io.github.beepboop2025由 GitHub 帳號 beepboop2025 發布v1.8.1更新於 Oct 28, 2026
Free bank-filing and counterparty research; cited evidence limits; public MCP needs no API key.
唯讀研究型 MCP，讓助理取得 LiquiLens 及其關聯產品提供、附引用的銀行倒閉、融資壓力與加密流動性證據。
Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。
把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。
閱讀 https://sourceweft.com/mcp/io.github.beepboop2025%2Fliquilens/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。把它新增到你客戶端的 mcpServers 設定中。
{
"mcpServers": {
"liquilens-the-failure-radar": {
"type": "http",
"url": "https://api.liquilens.in/mcp"
}
}
}Hosted Streamable HTTP MCP; no local server or API key for public read-only tools. Add the products you need to Claude Code:
Try this first: What changed in ESAF Small Finance Bank's NPAs? Cite the filing, reporting period and missing disclosures.
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.
Endpoint: https://api.liquilens.in/mcp (streamable HTTP, no auth, no install)
LiquiLens is the institution-evidence product of LIQUILENS PRIVATE LIMITED, a registered company in India (CIN U62011RJ2026PTC116792). One company, three connected products: LiquiLens investigates institutions, Seiche explains funding conditions, and Undertow examines market liquidity. People and AI agents can follow an exposure across all three while retaining each product's source dates, coverage gaps and research limits. International access does not imply universal market coverage or a shared score.
Read the company and investor story and the shared company profile.
Try it live: liquilens.in/developers · REST catalog: api.liquilens.in/api
LiquiLens is a failure early-warning system for banks and lenders, built on public
data with a machine-readable historical-evidence boundary served beside every claim.
Anonymous discovery on 11 October 2026 returned MCP 1.8.1 with 24 read-only tools
and 5 guided prompts, so an agent
reads the same status, eligibility flags and cited record a human sees. The repository
contract separately pins MCP 1.8.1 at
d6f99bdf2de14e8ef2f29032cf9561ca8a446de8, with 23 read-only tools and 5 guided prompts.
The capability tables below describe that pinned source. Discover the hosted
endpoint for the current public inventory, including institution_evidence_monitor.
It now reads both ends of the chain: which institutions are fragile, and whether that
stress is actually crossing into the real economy: companies rolling paper and drawing
credit lines, households falling behind. Channels that cannot be read are named in
cannot_see rather than reported as calm.
For Hermes and OpenClaw, use the native setup guides:
The current guides select thirteen research tools across LiquiLens, Seiche and Undertow, including GIFT City, reference FX and gold scenarios. Their dated native-client receipts retain the original nine-tool selection and exact verification scope. Public research requires no account or API key; fair-use limits apply and your model provider may charge separately.
The free starter kit also includes a Python brief, a manual n8n funding workflow and configurations for the clients below.
OpenClaw users can also install the optional research instructions from ClawHub:
Connect the MCP servers using the OpenClaw guide first. The skill supplies task instructions and a configuration template; installation does not configure servers or run research. Its source bundle is MIT-0; that license does not relicense source data or API responses.
Checked on 4 October 2026 (UTC): version 1.1.0 is public and ClawHub's
version-pinned verification result
reports a passed security check with a benign, high-confidence verdict.
Its embedded detailed scanner report retains
seven findings, including medium external-transmission flags for the public MCP
URLs, and reports partial analysis. Review the versioned security audit
before installation and use public research inputs.
Its isolated Linux install recorded the correct version and matched all
three reviewed source files. ClawHub's public verifier and the installed Linux
client's version-pinned openclaw skills verify now both report pass, with the
generated Skill Card present. The upload is unsigned and has no server-resolved
GitHub import provenance. A fresh isolated macOS install after storage recovery
also matched all three source-file hashes, and its version-pinned verification
reports pass. The earlier macOS timeout remains a separate failed attempt.
No model or research tool ran in these checks.
The direct MCP configuration is available independently of the ClawHub skill.
Claude Code:
Codex:
Cursor: merge the remote MCP config
into .cursor/mcp.json for one project or ~/.cursor/mcp.json for all projects.
The download includes the companion Seiche funding endpoint. Preserve existing entries.
For an existing Codex config, use the TOML snippet
and merge its server entries into ~/.codex/config.toml.
Claude.ai / ChatGPT: add a custom connector or MCP app with the endpoint above where that feature is available in your workspace.
This repository is the public discovery and documentation mirror. The hosted
implementation is maintained in a private core repository. This public mirror pins
its inspectable capability contract to the reviewed source revision above.
The official Registry entry
uses the name io.github.beepboop2025/liquilens. This repository's Registry
metadata revision 1.8.1 points to the public mirror and free starter kit.
The hosted MCP now reports version 1.8.1 at the same endpoint. The Registry
metadata and runtime happen to share a version number; they remain separately
verified contracts. The pinned source and tool inventory above describe the current
runtime. The existing Registry record continues to identify this public mirror.
The current runtime separates fresh model results from reviewed filing facts: expired filing scores are excluded from the live board, current disclosures retain their official source and publication clocks, and inactive institutions remain identifiable in historical evidence. Its US evidence includes the June 2026 panel and reviewed 2026 failure notices through 25 September.
The separate source-data MCP and Python client expose funding histories, bank filings and Bitcoin/Liquid settlement observations with source receipts, native units and capture clocks. Use the live coverage table or import its OpenAPI contract.
The research recipes run with
Python 3.11+ and its standard library. No API key, LLM or Python package install is needed.
Download and inspect financial_research.py,
then run:
The first command discovers covered bank slugs. The second checks coverage before
retrieving that exact bank's sourced asset-quality history; an absent slug stays
not_covered. The funding brief calls Seiche's money-market desk. Returned evidence
retains its native source dates, eligibility, unavailable states and limitations;
a successful request does not imply fresh or complete evidence. Each run is bounded
and performs no scheduling or trading. Operators should add --verification so their
checks are labelled synthetic and excluded from adoption totals.
For a visual workflow, download the n8n bank-review workflow and follow the import guide. It uses a manual trigger and no LLM. The guide records its execution-verification status; a downloadable workflow does not imply acceptance into n8n's template library.
2026-07-28: stateless requests use server/discover, per-request _meta,
MCP-Protocol-Version, and mirrored Mcp-Method / Mcp-Name routing headers.2025-11-25, 2025-06-18, and 2025-03-26: retained legacy initialization,
tools, prompts, notifications, batching, and ping behavior.resources/list and resources/templates/list are supported and currently return
empty catalogs. resources/read returns an explicit not-found error instead of
inventing a resource.The generative layer explains; deterministic screening policy scores. Historical diagnostics retain their served evidence status and eligibility flags and do not become validated-backtest or real-money evidence merely because a deterministic engine produced them. Screens, not ratings; not investment advice. Institutions without a vetted dossier are absent by design — the tools say so rather than inventing a score.
The three historical status tokens are part of the API contract, not marketing copy:
PERIOD_END_PROXY_CONSTRUCTION_PIT for India,
CURRENT_AMENDED_CONSTRUCTION_PIT for the United States, and
NAMED_CASE_FILES_CONSTRUCTION_PIT for Europe. In the current release, every market
serves validated_backtest_eligible: false and real_money_eligible: false.
https://api.seiche.info/palimpsest/mcp) — live internet-censorship signalsProduct: liquilens.in · Live demo: demo.liquilens.in
This account-linked marker supports ownership review of the existing directory record. Directory badges and cached tool counts are separate from the live MCP contract and its evidence limits.
Native framework tools and cited quant pipeline captures connect Seiche funding, LiquiLens bank diagnostics and Undertow market liquidity through compact read-only tables. LangChain/LangGraph, CrewAI, OpenAI Agents and Pydantic AI share one evidence contract and repeat-call revision tokens. Current published history is not an as-published vintage archive. No execution authority or institutional-adoption claim is implied.
來源：README.md，提交 0e1ee5e
NPA, SFB and cooperative-bank review
Cited NPA changes, PCR definitions and capital scope for banks/SFBs/UCBs, plus separately dated provisional business updates when accepted. Keep each period and provisional status explicit. No score, credit or execution authority.
slug必填as_ofinclude_historyReconcile a disclosed NPA movement
Reconcile supplied NPA movements; keep recoveries/write-offs/sales/upgrades distinct. Arithmetic, not input authentication.
statement必填Indian banking evidence coverage
Bank/SFB/UCB coverage with stale and missing evidence. Research, not a census or rating.
as_ofsectorCorporate Transmission board (US)
Answers ONE question: is US funding stress reaching nonfinancial firms? Use household_credit_board for households. CP, bank credit lines and real-economy confirmation; cannot_see preserves gaps. Seiche context never enters regime or transmission. Display-only; no institution score or tier. full:true adds methods.
fullBank/crypto exposure register
Read the compact cited bank/crypto exposure register: disclosed quantum, stablecoin and venue links, exposure channels, Undertow run-risk cross-read and compound flags. Detailed disclosures stay on the public REST detail route. Takes no arguments; display-only, never an institution score or investment advice.
無需輸入參數。
Crypto Regime board (BTC/ETH)
Read the compact BTC/ETH Crypto Regime board: current change-point state, log-SR statistic, last shift, observation count and the display-only cross-read against disclosed bank exposure. Time-series paths stay on the public REST detail route. Takes no arguments; feeds no institution score and is not investment advice.
無需輸入參數。
Historical evidence: European named case files
Read seven cited European retrospective case files through unrecalibrated Indian lenses. Named case studies, not a cohort: no European recall percentage to quote. Omit slug for summaries, or supply a returned slug for a full quarterly case file.
slugHistorical diagnostic: India construction-PIT replay
Read the 48-institution Indian construction-PIT crisis diagnostic, including misses and false alarms. Uses publication clocks where present and a +60-day filing-lag proxy otherwise; overwritten amendments are unreconstructable. evidence_institution returns a full replay.
無需輸入參數。
Historical diagnostic: one Indian case replay
Read a sourced Indian construction-PIT quarterly replay, lens alert timing and hit/miss/false-alarm verdict. Use evidence_india for exact slugs. Filing-availability proxies do not establish a validated backtest.
slug必填Historical evidence status: all markets
Historical evidence: India (48-institution construction-PIT diagnostic), US (industry-wide current-amended vintage), Europe (named cases, no cohort claim). Start here, then evidence_india, evidence_us or evidence_europe for details.
無需輸入參數。
Historical diagnostic: US construction-PIT watchlist
Read US bank current-amended-vintage diagnostics and named replays, including misses. Not a validated point-in-time backtest. Report the quarterly top-decile budgeted watchlist beside recall, uncertainty and lead times; it is not an individual-bank verdict. include_trajectories:true adds histories.
include_trajectoriesFailure Radar board (India)
Vetted Indian lender PDs, PCA/SAF and funding. market_dd requires tier authority; diagnostic clocks/refusals stay in market_dd_evidence. Slugs for failure_radar_institution. Research, not a rating.
無需輸入參數。
Failure Radar institution dossier
Read one Indian lender dossier: quarterly PDs and drivers, PCA/SAF headroom, funding, forensic and listed-market evidence. Discover slugs with failure_radar_board. Uncovered institutions remain absent, never scored from memory.
slug必填Markov forward odds per layer
Read counted Markov transitions and empirical 5/20-day reach odds. Odds are withheld until 60 observed days; counts stay visible and absence is never precision. Historical frequencies are not calibrated forecasts. Display-only, never a state driver.
無需輸入參數。
Household Credit board (US)
Answers ONE question: is stress reaching US household credit? Use corporate_transmission_board for firms. Delinquency, charge-offs, revolving credit and unscored debt-service context; gaps stay in cannot_see. Display-only; no institution score or watchlist tier. full:true adds methods and histories.
fullInstitution evidence monitor
Bank/NBFC evidence, gaps and review alerts. slug: one record; slugs: watchlist; neither: all tracked. End-of-day as_of. No scoring or delivery authority.
slugas_ofslugsinclude_historyInstitution coverage
Search Indian dossiers or RBI rows. Overlapping populations; registry presence grants no financial coverage or score.
qlimitscopeoffsetInstitution review packet (India)
Cited human review packet for an exact slug or unique normalized full name. No fuzzy match or new score; stale/dark gaps retained. Content hash detects alteration, not attestation or publication-time proof.
institution必填Latest evidence-led article
Read today's exact full-text LiquiLens editorial: current institution-risk analysis when the evidence moved, or a labelled historical replay when it did not. Returns the canonical headline, dek, Markdown, evidence clock and passing publication receipt; quote it without regenerating facts.
無需輸入參數。
RBI supervisory tape
Read the latest RBI enforcement and supervisory actions — monetary penalties, licence cancellations and supervisory directions — parsed from rbi.org.in press releases, newest first, each item carrying the RBI's own source URL. Takes no arguments. When no tape snapshot exists on the deployment, says so in a stated note instead of returning silent emptiness.
無需輸入參數。
Route to Palimpsest sources, Seiche funding, Undertow exit liquidity and NarcoScope data. Set limit for full metadata. Rights remain attached; no identity, score or eligibility changes.
limittopicoffsetStablecoin Rails board
Paged peg/run evidence; partial data is never CALM. Follow pagination.next_offset. Full receipts on REST. Display-only, not investment advice.
limitoffsetRBI NBFC register search
Search the RBI NBFC register by name/CIN substring, classification or regulation layer. Returns official register rows. Supply q or a filter; a filter without q browses that slice. Registration does not establish creditworthiness.
qlayerlimitclassificationVerify the published record
Verify a ledger stream by recomputing hash-chain commitments and checking enabled signatures and anchors. Returns the actual verifier verdict, including failures. Verifies record integrity, not economic accuracy.
stream已滿足適用檢查項的 90%
該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。
請在儲存庫或註冊中心條目中宣告授權條款。
claude mcp add --transport http liquilens https://api.liquilens.in/mcpclaude mcp add --transport http seiche https://api.seiche.info/mcpclaude mcp add --transport http undertow https://api.seiche.info/undertow/mcpopenclaw skills install @beepboop2025/liquilens-trading-research --version 1.1.0claude mcp add --transport http liquilens https://api.liquilens.in/mcpcodex mcp add liquilens --url https://api.liquilens.in/mcppython3 financial_research.py bank-reviewpython3 financial_research.py bank-review --slug cosmos-ucbpython3 financial_research.py funding-brief