All release walkthroughs

LIQUILENS · PLUGIN REVIEW EVIDENCE

Undertow

Five public research workflows, shown with actual captured MCP requests and results.

90 seconds · edited browser recording · no audio · no model API calls for this recording.

Inspect the interactive capture viewer · Case transcript · Recording manifest · Underlying service captures

What this demonstrates

The video shows direct calls to the public MCP service and preserves returned source dates, restrictions and unavailable states. It is not a native plugin-installation recording or a new model-routing test. Negative model cases remain unexecuted in this capture.

The product skill and negative model-routing cases are review expectations, not newly executed model tests. No trading, enrollment, collection, private-record access or execution was performed. NoiseFloor examples use synthetic inputs; all other values retain their service-provided dates and restrictions.

Cases shown

  1. Indicative BTC size comparison

    Use Undertow to compare indicative BTC exits for $10,000 and $100,000. Include venue coverage and timestamp limits; do not trade.

    Interpretation boundary: Request sizes_usd [10000,100000], preserve unavailable estimates and distinguish indicative exit evidence from executable quotes.

  2. Liquidity tiers

    Show Undertow's liquidity tiers and explain their coverage and evidence limits.

    Interpretation boundary: Retrieve the published tiers with definitions, dates and source scope; do not convert tiers into a guarantee of execution.

  3. Depth episodes

    Use Undertow to summarize depth episodes for a liquidity research note.

    Interpretation boundary: Return bounded available episodes and source timestamps, flag missing coverage and avoid representing historical episodes as current depth.

  4. Venue concentration

    Review Undertow's venue concentration evidence and list risks an analyst should investigate.

    Interpretation boundary: Report the observed venue coverage and concentration measures with units, dates and limitations; do not infer unsupported private positions.

  5. Venue price reconciliation

    Use Undertow to reconcile public venue-price evidence and flag unresolved differences.

    Interpretation boundary: Keep venue timestamps and units distinct, preserve discrepancies and unavailable prices, and avoid creating a consolidated executable quote.

Endpoint: https://agents.seiche.info/products/undertow/mcp

Video SHA-256: 87cf657662f384e77367ac2fb50f047cd770af5f90604ede166caf1b3daf2cdd

Draft review evidence. This page is not an OpenAI approval or publication receipt.