Undertow market liquidity and exit-cost tools
REMOTE · API.SEICHE.INFO
Dated exit evidence, depth, tiers and gold cash scenarios. No executable quotes or trade authority.
Available components
Last scanned (5 hours ago)
Scores higher than 93% of remote servers
Reachable. Last reached 5 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 Usability73
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (fair).Partial
- Tool/resource definitions use about 1193 tokens (~74/item across 16 items; 16 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 Coverage73
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 20% 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 16 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 17 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.
- 29 Oct 26 −2
- The server rewrote its instructions, which are the text every model session reads security
- Tool “agent_access_status” rewrote its description, which is the text the model reads security
- Tool “crypto_exit_check” rewrote its description, which is the text the model reads security
- Tool “crypto_funding_cost” rewrote its description, which is the text the model reads security
- Tool “crypto_portfolio_stress” rewrote its description, which is the text the model reads security
- Tool “depth_episodes” rewrote its description, which is the text the model reads security
- Tool “exit_cost” rewrote its description, which is the text the model reads security
- Tool “gold_cash_realisation” 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 “liquidity_tiers” rewrote its description, which is the text the model reads security
- Tool “market_corpus_context” rewrote its description, which is the text the model reads security
- Tool “research_network” rewrote its description, which is the text the model reads security
- Tool “sealed_record” rewrote its description, which is the text the model reads security
- Tool “trade_safety_exit_context” rewrote its description, which is the text the model reads security
- Tool “unwind_watch” rewrote its description, which is the text the model reads security
- Tool “venue_concentration” rewrote its description, which is the text the model reads security
- Schema quality: good → fair functional
- Tool “crypto_exit_check” changed its title: Compare crypto exit sizes and freshness → Crypto exit sizes and freshness cosmetic
- Tool “crypto_funding_cost” changed its title: Calculate perpetual funding and fee drag → Perpetual funding and fees cosmetic
- Tool “gold_cash_realisation” changed its title: Gold sale, FX and cash availability scenario → Gold sale, FX and cash scenario cosmetic
- Tool “market_corpus_context” changed its title: Public corpus coverage and source clocks → Corpus coverage and source clocks cosmetic
- 10 Oct 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “gold_cash_realisation” 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 “market_corpus_context” rewrote its description, which is the text the model reads security
- Tool “research_network” rewrote its description, which is the text the model reads security
- Tool coverage: 13% → 20% ▲ functional
- “research_network” reworded the description of “limit” cosmetic
- “research_network” reworded the description of “offset” cosmetic
- “research_network” reworded the description of “topic” cosmetic
- Tool “latest_article” changed its title: latest_article → Published editorial cosmetic
- Tool “research_network” changed its title: research_network → Connected research cosmetic
- 3 Oct 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “agent_access_status” rewrote its description, which is the text the model reads security
- Tool “crypto_exit_check” rewrote its description, which is the text the model reads security
- Tool “crypto_funding_cost” rewrote its description, which is the text the model reads security
- Tool “crypto_portfolio_stress” rewrote its description, which is the text the model reads security
- Tool “depth_episodes” rewrote its description, which is the text the model reads security
- Tool “exit_cost” 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 “liquidity_tiers” rewrote its description, which is the text the model reads security
- Tool “research_network” rewrote its description, which is the text the model reads security
- Tool “sealed_record” rewrote its description, which is the text the model reads security
- Tool “trade_safety_exit_context” rewrote its description, which is the text the model reads security
- Tool “unwind_watch” rewrote its description, which is the text the model reads security
- Tool “venue_concentration” rewrote its description, which is the text the model reads security
- Tool “venue_price_reconciliation” rewrote its description, which is the text the model reads security
- Tool coverage: 25% → 13% ▼ functional
- Tool coverage: 25% → 14% ▼ functional
- Schema quality: 95 → 77 ▲ functional
- Schema quality: 95 → 79 ▲ functional
- Server version: 1.12.0 → 1.13.0 functional
- Server version: 1.11.0 → 1.12.0 functional
- New tool “market_corpus_context” functional
- New tool “gold_cash_realisation” 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
- 26 Sept 26 0
- Endpoint reachability: reachable → not serving MCP ▼ security
- Stability: pass → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Transport: pass → fail ▼ security
- Authorization: Authorisation not fully verified: no authorisation is required to connect, but we couldn't read the whole tool list to see what that exposes. security
- Tool “agent_access_status” rewrote its description, which is the text the model reads security
- Tool “depth_episodes” rewrote its description, which is the text the model reads security
- Tool “exit_cost” 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 “research_network” rewrote its description, which is the text the model reads security
- Tool “sealed_record” rewrote its description, which is the text the model reads security
- Tool “unwind_watch” rewrote its description, which is the text the model reads security
- Tool “venue_concentration” rewrote its description, which is the text the model reads security
- Tool “venue_price_reconciliation” rewrote its description, which is the text the model reads security
- Tool “liquidity_tiers” rewrote its description, which is the text the model reads security
- Tool coverage: 36% → 25% ▼ functional
- Schema quality: 100 → unverified ▼ functional
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Endpoint reachability: not serving MCP → reachable ▲ functional
- Schema quality: fail → pass ▲ functional
- Schema quality: excellent → good functional
- Server version: 1.10.1 → 1.11.0 functional
- Server version: 1.10.0 → 1.10.1 functional
- New tool “crypto_exit_check” functional
- New tool “crypto_funding_cost” functional
- New tool “crypto_portfolio_stress” functional
- 25 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
- 9 Sept 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool coverage: 50% → 36% ▼ functional
- Schema quality: 190 → 150 ▲ functional
- New tool “research_network” functional
- 4 Sept 26 0
- Judged manipulation: unverified → pass ▲ security
- Schema quality: unverified → excellent ▲ 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 5 Nov 2026 · Probed https://api.seiche.info/undertow/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=api.seiche.info | CN=YE1,O=Let's Encrypt,C=US | 7 Sept 2026 | 6 Dec 2026 | ECDSA 256 | ECDSA-SHA384 | 51c1896503dd693d96ce81ef09be5a03892 |
| SANs: api.seiche.info | ||||||
| CN=YE1,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 5ddd70dd31f801c85c186a7a04b80afe |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC secure
Validation of api.seiche.info. — Secure
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| info. | present | 9986 | 8 | Verified |
| seiche.info. | present | 2371 | 13 | Verified |
| api.seiche.info. | 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'; frame-ancestors 'none'; base-uri 'none' |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | camera=(), microphone=(), geolocation=(), payment=(), usb=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://api.seiche.info/undertow/mcp | Verified | 200 | |
| http (plaintext) | http://api.seiche.info/undertow/mcp | HTTPS enforced | 308 | https://api.seiche.info/undertow/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 →
agent_access_status Your access + meter ~25
Identity, entitlement, daily usage, access instructions; missing/refused subscriber tools.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
crypto_exit_check Crypto exit sizes and freshness ~55
Four BTC sell sizes by rung/bracket. Withholds stale/future, uncovered or unconverted venues. Fees excluded; no trade clearance.
| Name | Type | Req | Description |
|---|---|---|---|
| max_age_seconds | integer | – | – |
| sizes_usd | array | – | – |
No output schema declared.
No examples provided.
crypto_funding_cost Perpetual funding and fees ~97
Input perpetual funding/fees, net carry, linear break-even. Positive funding: longs pay shorts. Constant-rate scenario, not forecast.
| Name | Type | Req | Description |
|---|---|---|---|
| notional_usd | number | yes | – |
| rate_bps_per_settlement | number | yes | 1 bp = 0.01%; positive rate means longs pay shorts. |
| round_trip_fee_bps | number | – | – |
| settlements | integer | yes | – |
| side | – | yes | – |
No output schema declared.
No examples provided.
crypto_portfolio_stress Stress a crypto portfolio ~58
Linear input shocks, 20 exposures: P&L/equity, asset/venue concentration. Symbols label scenarios. No liquidation/probability model.
| Name | Type | Req | Description |
|---|---|---|---|
| equity_usd | number | yes | – |
| positions | array | yes | – |
No output schema declared.
No examples provided.
depth_episodes Realized depth collapses ~37
BTC depth-collapse onset/trough/recovery under preregistered rules. Zero differs from missing. Subscriber exit_desk_full: ETH.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
exit_cost Exit cost at your size, per venue ~70
BTC nearest-rung sell estimates; interpolated bid-depth bands. Fees excluded; not executable. Sizes/freshness: crypto_exit_check.
| Name | Type | Req | Description |
|---|---|---|---|
| size_usd | number | – | position size in USD (published rungs run $1,000 to $1,000,000; nearest rung is used) |
No output schema declared.
No examples provided.
gold_cash_realisation Gold sale, FX and cash scenario ~219
Gold sale/cash gates from inputs: decimal kg, fineness (0,1], USD/troy-oz bid, USD fees, currency/USD FX (USD=1), aware ISO clocks. Arithmetic and withheld-cash reasons only; no fetch, storage, execution or verified balance.
| Name | Type | Req | Description |
|---|---|---|---|
| access_restricted | boolean | yes | – |
| bid_usd_per_oz | string | yes | – |
| cleared | boolean | yes | – |
| cutoff | string | yes | – |
| fees_usd | string | yes | – |
| fineness | string | yes | – |
| fx_asof | string | yes | – |
| fx_fee_bps | string | yes | – |
| fx_quote_per_usd | string | yes | – |
| fx_valid_until | string | yes | – |
| max_quote_age_seconds | integer | – | – |
| pledged | boolean | yes | – |
| quantity_kg | string | yes | – |
| quote_asof | string | yes | – |
| quote_currency | string | yes | – |
| quote_valid_until | string | yes | – |
| settlement_at | string | yes | – |
No output schema declared.
No examples provided.
latest_article Published editorial ~42
Latest published editorial: title/full text/URL/clock/quality receipt. No args or generated prose. Missing text/failed receipt errors. Board: liquidity_tiers.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
liquidity_tiers Full board: tiers + funding ~38
Nine segment tiers, Seiche funding, measure counts, replay/withholding reasons. PARTIAL: missing history/unpassed replay, never calm.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
market_corpus_context Corpus coverage and source clocks ~66
Corpus coverage/rights/clocks. No summary pagination; other views: records/total/next_offset. Retrieval age is not observation freshness. Readings: liquidity_tiers.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| offset | integer | – | – |
| view | string | – | – |
No output schema declared.
No examples provided.
research_network Connected research ~95
Cross-product metadata, clocks, rights, next steps. Follow next_offset. Unavailable: retrieval/contract/size failure. Local counts: market_corpus_context. No shared score or authority.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Set for full metadata; omission returns 2 compact rows. |
| offset | integer | – | Zero-based page start; follow next_offset. |
| topic | string | – | Catalog topic, not a free-text query. |
No output schema declared.
No examples provided.
sealed_record Sealed calls record (misses kept) ~31
Calls sealed/signed before outcomes: hits/misses, decided counts, ledger root. Report hits and misses together.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
trade_safety_exit_context PIT-bound exact-rung paper exit context ~96
Exact-rung BTC/USD observe/paper: request hash, PIT source/rights, conversion, bid bands, six venue clocks, startup SHA. No live mode/clearance.
| Name | Type | Req | Description |
|---|---|---|---|
| instrument | – | yes | – |
| mode | – | yes | – |
| request_hash | string | yes | Opaque complete-request hash |
| requested_size_usd | number | yes | Exact published USD rung |
| side | – | yes | – |
| venue | null | yes | – |
No output schema declared.
No examples provided.
unwind_watch Can the watched books exit? (free) ~69
Watched-filer headlines: effective positions, days-to-exit brackets, blind spots. No live execution model. Full grids: unwind_stress.
| Name | Type | Req | Description |
|---|---|---|---|
| cik | integer | – | optional: SEC CIK of a watched filer (returns that filer's full FREE row instead of the all-filer headline) |
No output schema declared.
No examples provided.
venue_concentration Depth concentration today ~35
BTC two-sided depth: HHI, effective/top venue, venue depth. Subscriber exit_desk_full: ETH and venue failure.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
venue_price_reconciliation Consensus price when venues disagree ~39
BTC/ETH consensus: depth/squared-half-spread weights, deepest-venue blindness, concentration, dislocations. Experimental; no execution authority.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
How do I install the Undertow market liquidity and exit-cost tools MCP server?
Undertow market liquidity and exit-cost tools is a hosted endpoint at https://api.seiche.info/undertow/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.seiche.info
claude mcp add --transport http beepboop2025-undertow 'https://api.seiche.info/undertow/mcp'
What is the Undertow market liquidity and exit-cost tools MCP server?
Undertow market liquidity and exit-cost tools is an MCP server listed in the public MCP registry as io.github.beepboop2025/undertow. Dated exit evidence, depth, tiers and gold cash scenarios. No executable quotes or trade authority. This page covers its hosted endpoint (https://api.seiche.info/undertow/mcp).
Is the Undertow market liquidity and exit-cost tools MCP server safe to use?
Undertow market liquidity and exit-cost tools scores 86 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 Undertow market liquidity and exit-cost tools MCP server expose?
Undertow market liquidity and exit-cost tools exposes 16 tools: agent_access_status, crypto_exit_check, crypto_funding_cost, crypto_portfolio_stress, depth_episodes, and 11 more. Their descriptions and schemas cost roughly 1,072 tokens of context every time the server is loaded.
Does the Undertow market liquidity and exit-cost tools MCP server require authentication?
No. We connected to Undertow market liquidity and exit-cost tools without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Undertow market liquidity and exit-cost tools MCP server still maintained?
Undertow market liquidity and exit-cost tools is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.