Model Context Protocol (MCP) server for freee API integration
Nothing to run from here
LiqFlow is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
96/100
tool-list score
15
tools declared
remote
at its publisher
—
calls last 7d
What it does
Hyperliquid liquidation levels, whale positions, liquidations, cohorts and funding. Free.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http liqflow-mcp https://liqflow.app/mcp
# 2 — ask your agent for something these tools do
# market_overview, list_markets, open_interest_ranking and 12 more
LiqFlow costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
LIAll 1 server
liqflow1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http liqflow-mcp https://liqflow.app/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
15 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
The whole market in one reading: how many perps lean bullish vs bearish on liquidation pressure, and the markets leaning hardest each way. The score compares short-liquidation exposure ABOVE price (forced buys if price rises) with long-liquidation exposure BELOW it (forced sells if it falls), weighted by distance. Negative = more fuel below, a bearish pull; positive = the reverse. Uses 2 API call
| Parameter | Type | Required | Notes |
|---|---|---|---|
| top | integer | no | How many markets to list on each side |
Market symbols LiqFlow covers, to resolve a name ("solana") to its market symbol (SOL). scored markets also have scores, funding, depth and volume; the rest have node data only (positions, levels, liquidations). Uses 2 API calls.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | no | Filter by symbol or name, e.g. "pepe" or "bitcoin" |
Hyperliquid markets ranked by open interest (USD), with how many positions are open in each, from every wallet on the node.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | — |
Everything about one market right now: live price and 24h change, its liquidation-pressure score, liquidation exposure each side and how close it sits, the nearest big cluster, its rank among all markets, and what changed since the previous snapshot. Start here for any question about one coin. Uses 2 API calls.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| coin | string | yes | Hyperliquid market symbol, e.g. BTC, ETH, HYPE, xyz:SKHX |
Where the forced orders sit around the current price for one market, from every wallet on the node: liquidation prices (longs below = forced sells, shorts above = forced buys), resting stop-loss / take-profit trigger orders, and order-book depth, summed into price bands either side of the mark price, plus the biggest liquidation clusters. This is the "liquidation heatmap" question: where would a
| Parameter | Type | Required | Notes |
|---|---|---|---|
| coin | string | yes | Hyperliquid market symbol, e.g. BTC, ETH, HYPE, xyz:SKHX |
| range_pct | number | no | How far either side of price to map, in % |
| bands | integer | no | Price bands per side |
Perp funding rates. With a coin: the rate on each venue (Hyperliquid, Binance, Bybit, OKX, Bitget, Gate) normalised to 8 hours, plus the open-interest weighted aggregate. Without: the markets paying the most positive and most negative funding right now. Positive = longs pay shorts.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| coin | no | One market; omit for the most extreme rates across all | |
| limit | integer | no | Markets per side when no coin is given |
A metric's history for one market (with the price where the data has it), thinned to at most 60 points.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| coin | string | yes | Hyperliquid market symbol, e.g. BTC, ETH, HYPE, xyz:SKHX |
| metric | string | no | score = liquidation-pressure score; funding = aggregate funding; depth = cross-exchange order-book imbalance; volume = cross-exchange traded volume |
| days | integer | no | — |
Individual Hyperliquid liquidation fills, newest first, straight off the node: who was liquidated, on which market, how big, at what price. One liquidation can be several fills sharing an order id.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| coin | no | One market; omit for all | |
| side | no | Which side was liquidated | |
| min_usd | no | Only fills at least this large | |
| hours | number | no | — |
| limit | integer | no | — |
How much was liquidated. Without a coin: every market ranked by liquidated USD over the window, long vs short. With a coin: long and short liquidations per time bucket. Windows that the node missed are listed under gaps -- those are missing data, not quiet periods.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| coin | no | One market, for a time series; omit for a ranking of markets | |
| hours | number | no | — |
| interval | no | Bucket size for the time series; chosen from hours if omitted | |
| limit | integer | no | Markets in the ranking |
Past sharp moves (at least min_move_pct in one 4-hour step) paired with how much liquidation exposure sat in their path just before -- the evidence for whether clusters actually get run.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| coin | no | Only this market | |
| days | integer | no | — |
| min_move_pct | number | no | Smallest 4-hour move to count |
| sort | string | no | Newest first, or most exposure first |
| limit | integer | no | — |
The largest open positions on Hyperliquid right now, longs and shorts, read live from the node: wallet, size, notional, entry, leverage, liquidation price and how far price is from it, unrealised PnL, and the wallet's size cohort.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| coin | no | One market; omit for the largest on any market | |
| side | no | Omit for both | |
| limit | integer | no | Per side |
One Hyperliquid wallet right now, read live from the node: account value, PnL, every open position with leverage, liquidation price and how far price is from it, and its open orders (limits, stops and take-profits).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| address | string | yes | Hyperliquid wallet address, 0x... |
How different kinds of traders are positioned: wallets grouped by account size (Micro under $250 up to Whale over $1M) and by all-time PnL (Highly Unprofitable to Highly Profitable), with each group's long and short notional and the share that is long. "Are whales and the profitable traders on the other side of retail?" Uses 2 API calls without a coin.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| coin | no | One market; omit for all markets combined |
Which coins one trader cohort is most long and most short on, ranked across every market: "What are the most profitable traders most bullish and most bearish on?" Each coin has the cohort's long and short notional, net USD, share long and wallet count, plus the cohort's overall lean across all markets to compare against. Uses 2 API calls without a side.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cohort | string | no | By all-time PnL: Highly Profitable (over $100k) down to Highly Unprofitable (under -$100k). By account size: Whale (over $1M) down to Micro (under $250). |
| side | no | long: the coins the cohort is most bullish on; short: most bearish on. Omit for both | |
| rank_by | string | no | ratio: by the share of the cohort's notional that is long (conviction). net: by long minus short USD (the biggest bets, which favours BTC and ETH) |
| min_notional_usd | number | no | Skip coins where the cohort holds less than this, long plus short. Without a floor a ratio ranking is all tiny markets where a few wallets are 100% one way |
| limit | integer | no | Coins per side |
Hyperliquid wallets ranked by all-time PnL or by 30-day volume.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| by | string | no | All-time PnL, or 30-day traded volume |
| limit | integer | no | — |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install LiqFlow or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 96 / 100
Release 1.1.0 · scanned 22 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings0 threat · 0 capability
Capabilityminimal
Coveragemanifest
Verificationnot in this report
Surface digeste7cb0483d5b25f9b45742ba6fe9d8b287fa09e36a5475a330911042e04d0dfc7
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| market_overview | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_markets | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| open_interest_ranking | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| coin_snapshot | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| liquidation_map | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| funding | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| coin_history | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| recent_liquidations | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| liquidation_totals | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cascades | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| top_positions | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| wallet | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cohort_positioning | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cohort_top_coins | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| leaderboard | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digeste7cb0483d5b25f9b
Scanned2026-10-22
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.1.0.
1.1.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish LiqFlow can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.