LiquiLens — the Failure Radar
REMOTE · API.LIQUILENS.IN
Free bank-filing and counterparty research; cited evidence limits; public MCP needs no API key.
Available components
Last scanned (19 hours ago)
Scores higher than 96% of remote servers
Reachable. Last reached 4 Nov 2026.
Category Finance and Payments
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security83
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC is configured correctly; the domain's records validate against the full chain to the root. View diagnostics → Pass
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability81
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 2370 tokens (~98/item across 24 items; 24 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage82
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 45% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 24 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 25 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 2 Nov 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “banking_specialisation_coverage” rewrote its description, which is the text the model reads security
- Tool “institution_research_coverage” rewrote its description, which is the text the model reads security
- 1 Nov 26 −1
- Tool “crypto_exposure_board” rewrote its description, which is the text the model reads security
- Tool “crypto_regime_board” rewrote its description, which is the text the model reads security
- Tool “evidence_europe” rewrote its description, which is the text the model reads security
- Tool “evidence_us” rewrote its description, which is the text the model reads security
- Tool “latest_article” rewrote its description, which is the text the model reads security
- Tool “rbi_supervisory_tape” rewrote its description, which is the text the model reads security
- Tool “universe_search” rewrote its description, which is the text the model reads security
- “corporate_transmission_board” reworded the description of “full” cosmetic
- “evidence_europe” reworded the description of “slug” cosmetic
- “evidence_institution” reworded the description of “slug” cosmetic
- “evidence_us” reworded the description of “include_trajectories” cosmetic
- “household_credit_board” reworded the description of “full” cosmetic
- “universe_search” reworded the description of “classification” cosmetic
- “universe_search” reworded the description of “limit” cosmetic
- “verify_published_record” reworded the description of “stream” cosmetic
- 29 Oct 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Schema quality: fail → pass ▲ functional
- 15 Oct 26 0
- Tool “bank_asset_quality_review” rewrote its description, which is the text the model reads security
- Tool “stablecoin_rails_board” rewrote its description, which is the text the model reads security
- Schema quality: excellent → good functional
- “stablecoin_rails_board” added an optional parameter “limit” cosmetic
- “stablecoin_rails_board” added an optional parameter “offset” cosmetic
- 10 Oct 26 0
- Tool coverage: 56% → 48% ▼ functional
- 7 Oct 26 −1
No change was recorded against any check on this day. Schema Quality & AI Usability went from 87 to 86.
- 2 Oct 26 0
- Server version: 1.8.0 → 1.8.1 functional
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 4 Nov 2026 · Probed https://api.liquilens.in/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=liquilens.in | CN=WE1,O=Google Trust Services,C=US | 30 Oct 2026 | 28 Jan 2027 | ECDSA 256 | ECDSA-SHA256 | 1872a46fc873ff720ec8dca11a68708e |
| SANs: liquilens.in, *.liquilens.in | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC secure
Validation of api.liquilens.in. — Secure
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| in. | present | 10094 | 13 | Verified |
| liquilens.in. | present | 2371 | 13 | Verified |
| api.liquilens.in. | Verified address RRset verified with the apex keys |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains; preload |
| content-security-policy | default-src 'none'; style-src 'unsafe-inline'; img-src 'self' data:; base-uri 'none'; form-action 'none'; frame-ancestors 'none'; |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | camera=(), microphone=(), geolocation=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://api.liquilens.in/mcp | Verified | 200 | |
| http (plaintext) | http://api.liquilens.in/mcp | HTTPS enforced | 301 | https://api.liquilens.in/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
bank_asset_quality_review NPA, SFB and cooperative-bank review ~85
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.
| Name | Type | Req | Description |
|---|---|---|---|
| as_of | string | – | End-of-day cutoff; not future. |
| include_history | boolean | – | – |
| slug | string | yes | – |
No output schema declared.
No examples provided.
bank_npa_reconciliation Reconcile a disclosed NPA movement ~42
Reconcile supplied NPA movements; keep recoveries/write-offs/sales/upgrades distinct. Arithmetic, not input authentication.
| Name | Type | Req | Description |
|---|---|---|---|
| statement | object | yes | – |
No output schema declared.
No examples provided.
banking_specialisation_coverage Indian banking evidence coverage ~54
Bank/SFB/UCB coverage, stale/missing evidence and co-op census counts. Not a rating.
| Name | Type | Req | Description |
|---|---|---|---|
| as_of | string | – | End-of-day cutoff; not future. |
| sector | string | – | – |
No output schema declared.
No examples provided.
corporate_transmission_board Corporate Transmission board (US) ~92
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.
| Name | Type | Req | Description |
|---|---|---|---|
| full | boolean | – | add method_note, thresholds and per-leg basis prose (larger payload) |
No output schema declared.
No examples provided.
crypto_exposure_board Bank/crypto exposure register ~58
Read the compact cited bank/crypto exposure register: disclosed quantum, stablecoin and venue links, exposure channels, Undertow run-risk cross-read and compound flags. Details stay on REST. Display-only, never an institution score or investment advice.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
crypto_regime_board Crypto Regime board (BTC/ETH) ~64
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 REST. Feeds no institution score; not investment advice.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
evidence_europe Historical evidence: European named case files ~66
Read seven cited European retrospective case files through unrecalibrated Indian lenses. Named case studies, not a cohort: no European recall percentage to quote.
| Name | Type | Req | Description |
|---|---|---|---|
| slug | string | – | case-file slug returned by the summaries, e.g. 'credit-suisse'; omit for all seven |
No output schema declared.
No examples provided.
evidence_india Historical diagnostic: India construction-PIT replay ~59
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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
evidence_institution Historical diagnostic: one Indian case replay ~72
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.
| Name | Type | Req | Description |
|---|---|---|---|
| slug | string | yes | kebab-case replay slug, e.g. 'dhfl' |
No output schema declared.
No examples provided.
evidence_markets Historical evidence status: all markets ~57
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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
evidence_us Historical diagnostic: US construction-PIT watchlist ~83
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.
| Name | Type | Req | Description |
|---|---|---|---|
| include_trajectories | boolean | – | add per-quarter score series for marquee replays (large payload) |
No output schema declared.
No examples provided.
failure_radar_board Failure Radar board (India) ~57
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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
failure_radar_institution Failure Radar institution dossier ~86
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.
| Name | Type | Req | Description |
|---|---|---|---|
| slug | string | yes | kebab-case institution slug from a failure_radar_board row, e.g. 'esaf-sfb' |
No output schema declared.
No examples provided.
forward_odds Markov forward odds per layer ~57
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.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
household_credit_board Household Credit board (US) ~93
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.
| Name | Type | Req | Description |
|---|---|---|---|
| full | boolean | – | add method_note, thresholds, labels and full sparklines (larger payload) |
No output schema declared.
No examples provided.
institution_evidence_monitor Institution evidence monitor ~80
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.
| Name | Type | Req | Description |
|---|---|---|---|
| as_of | string | – | – |
| include_history | boolean | – | – |
| slug | string | – | – |
| slugs | array | – | – |
No output schema declared.
No examples provided.
institution_research_coverage Institution coverage ~66
Search Indian dossiers, RBI rows or NAFSCOB co-op census. Overlapping populations; listing grants no coverage or score.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| offset | integer | – | – |
| q | string | – | – |
| scope | string | – | – |
No output schema declared.
No examples provided.
institution_review_packet Institution review packet (India) ~65
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.
| Name | Type | Req | Description |
|---|---|---|---|
| institution | string | yes | exact Failure Radar slug or full institution name |
No output schema declared.
No examples provided.
latest_article Latest evidence-led article ~53
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. Quote it with its evidence clock and passing publication receipt, without regenerating facts.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
rbi_supervisory_tape RBI supervisory tape ~61
Read the latest RBI enforcement and supervisory actions (penalties, licence cancellations, directions) from rbi.org.in press releases, newest first, each with its RBI source URL. A missing snapshot is stated, never returned as silent emptiness.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
research_network ~69
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.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| offset | integer | – | – |
| topic | string | – | – |
No output schema declared.
No examples provided.
stablecoin_rails_board Stablecoin Rails board ~55
Paged peg/run evidence; partial data is never CALM. Follow pagination.next_offset. Full receipts on REST. Display-only, not investment advice.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| offset | integer | – | – |
No output schema declared.
No examples provided.
universe_search RBI NBFC register search ~110
Search the RBI NBFC register by name/CIN substring, classification or regulation layer. Supply q or a filter; a filter without q browses that slice. Registration does not establish creditworthiness.
| Name | Type | Req | Description |
|---|---|---|---|
| classification | string | – | exact RBI register classification, e.g. 'MFI' or 'HFC' |
| layer | string | – | Scale Based Regulation layer filter |
| limit | integer | – | maximum rows to return |
| q | string | – | case-insensitive substring of the registered name or CIN |
No output schema declared.
No examples provided.
verify_published_record Verify the published record ~58
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.
| Name | Type | Req | Description |
|---|---|---|---|
| stream | string | – | ledger stream name to verify |
No output schema declared.
No examples provided.
How do I install the LiquiLens — the Failure Radar MCP server?
LiquiLens — the Failure Radar is a hosted endpoint at https://api.liquilens.in/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · api.liquilens.in
claude mcp add --transport http beepboop2025-liquilens 'https://api.liquilens.in/mcp'
What is the LiquiLens — the Failure Radar MCP server?
LiquiLens — the Failure Radar is an MCP server listed in the public MCP registry as io.github.beepboop2025/liquilens. Free bank-filing and counterparty research; cited evidence limits; public MCP needs no API key. This page covers its hosted endpoint (https://api.liquilens.in/mcp).
Is the LiquiLens — the Failure Radar MCP server safe to use?
LiquiLens — the Failure Radar scores 88 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the LiquiLens — the Failure Radar MCP server expose?
LiquiLens — the Failure Radar exposes 24 tools: bank_asset_quality_review, bank_npa_reconciliation, banking_specialisation_coverage, corporate_transmission_board, crypto_exposure_board, and 19 more. Their descriptions and schemas cost roughly 1,642 tokens of context every time the server is loaded.
Does the LiquiLens — the Failure Radar MCP server require authentication?
No. We connected to LiquiLens — the Failure Radar without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the LiquiLens — the Failure Radar MCP server still maintained?
LiquiLens — the Failure Radar is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.