LiquiLens — the Failure Radar
Free bank-filing and counterparty research; cited evidence limits; public MCP needs no API key.
我该使用它吗
质量与安全性
发现（1）
- LOWTool 'banking_specialisation_coverage' name length outside 3-30 range在 banking_specialisation_coverage 中
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"liquilens": {
"url": "https://api.liquilens.in/mcp"
}
}
}远程端点
https://api.liquilens.in/mcpstreamable-http它能做什么
工具清单
工具（23）
🟢bank_asset_quality_review(slug, as_of, include_history)
Sourced GNPA/NNPA, percentage-point changes, PCR definitions, capital scope and NPA reconciliation with SFB/UCB context. Free; no score, credit or execution authority.
输入模式
{
"type": "object",
"properties": {
"slug": {
"type": "string"
},
"as_of": {
"type": "string",
"format": "date",
"description": "End-of-day YYYY-MM-DD cutoff; not future."
},
"include_history": {
"type": "boolean",
"default": false
}
},
"required": [
"slug"
],
"additionalProperties": false
}🟢bank_npa_reconciliation(statement)
Check supplied NPA stock movements. Keep recoveries, write-offs, sales and upgrades distinct. Free arithmetic; no input authentication or loan classification.
输入模式
{
"type": "object",
"properties": {
"statement": {
"type": "object",
"properties": {
"period_start": {
"type": "string",
"format": "date"
},
"period_end": {
"type": "string",
"format": "date"
},
"amount_unit": {
"type": "string",
"enum": [
"INR_crore",
"INR_lakh",
"INR",
"INR_thousand"
]
},
"opening_gnpa": {
"type": "number",
"minimum": 0,
"maximum": 1000000000000000000
},
"additions": {
"type": "number",
"minimum": 0,
"maximum": 1000000000000000000
},
"closing_gnpa": {
"type": "number",
"minimum": 0,
"maximum": 1000000000000000000
},
"rounding_decimals": {
"type": "integer",
"minimum": 0,
"maximum": 6
},
"complete": {
"type": "boolean"
},
"reductions": {
"type": "array",
"maxItems": 16,
"items": {
"type": "object",
"properties": {
"kind": {
"type": "string",
"enum": [
"cash_recoveries",
"upgrades",
"write_offs",
"asset_sales",
"compromise_settlements",
"combined_reductions",
"other_reductions"
]
},
"amount": {
"type": "number",
"minimum": 0,
"maximum": 1000000000000000000
}
},
"required": [
"kind",
"amount"
],
"additionalProperties": false
}
}
},
"required": [
"period_start",
"period_end",
"amount_unit",
"opening_gnpa",
"additions",
"closing_gnpa",
"reductions",
"complete",
"rounding_decimals"
],
"additionalProperties": false
}
},
"required": [
"statement"
],
"additionalProperties": false
}🟢banking_specialisation_coverage(sector, as_of)
Indian bank, SFB and UCB coverage with observed, stale, historical and absent evidence. Free research; not a census or rating.
输入模式
{
"type": "object",
"properties": {
"sector": {
"type": "string",
"enum": [
"all",
"bank",
"sfb",
"ucb"
]
},
"as_of": {
"type": "string",
"format": "date",
"description": "End-of-day YYYY-MM-DD cutoff; not future."
}
},
"additionalProperties": false
}🟢corporate_transmission_board(full)
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.
输入模式
{
"type": "object",
"properties": {
"full": {
"type": "boolean",
"description": "also return method_note, thresholds and per-leg basis prose (larger payload); default false",
"default": false
}
},
"additionalProperties": false
}🟢crypto_exposure_board
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.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢crypto_regime_board
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.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢evidence_europe(slug)
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.
输入模式
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "optional kebab-case case-file slug, e.g. 'credit-suisse'; omit for all seven summaries"
}
},
"additionalProperties": false
}🟢evidence_india
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.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢evidence_institution(slug)
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.
输入模式
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "kebab-case slug of a replayed institution, e.g. 'dhfl' or 'global-trust-bank'"
}
},
"required": [
"slug"
],
"additionalProperties": false
}🟢evidence_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.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢evidence_us(include_trajectories)
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.
输入模式
{
"type": "object",
"properties": {
"include_trajectories": {
"type": "boolean",
"description": "also return per-quarter score series for the marquee replays (large payload); default false",
"default": false
}
},
"additionalProperties": false
}🟢failure_radar_board
Read fresh-vetted Indian lender rows with failure PDs, disclosure, PCA/SAF, funding and listed-name DD. Scalar market_dd requires tier authority; display-only DD retains clocks and refusal reasons in market_dd_evidence. Discover slugs here, then failure_radar_institution. Research screen, not a credit rating.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢failure_radar_institution(slug)
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.
输入模式
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "kebab-case institution slug from a failure_radar_board row, e.g. 'esaf-sfb'"
}
},
"required": [
"slug"
],
"additionalProperties": false
}🟢forward_odds
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.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢household_credit_board(full)
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.
输入模式
{
"type": "object",
"properties": {
"full": {
"type": "boolean",
"description": "also return method_note, thresholds, labels and full sparklines (larger payload); default false",
"default": false
}
},
"additionalProperties": false
}🟢institution_research_coverage(scope, q, limit, offset)
Search Indian dossiers or RBI rows and evidence gaps. Populations overlap; do not infer identity or financial coverage from registry presence. Research only; no scoring.
输入模式
{
"type": "object",
"properties": {
"scope": {
"type": "string",
"enum": [
"dossiers",
"rbi_registry"
]
},
"q": {
"type": "string",
"maxLength": 150
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 500
},
"offset": {
"type": "integer",
"minimum": 0,
"maximum": 100000
}
},
"additionalProperties": false
}🟢institution_review_packet(institution)
Build a compact cited human review packet from canonical fresh-vetted Indian radar records. Exact slug or uniquely normalized full name only; no fuzzy matching or new score. Preserves stale/dark gaps and validation hashes. Its content hash detects alteration; it is not attestation or a publication-time proof.
输入模式
{
"type": "object",
"properties": {
"institution": {
"type": "string",
"description": "exact Failure Radar slug or full institution name"
}
},
"required": [
"institution"
],
"additionalProperties": false
}🟢latest_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.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢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.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢research_network(topic, offset, limit)
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.
输入模式
{
"type": "object",
"properties": {
"topic": {
"type": "string",
"enum": [
"all",
"china",
"regions",
"information_controls",
"model_evaluations",
"funding",
"institutions",
"liquidity",
"global_data"
],
"default": "all"
},
"offset": {
"type": "integer",
"minimum": 0,
"maximum": 1000,
"default": 0
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 25,
"default": 2
}
},
"additionalProperties": false
}🟢stablecoin_rails_board
Read the compact Stablecoin Rails board: every tracked issuer's peg, redemption-run, direct-chain liability validation, coverage-gated reserve and executable-exit evidence, chain concentration and tripwire state plus the aggregate regime. Series and full receipts stay on the public REST detail route. Takes no arguments; the full oracle state never treats partial evidence as CALM (the separate peg/run alert is retained for compatibility), and the board is not investment advice.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢universe_search(q, classification, layer, limit)
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.
输入模式
{
"type": "object",
"properties": {
"q": {
"type": "string",
"description": "case-insensitive substring of the registered name or CIN"
},
"classification": {
"type": "string",
"description": "exact RBI classification as it appears in the register, e.g. 'MFI' or 'HFC'"
},
"layer": {
"type": "string",
"enum": [
"Upper",
"Middle",
"Base"
],
"description": "Scale Based Regulation layer filter"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"description": "maximum rows to return (default 20, capped at 50)",
"default": 20
}
},
"additionalProperties": false
}🟢verify_published_record(stream)
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.
输入模式
{
"type": "object",
"properties": {
"stream": {
"type": "string",
"description": "ledger stream name to verify (default 'mfi_watchlist')",
"default": "mfi_watchlist"
}
},
"additionalProperties": false
}社区
证据