LiquiLens — the Failure Radar

Free bank research: NPA reconciliation, small finance banks, UCBs and cited evidence limits.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

    What data it sees

    Do you need an account

    No: the server works without sign-in

    Free bank research: NPA reconciliation, small finance banks, UCBs and cited evidence limits.

    How to connect

    How to connect LiquiLens — the Failure Radar to Claude

    The server address to paste into Claude settings:

    https://api.liquilens.in/mcp

    1. Open Claude (claude.ai or the desktop app).
    2. Go to Settings → Connectors.
    3. Click Add custom connector.
    4. Paste the server address copied below into Remote MCP server URL and click Add.
    5. In a chat, click + → Connectors and switch the new connector on.

    Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

    Authorization

    After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

    How to connect LiquiLens — the Failure Radar to ChatGPT

    The server address to paste into ChatGPT settings:

    https://api.liquilens.in/mcp

    1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
    2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
    3. Open Settings → Connectors and click Create.
    4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
    5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
    6. In a new chat open + → Apps/Connectors and enable the connector.

    OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

    Authorization

    On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

    How to connect LiquiLens — the Failure Radar to Cursor

    The server address to paste into Cursor settings:

    https://api.liquilens.in/mcp

    Fastest: click Open in Cursor below and confirm the prompt.

    Manually:

    1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
    2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
    3. Save the file. The server appears in the MCP list; authorize it there if asked.

    Authorization

    If the service needs sign-in, an authorize button appears next to the server in the MCP list.

    Server tool list (22)

    Raw names from tools/list. Only developers need these.

    bank_asset_quality_reviewRead a bank's sourced GNPA/NNPA history, percentage-point changes, distinct PCR definitions, capital scope and disclosed NPA stock reconciliation. SFB and UCB review questions are tailored to their funding and supervisory context. Free; no new score, credit approval or execution authority.
    bank_npa_reconciliationReconcile a caller-supplied closed NPA movement table: opening stock plus additions less classified reductions equals closing stock. Keeps write-offs, sales, upgrades and cash recoveries distinct. Free arithmetic check; does not authenticate the input or classify individual loans.
    banking_specialisation_coverageDiscover covered Indian commercial, small finance and urban cooperative banks. Separates observed, stale, historical and absent evidence. Free read-only research; this is not a census or rating.
    corporate_transmission_boardAnswers 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.
    crypto_exposure_boardRead 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.
    crypto_regime_boardRead 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.
    evidence_europeRead 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.
    evidence_indiaRead 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.
    evidence_institutionRead 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.
    evidence_marketsRead the historical-evidence headline for each market: India (48-institution construction-PIT diagnostic), United States (industry-wide current-amended-vintage diagnostic), and Europe (named cited case files, deliberately no cohort claim). Takes no arguments. Start here when asked what LiquiLens has tested, then drill into evidence_india, evidence_us or evidence_europe for the full record behind each headline.
    evidence_usRead 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.
    failure_radar_boardRead 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.
    failure_radar_institutionRead 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.
    forward_oddsRead 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.
    household_credit_boardAnswers 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.
    institution_review_packetBuild 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.
    latest_articleRead 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.
    rbi_supervisory_tapeRead 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.
    research_networkConnect institution research with Palimpsest's complete source catalog, Seiche funding context, Undertow exit-liquidity evidence and NarcoScope global data. Compact default; set limit for full metadata. No institution identifiers, scores or eligibility changes; source rights stay attached.
    stablecoin_rails_boardRead 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.
    universe_searchSearch 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.
    verify_published_recordVerify 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.
    LiquiLens — the Failure Radar: connect to Claude, ChatGPT, Cursor · Connectors.fun