# Undertow MCP | Market liquidity and exit-cost tools

## Connect and ask one question

Hosted Streamable HTTP MCP; no local server or API key for public read-only tools.
Add the products you need to Claude Code:

```sh
claude mcp add --transport http undertow https://api.seiche.info/undertow/mcp
claude mcp add --transport http liquilens https://api.liquilens.in/mcp
claude mcp add --transport http seiche https://api.seiche.info/mcp
```

**Try this first:** What is the estimated exit cost for a $100,000 BTC sell? Compare available venues, snapshot times and excluded costs.

[Try it in your browser](https://liquilens.in/start/?task=exit&size=100000) ·
[Cursor configuration](https://liquilens.in/agents/cursor.json) ·
[Codex commands](https://liquilens.in/agents/codex.txt) ·
[Free three-product starter kit and skill](https://liquilens.in/agents/#connect)

For a connected review, ask for institution evidence → funding context → BTC
exit estimates, with each source date, coverage gap and limitation kept separate.
Client/model costs and fair-use limits may apply. Research calls do not execute trades.

**Endpoint:** `https://api.seiche.info/undertow/mcp` (streamable HTTP, no install)

[![Undertow on AllMCPs](https://allmcps.com/api/badge/undertow-market-liquidity-map-2)](https://allmcps.com/mcp/undertow-market-liquidity-map-2?verify=2089e298-cdac-4926-8727-66e710e1c1fe)

Undertow is the market-liquidity product of **LIQUILENS PRIVATE LIMITED**, a
registered company in India (CIN **U62011RJ2026PTC116792**). One company, three
connected financial-evidence products: LiquiLens investigates institutions,
Seiche explains funding conditions, and Undertow examines market exit evidence.
Together they support a review of an exposure from institution to funding to
liquidity, with each source date, coverage gap and research limit retained.

Built for people and AI agents working internationally. Access is global;
coverage is market-specific. Read the [company and investor story](https://liquilens.in/investors/)
or inspect the [shared company profile](https://liquilens.in/company-profile.json).

**Start with a question:** [Open the crypto workbench](https://liquilens-undertow.com/crypto/).
Choose a dollar size and click to read the current published venue estimates,
snapshot date and method. No account, key, wallet or client installation is
needed for this example. The result is a depth-based estimate, not an executable
quote. The same page provides Codex, Claude Code, Cursor and VS Code setup.

**Try it live:** [liquilens-undertow.com/developers](https://liquilens-undertow.com/developers/) ·
**API catalog:** [api.seiche.info/undertow](https://api.seiche.info/undertow/)

Undertow exposes estimated exit cost by position size and venue, the concentration of
quoted depth, realized depth-collapse episodes, and liquidity tiers across market segments.
This MCP 1.13.0 endpoint exposes 24 read-only tools, split into 16 public and 8 subscriber
tools, plus 3 guided prompts. Its capability inventory is pinned to liquilens-undertow
commit `f103a9929a438f92964e7254edd7553c5a4dfe3a`, the hosted implementation at
`deploy/hetzner/undertow-mcp`. The stdio discovery server in
`undertow_mm/mcp_server.py` is a separate discovery surface; it is neither
this registry listing nor the public stdio adapter provided here.

The `liquidity_tiers` result includes public measure counts, replay eligibility and the published reason a score is withheld. A PARTIAL tier can remain even when every measure qualifies. [Settlement histories and source receipts](https://liquilens.in/agents/#source-data) are available through the separate source-data MCP.

## Add it

Claude Code:

    claude mcp add --transport http undertow https://api.seiche.info/undertow/mcp

Claude.ai / ChatGPT / Cursor: add a custom connector or MCP server with the URL above.
No key and no wallet for the free surface.

The [free agent starter kit](https://liquilens.in/agents/) connects Undertow exit
estimates and venue concentration with Seiche funding context and LiquiLens bank
evidence. Follow the [Hermes](https://liquilens.in/agents/hermes/) or
[OpenClaw](https://liquilens.in/agents/openclaw/) guide for the shared setup. It uses
public tools under fair-use limits; model-provider costs remain separate.

For a recurring research workflow, use the [shared infrastructure setup guide](https://liquilens.in/agents/infrastructure/)
and [current interface catalog](https://beepboop2025.github.io/financial-evidence-skills/agents/system.json).
They distinguish the public research MCPs, the eight-tool Research Desk and
optional private runtimes. Private paper assessment is a separate integration;
Undertow's public tools do not submit orders. Source observation dates, data
rights and eligibility remain explicit even when hosting and backups are healthy.

This repository contains the discovery manifest, documentation and an optional
anonymous stdio adapter for the hosted service. The official registry serves
[`io.github.beepboop2025/undertow` version 1.13.0](https://registry.modelcontextprotocol.io/v0.1/servers/io.github.beepboop2025%2Fundertow/versions/latest).

## Local stdio and container installation

The direct hosted URL above remains the simplest connection. For clients that
require stdio, clone this repository at a reviewed commit and use Python 3.12+
and [uv](https://docs.astral.sh/uv/):

```sh
uv sync --locked
uv run --locked undertow-mcp
```

A Claude Desktop configuration can use `uv` as its command and
`["run", "--directory", "/absolute/path/to/undertow-mcp", "--locked", "undertow-mcp"]`
as its arguments. The stdio adapter exposes only the 16 anonymous tools and
three prompts; subscriber access uses the direct hosted URL instead.

For Docker and Glama's container build:

```sh
docker build -t undertow-mcp .
docker run --rm -i undertow-mcp
```

The root Dockerfile runs as an unprivileged user and starts stdio directly.
No API key, bearer token, wallet, port, volume or environment setting is needed.
Outbound HTTPS access to the fixed `api.seiche.info` endpoint is required.
Redirects, environment proxies and arbitrary upstream URLs are disabled.
Requests are capped at 64 KiB, responses at 2 MiB, and each upstream operation
at 10 seconds including queue wait. No automatic retries or response cache can
hide outages or spend a quota twice. Upstream version/catalog drift fails closed.
Tool results, native `isError` values and rights refusals are preserved.

A Glama maintainer can configure the root Dockerfile, complete its build test,
and publish a Glama release from the listing's admin page. A GitHub commit or
release does not create a Glama release. This repository does not claim a grade
until Glama has actually rescanned and inspected it. See
[Glama's release guide](https://glama.ai/blog/2026-03-15-how-to-make-a-release).

## Hosted protocol compatibility

- `2026-07-28`: stateless requests use `server/discover`, per-request `_meta`,
  `MCP-Protocol-Version`, and mirrored `Mcp-Method` / `Mcp-Name` routing headers.
- `2025-11-25`, `2025-06-18`, and `2025-03-26`: retained legacy initialization,
  tools, prompts, notifications, batching, and ping behavior.
- Discovery identifies all sixteen public and eight subscriber tools. Anonymous
  `tools/list` returns only the public inventory; entitlement is checked fresh on every
  subscriber request.
- `resources/list` and `resources/templates/list` return explicit empty catalogs.
  `resources/read` returns a not-found error and never invents a resource.

## Example

In the snapshot generated at **2026-08-08T15:01:22Z**, selling $1,000,000 of BTC
at the selected **$1,000,000 published size rung** cost **2.386 bp on Binance and
13.623 bp on Bitfinex**: about $238.60 against $1,362.30. Gemini was the dearest
observed venue in that same snapshot at 25.852 bp, or about $2,585.20.

Venue rankings can change during the day, and those differences are not visible in a
single consolidated price. Undertow publishes the observation time and venue inputs with
the estimate.

## Crypto workbench and skills

The [browser workbench](https://liquilens-undertow.com/crypto/) combines published BTC exit comparisons with funding and portfolio scenarios. The scenario forms run locally in the browser.

The [crypto agent kit](https://liquilens-undertow.com/crypto/undertow-crypto-kit.zip) contains three installable skills, a standard-library Python client, offline scenario calculators and a repeatable brief connecting Undertow, Seiche and optional LiquiLens institution evidence. [Exact file digests](https://liquilens-undertow.com/crypto/kit-manifest.json) accompany the download. Nothing runs or installs automatically.

## Tools

| Tool | What it serves | Surface |
|---|---|---|
| `agent_access_status` | Your current tier, daily meter, grants, and the exact route to Agent or Desk access | free |
| `board_full` | Every measure with its stress percentile or ACCRUING label, limits and analyst note | subscriber |
| `corporate_transmission` | Whether funding stress is reaching nonfinancial firms | subscriber |
| `crypto_exit_check` | Compare up to four requested BTC sell sizes across published rungs, with observation clocks and explicit stale/depth gaps; never interpolate a requested size | free |
| `crypto_funding_cost` | Calculate funding, round-trip fees and linear break-even from caller-supplied inputs | free |
| `crypto_portfolio_stress` | Apply caller-supplied price shocks and costs to linear exposures; show equity and gross asset/venue concentration | free |
| `depth_episodes` | Realized depth-collapse episodes with onset, trough, drawdown and recovery, against thresholds declared before any episode accrued | free |
| `divergence_status` | Compact comparison of corporate and household transmission regimes | subscriber |
| `exit_cost` | Per-venue sell cost in basis points at the nearest published size rung, cheapest and dearest venue with approximate dollar cost, and the venue spread | free |
| `exit_desk_full` | BTC and ETH at every published rung, plus the venue-failure withdrawal scenario | subscriber |
| `exit_schedule` | Position-sized hour-by-hour liquidation schedule beside immediate and TWAP baselines | subscriber |
| `gold_cash_realisation` | Caller-input gold sale and FX scenario with separate quote, settlement, access and pledge gates; no verified balance or executable quote | free |
| `household_credit` | Whether funding stress is reaching household balance sheets | subscriber |
| `latest_article` | The exact reviewed daily market-liquidity editorial with its evidence clock and publication authority | free |
| `liquidity_tiers` | A liquidity tier per market segment (UST, IG, HY, equities, ETF, FX, China basin, crypto) with the funding-stress overlay | free |
| `market_corpus_context` | Seiche corpus counts, rights and clocks, with bounded metadata pages; retrieval is not source-observation freshness | free |
| `research_network` | Bounded Palimpsest and Seiche research discovery with source clocks, availability and no blended score | free |
| `sealed_record` | The sealed forward-calls record, hash-chained and signed before outcomes, misses kept | free |
| `tide_clock` | Clock-phase liquidity map and exit-cost-by-phase for BTC or ETH perpetuals | subscriber |
| `trade_safety_exit_context` | Exact-rung BTC/USD sell context with request, PIT, rights, clock and depth checks; unavailable inputs remain unavailable, never order clearance | free |
| `unwind_stress` | Full institutional unwind and forced-sale stress pack | subscriber |
| `unwind_watch` | Banded public watch over institutional unwind time and forced-sale pressure, with exact sensitive quantities withheld | free |
| `venue_concentration` | The BTC depth backbone: top venue share of aggregate depth, HHI, effective venue count, per-venue depth in USD | free |
| `venue_price_reconciliation` | A consensus mark weighted by resting depth over squared half-spread, plus the gap between the deepest venue and consensus | free |

## Prompts

| Prompt | Guided playbook |
|---|---|
| `can_this_book_exit` | Compare watched-book door width, unwind horizon, margin clock, venue concentration, and realized depth collapses |
| `exit_cost_check` | Price a position-sized exit across venues and identify the observed depth limitations |
| `market_liquidity_briefing` | Read the market-level liquidity board, funding overlay, concentration, and current exit-cost evidence together |

Commodity futures are intentionally absent from that table. Undertow has no
licensed point-in-time depth by contract month, venue and session, so
executable commodity exit cost is `CANNOT_ASSESS_EXECUTABLE_EXIT_COST`; open
interest or daily volume is never substituted. For aggregate WTI/Henry Hub
cash pressure, Cushing and benchmark structure, call Seiche's public
`oil_funding_context` or use `/oil` in
[`@seiche_desk_bot`](https://t.me/seiche_desk_bot).

## Limitations

- **PARTIAL is not calm.** A publishable segment needs enough qualifying measures and a passing replay. The response preserves the exact counts and withheld-score reason; qualifying measures alone do not imply a score.
- **Exit costs are estimates**, interpolated from published quote depth at the 1% and
  2% bands. Never a book walk. The snapshot refreshes roughly hourly, so it is a
  snapshot and not a real-time feed.
- **Crypto measures are still accruing**, so the board has not earned a crypto stress
  percentile and you should never quote one from it.
- **The sealed record includes misses.** Calls are hash-chained and signed before
  their outcomes are knowable, then scored against the point-in-time board.
- **Commodity execution is a declared coverage gap.** Ballast is useful upstream
  context from Seiche, not a depth ladder and not an Undertow exit-cost estimate.

Research and market data, not investment advice.

## Subscriber tier

The Agent and Desk tiers unlock the eight subscriber tools. Send `/agent` to the
[Telegram bot](https://t.me/undertow_LiquiLens_bot) to mint a bearer token:

```json
{
  "mcpServers": {
    "undertow": {
      "url": "https://api.seiche.info/undertow/mcp",
      "headers": { "Authorization": "Bearer YOUR_TOKEN" }
    }
  }
}
```

The token proves **identity only**. Entitlement is re-read from live membership on
every call, so access stops when the subscription does rather than when the token
expires. Subscriber tools are invisible to an anonymous `tools/list`, and
`agent_access_status` tells you where you stand.

Only `tools/call` is metered, reported on `X-MCP-Usage-Used`, `X-MCP-Usage-Limit`
and `X-MCP-Usage-Remaining`. `GET /undertow/mcp/usage` is the self-meter. Hitting a
quota returns a normal JSON-RPC result carrying `isError` and an upgrade pointer,
never a dropped connection.

## About this repository

This repo is the **listing**: a README and the two manifests that let directories
describe the server accurately. The server itself is hosted at the endpoint above;
its source is `deploy/hetzner/undertow-mcp` in the
[Undertow product repository](https://github.com/beepboop2025/liquilens-undertow)
and the registry target remains hosted 1.13.0. The adapter forwards the native public schemas and results without computing
market values or granting subscriber access. Its own version is 0.2.0; the
upstream contract is 1.13.0.

## Verification and deployment boundary

The verification workflow validates the exact 40-character `releaseCommit` in
`contract.json` against the immutable source receipt in `source-receipt.json`. The
receipt binds that commit and contract to SHA-256 digests of the hosted implementation
and registry manifest without granting this public repository access to the private
product repository. A maintainer creates or updates the receipt only after running the
local pinned-core verifier against a clean checkout; that verifier derives the
public/subscriber split, prompt inventory, protocol versions, server identity and
registry manifest directly from the source and checks both artifact digests. A branch
name or current product-repository HEAD is never accepted as release provenance.

A separate scheduled and manually dispatchable smoke makes anonymous, read-only calls
to the listed endpoint. It initializes the legacy protocol, exercises modern discovery,
checks the public tools, subscriber advertisement, prompts and explicit empty resource
catalogs, then calls `agent_access_status`. It does not use a bearer token or exercise a
subscriber tool. Run the same checks locally with:

    uv run --locked python -m unittest discover -s tests -v
    python3 scripts/verify_core_pin.py --receipt
    python3 scripts/verify_core_pin.py --core /path/to/exact/core/checkout
    python3 scripts/smoke_live_mcp.py

The source pin is a reviewed **contract boundary**, not an HTTP deployment receipt.
Undertow's release controller records the deployed SHA and append-only receipts on the
host, while the public MCP response currently reports its semantic version and
capability catalog but no exact Git commit. Therefore a green live smoke proves the
published behavior, not that the host runs this exact SHA. Do not repin this listing
from a matching version or catalog alone; require the host's exact successful deployment
receipt (or an equivalent authenticated SHA attestation) first.

## Siblings from the same lab

- [Seiche](https://api.seiche.info/mcp): US dollar funding stress.
- [LiquiLens](https://api.liquilens.in/mcp): bank, NBFC and lender failure risk, and
  whether that stress is reaching firms and households.
- [groundcheck](https://groundcheck.seiche.info): claim grounding and citation
  verification for general text.
- [Palimpsest](https://api.seiche.info/palimpsest/mcp): live internet-censorship
  signals.

Human front door: [liquilens-undertow.com](https://liquilens-undertow.com) and the
[Telegram desk](https://t.me/undertow_LiquiLens_bot).

## License

The original public integration code and documentation in this repository are
[MIT licensed](LICENSE). See [NOTICE.md](NOTICE.md) for scope: this grant does
not cover the private Undertow service or third-party market data. Native
access controls, evidence limitations and source-rights holds still apply.