dropping them.

Use Seiche from an AI agent

Seiche is a Model Context Protocol server. Run it locally over stdio:

SEICHE_MCP_PUBLIC=1 .venv/bin/seiche-mcp

Or connect an MCP-capable client directly to the public Streamable HTTP server:

https://api.seiche.info/mcp

The public trade_safety_risk_context tool returns only the last completed Seiche regime, index, coverage, source-status counts, and conservative clocks. It is metadata-only derived context, never an executable or real-money-eligible claim, and does not inspect the attestation ledger. Stream attestations are verified separately and never confer per-order execution authority.

Sixteen evidence/context tools are anonymous: the current funding-stress read, cache-only Trade Safety context, historical analogs, public backtest, data health, crypto record, institutional flows, oil/funding, FX/materials, US money markets, world markets, connected research (research_network), structured FX and China (market_workbench), the latest article, India–UAE funding and gold (gift_city_context), and explicit gold financing scenarios (gold_inventory_carry). Five higher-cost forecast, replay, positioning, prose, and LLM tools require an account and are omitted from anonymous tools/list responses.

Authenticated hosted MCP adds five private Agent Room preview tools for identity-to-key binding, room creation, signed append, verified listing, and full-chain verification. The same protected operations have REST twins under /api/agent-room/. They are discussion and evidence primitives only: every record is non-executable, x402 cannot unlock them, and local stdio has no bearer principal with which to expose them. See docs/AGENT-ROOM.md.

The canonical registry ownership marker is:

mcp-name: io.github.beepboop2025/seiche

See the MCP integration guide for Claude, Codex, Cursor, VS Code, and raw JSON-RPC examples.

Data and licensing boundary

The source code is licensed under AGPL-3.0-or-later. Upstream data keeps its own terms: Seiche's software license does not grant redistribution rights over data from third parties. Public outputs distinguish redistributable observations, bounded derived context, metadata-only sources, restricted inputs, and declared gaps. Review the source citation and rights fields before republishing data.

For research citation, use the repository's CITATION.cff; for defects or data questions, open a GitHub issue.