seicheCAUTION
Free AGPL funding and market-context research for international workflows. A LiquiLens product, connected to institution evidence and Undertow liquidity via API/MCP.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Connect and ask one question
Hosted Streamable HTTP MCP; no local server or API key for public read-only tools. Add the products you need to Claude Code:
claude mcp add --transport http seiche https://api.seiche.info/mcp claude mcp add --transport http liquilens https://api.liquilens.in/mcp claude mcp add --transport http undertow https://api.seiche.info/undertow/mcp
Try this first: What is the current US funding stress regime, and which dated funding events are next? Cite source dates and missing evidence.
Try it in your browser · Cursor configuration · Codex commands · Free three-product starter kit and skill
For a connected review, ask for institution evidence → funding context → BTC exit estimates, with each source date, coverage gap and limitation kept separate. Client/model costs and fair-use limits may apply. Research calls do not execute trades.
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.
LiquiLens, Seiche and Undertow are connected research products from LIQUILENS PRIVATE LIMITED, a registered company in India. Built for international review workflows: institution evidence → funding conditions → market liquidity. Market coverage, source clocks and authority remain specific to each product. Company and investors · Company profile · Try the connected workflow.
[](https://api.seiche.info/api/notary)
A seiche is a standing wave in
875350154927OBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add seiche -- None seiche==0.16.2
Trust audit
CAUTIONgrade F · trust 36/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (5 observation(s))
- Network
- declared (6 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (25)
const token='editorial-'+Math.random().toString(36).slice(2,10);panel.id=token+'-panel';
"<script type='module' src='https://static.cloudflareinsights.com/beacon.min.js' "
'data-cf-beacon=\'{"token": "534f08f7270a4f4f9a9a10f90d723ca7"}\'></script>'CMD ["/home/nonroot/venv/bin/python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8787/api', timeout=4).read(1)"]PRODUCTION_API_URL = "http://127.0.0.1:8787"
not proof["api_url"].startswith("http://127.0.0.1:")if not paths.api_url.startswith("http://127.0.0.1:") or paths.api_url.endswith("/"):export const fundingPreview = 'data:image/svg+xml;base64,PD94bWwgdmVyc2lvbj0iMS4wIiBlbmNvZGluZz0idXRmLTgiIHN0YW5kYWxvbmU9Im5vIj8+CjwhRE9DVFlQRSBzdmcgUFVCTElDICItLy9XM0MvL0RURCBTVkcgMS4xLy9FTiIKICAiaHR
github.com ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABgQCj7ndNxQowgcQnjshcLrqPEiiphnt+VTTvDP6mHBL9j1aNUkY4Ue1gvwnGLVlOhGeYrnZaMgRK6+PKCUXaDbC7qtbW8gIkhL7aGCsOr/C56SJMy/BCZfxd1nWzAOxSDPgVsmerOBYfNqltV9/hWCqBy
"duration sleeves are PAPER PROXIES: r ≈ y/252 − D·Δy + 1⁄2C·Δy2 on constant-maturity "
f"renormalize, never score as calm; regime = 6m Δrate vs ±{HARBOR_REGIME_BP}bp"frm = off.sum(axis=1) # from others into i (row off-diагonal)
const MODES = [1, 2, 3]; // driven standing modes (fixed-fixed: sin(kπx/L))
<thead><tr><th>toggle</th><th>what breaks</th><th>AUROC</th><th>ΔAUROC</th><th>recall</th><th>run-precision</th></tr></thead>
SEICHE_TEST_POSTGRES_URL: postgresql://seiche:[email protected]:5432/seiche_test
"postgresql://private-user:private-password@db/seiche"
"postgresql://private-user:private-password@db/seiche?token=private"
secret_dsn = "postgresql://operator:[email protected]/seiche"
dsn = f"postgresql://desk:p%40ss%20word@test/{name}?sslmode=require"secret = "tool-error-secret-74"
if not key.startswith("-----BEGIN OPENSSH PRIVATE KEY-----"):if not key.startswith("-----BEGIN OPENSSH PRIVATE KEY-----"):{"note": "-----BEGIN PRIVATE KEY-----\nabc"},"PROBE_SSH_KEY": "-----BEGIN OPENSSH PRIVATE KEY-----\nfixture\n",
"PROBE_SSH_KEY": "-----BEGIN OPENSSH PRIVATE KEY-----\nfixture",
Gates applied: no_behavioural_pass.
875350154927full audit observations/trust-audit/mcp-server/beepboop2025__seiche.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 875350154927 | CAUTION | F | 36 | first audit |
Questions
What is the seiche MCP server?
Free AGPL funding and market-context research for international workflows. A LiquiLens product, connected to institution evidence and Undertow liquidity via API/MCP.
Is seiche safe to connect to an agent?
With care. The audit graded it F (36/100) and found 25 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does seiche need?
It reads CLOUDFLARE_API_TOKEN, EDITORIAL_LLM_API_KEY, EXPECTED_AUTHORITY, FIXTURE_KEY, GH_TOKEN, GITHUB_TOKEN, KEY_MD5, RELEASE_SIGNING_KEY_FINGERPRINT, SEICHE_AGENT_ROOM_EXPECTED_KEY_ID, SEICHE_ASOF_AUTH, SEICHE_ATTEST_TRUSTED_PUBLIC_KEYS and SEICHE_AUTH_SECRET from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does seiche run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as seiche-ui at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (875350154927), read on 2026-10-11. The repository is watched and re-audited when it changes.