Metadata-Version: 2.4
Name: seiche
Version: 0.16.6
Summary: Funding, money-market and FX evidence for Python and AI agents, with source dates, provenance and explicit data-access boundaries.
Project-URL: Homepage, https://seiche.info
Project-URL: Documentation, https://seiche.info/developers
Project-URL: Source, https://github.com/beepboop2025/seiche
Project-URL: Issues, https://github.com/beepboop2025/seiche/issues
Project-URL: Changelog, https://github.com/beepboop2025/seiche/blob/main/CHANGELOG.md
Project-URL: MCP server, https://api.seiche.info/mcp
Author-email: Mrinal <beepboop2025@users.noreply.github.com>
Maintainer-email: Seiche maintainers <beepboop2025@users.noreply.github.com>
License-Expression: AGPL-3.0-or-later
License-File: LICENSE
Keywords: capital-markets,financial-data,funding-liquidity,mcp,model-context-protocol,money-markets,open-data,research
Classifier: Development Status :: 4 - Beta
Classifier: Environment :: Console
Classifier: Environment :: Web Environment
Classifier: Framework :: FastAPI
Classifier: Intended Audience :: Financial and Insurance Industry
Classifier: Intended Audience :: Science/Research
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Office/Business :: Financial :: Investment
Classifier: Topic :: Scientific/Engineering :: Information Analysis
Requires-Python: >=3.12
Requires-Dist: arch>=7
Requires-Dist: cryptography>=42
Requires-Dist: fastapi>=0.115
Requires-Dist: holidays>=0.76
Requires-Dist: httpx>=0.27
Requires-Dist: numpy>=1.26
Requires-Dist: pandas>=2.2
Requires-Dist: scikit-learn>=1.4
Requires-Dist: scipy>=1.11
Requires-Dist: tzdata>=2025.2
Requires-Dist: uvicorn>=0.30
Provides-Extra: collectors
Requires-Dist: openpyxl>=3.1; extra == 'collectors'
Requires-Dist: pyarrow>=16; extra == 'collectors'
Requires-Dist: xlrd>=2.0.1; extra == 'collectors'
Provides-Extra: deploy-test
Requires-Dist: httpx2>=2.0.0; extra == 'deploy-test'
Requires-Dist: pytest-asyncio>=0.23; extra == 'deploy-test'
Requires-Dist: pytest>=8; extra == 'deploy-test'
Provides-Extra: dev
Requires-Dist: httpx2>=2.0.0; extra == 'dev'
Requires-Dist: pytest-asyncio>=0.23; extra == 'dev'
Requires-Dist: pytest-memray>=1.7; (sys_platform != 'win32') and extra == 'dev'
Requires-Dist: pytest-pystack>=1.0; (sys_platform == 'linux') and extra == 'dev'
Requires-Dist: pytest>=8; extra == 'dev'
Provides-Extra: notary
Requires-Dist: opentimestamps>=0.4; extra == 'notary'
Provides-Extra: postgres
Requires-Dist: psycopg[binary]>=3.2; extra == 'postgres'
Description-Content-Type: text/markdown

# Seiche: funding and FX evidence for Python and AI agents

Research US-dollar funding, money markets, foreign exchange, and capital-market
context with source dates, provenance, coverage, and known gaps attached.

[Open the hosted terminal](https://seiche.info/) ·
[Connect an agent](https://seiche.info/developers) ·
[Read dated research answers](https://seiche.info/questions/)

[![PyPI](https://img.shields.io/pypi/v/seiche)](https://pypi.org/project/seiche/)
[![Python](https://img.shields.io/pypi/pyversions/seiche)](https://pypi.org/project/seiche/)
[![MCP Registry](https://img.shields.io/badge/MCP-registry-6f42c1)](https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.beepboop2025%2Fseiche)
[![AGPL-3.0-or-later](https://img.shields.io/badge/code-AGPL--3.0--or--later-blue)](https://github.com/beepboop2025/seiche/blob/main/LICENSE)

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.

Outputs retain their as-of dates, provenance, evidence status, known gaps, and
point-in-time eligibility. Use them for financial research, agent context, and
reviewable evidence. Seiche does not execute trades or provide real-time quotes
or investment advice.

- Live terminal: [seiche.info](https://seiche.info)
- Developer guide and tool runner: [seiche.info/developers](https://seiche.info/developers)
- Source and full documentation: [github.com/beepboop2025/seiche](https://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](https://github.com/beepboop2025/seiche/blob/main/docs/COUNTRY_FUNDING.md).

## Connect an AI agent without installing Seiche

Connect an MCP-capable client to the public Streamable HTTP endpoint:

```text
https://api.seiche.info/mcp
```

For clients that accept `mcpServers` JSON configuration:

```json
{
  "mcpServers": {
    "seiche": {
      "url": "https://api.seiche.info/mcp"
    }
  }
}
```

Public evidence tools can be used without an account, subject to service limits.
Start with `tools/list` to discover the tools available to your caller, then use:

| Research task | MCP tool and arguments |
| --- | --- |
| Read the funding-stress conclusion | `funding_stress_now` with `{}` |
| Get compact USD funding evidence | `money_market_context` with `{"section":"summary"}` |
| Check source freshness and faults | `data_health` with `{}` |
| Review a country's funding references | `money_market_context` with `{"section":"countries","country":"JP"}` |
| Discover connected evidence products | `research_network` with `{}` |

For example, this anonymous read returns a bounded funding summary:

```bash
curl --fail-with-body https://api.seiche.info/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  --data '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"money_market_context","arguments":{"section":"summary"}}}'
```

Keep returned dates, coverage, caveats, and unavailable or restricted states in
your agent's answer. A successful request does not make every source current.
See the [MCP integration guide](https://github.com/beepboop2025/seiche/blob/main/docs/MCP.md)
for Claude, Codex, Cursor, VS Code, and raw JSON-RPC examples.

## Install the Python package for local research

Seiche requires Python 3.12 or newer. On macOS or Linux:

```bash
python3.12 -m venv .venv
.venv/bin/python -m pip install --upgrade seiche
.venv/bin/seiche --help
```

The package installs the `seiche` research CLI and `seiche-mcp` stdio server.
To connect an agent to your local installation's public tool surface:

```bash
SEICHE_MCP_PUBLIC=1 .venv/bin/seiche-mcp
```

Local tools use local source and cache state. For an optional local collection
and brief:

```bash
.venv/bin/seiche pull
.venv/bin/seiche brief
```

The first pull can be slow while public histories populate the local cache.
Later reads reuse the cadence-aware cache; stale and unavailable inputs remain
explicit. Local collection depends on upstream availability and source access.

Start the local REST API at `http://127.0.0.1:8787` with:

```bash
.venv/bin/seiche serve
```

**The PyPI wheel contains the Python backend, not the browser terminal.** Use
[seiche.info](https://seiche.info/) for the hosted terminal. To serve a local
browser UI, use a [source checkout](https://github.com/beepboop2025/seiche#run-it),
install the backend there, and build the frontend with `npm ci` followed by
`npm run build` in `frontend/`. The source checkout's API serves the resulting
`frontend/dist` directory when it is present.

## Connect the product family

Seiche provides funding and macro context. Follow a research question to the
product responsible for the next evidence type:

| Need | Product |
| --- | --- |
| Bank disclosures and named-institution evidence | [LiquiLens](https://liquilens.in/) |
| Indicative BTC exit cost and market-depth research | [Undertow](https://liquilens-undertow.com/) |
| China and regional public-record research | [Palimpsest](https://palimpsest.info/) |
| Saved reviews and Python agent workflows across the family | [Financial Evidence](https://pypi.org/project/financial-evidence/) |

Each product retains its own coverage, access rules, source clocks, and data
rights. The [shared connection guide](https://beepboop2025.github.io/financial-evidence-skills/connect/)
lists the available hosted MCP endpoints.

## Access and evidence boundaries

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 the
[Agent Room guide](https://github.com/beepboop2025/seiche/blob/main/docs/AGENT-ROOM.md).

The canonical registry ownership marker is:

```text
mcp-name: io.github.beepboop2025/seiche
```

## 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
[CITATION.cff](https://github.com/beepboop2025/seiche/blob/main/CITATION.cff); for
defects or data questions, open a
[GitHub issue](https://github.com/beepboop2025/seiche/issues).
