Skip to content

MCP servers › io.github.ironflowsh › hyperliquid

MCP server · registry snapshot 2026-11-03 · last tested 2026-11-03

io.github.ironflowsh/hyperliquid

Ironflow: Hyperliquid data — the publisher's title

by ironflowsh · GitHub account (the registry's namespace rule)repository: same ownerSource ↗npm ↗

Read-only Hyperliquid data for AI agents: fills, candles, funding, liquidations, wallet analytics. — the publisher's description

6 of 9 record checks metRead-only · tools listed 2026-11-03version 0.11.2TypeScriptMITstandard input/output, streamable HTTP36 tools

Summary

io.github.ironflowsh/hyperliquid is a remote and local MCP server listed in the official MCP registry at version 0.11.2, under the namespace of the GitHub account ironflowsh. Its linked repository, github.com/ironflowsh/mcp, belongs to the same GitHub account. On 2026-11-03 ProtocolProbe connected to it in read-only mode and read its inventory: 36 tools, 0 resources and 0 prompts.

Record checks

6 of 9 record checks met

  • met: Registry entry is active and says how to run it
  • met: Source repository link opens
  • met: Repository is not archived
  • met: Code pushed to the repository in the 90 days before our check
  • not met: Repository publishes a security policy (SECURITY.md)
  • met: Package names its licence with a standard (SPDX) identifier
  • met: The version the registry lists can be installed and is not withdrawn
  • not met: npm package carries build provenance (attestation)
  • not met: No known critical or high advisory in the package or its dependencies
  • #3,117 of 18,234 packages by monthly downloads, tied with 4 others
  • Not ranked by stars: 0 stars (ranked from 10)

From public records, not a safety rating. Each check with its reason · Is it safe to install?

Operate this server? Correct a fact · README badge · Run the checks yourself

Key facts

Runs
remote and local package
Transport
standard input/output, streamable HTTP
Your own values
none declared (not a guarantee)
Sign-in
none needed to open a session
Package
npm · listed version current
License
MIT
Dependencies
2 packages with a critical or high advisory (0 critical, 2 high)
Repository
public
Tools
36
Last tested
2026-11-03

Tool list size

10,519 tokens on Claude Opus 5.5

Added to every request that loads this server's tools (36 tools). Counted with Anthropic's token counter on 2026-11-03, from the tool list we read on 2026-11-03. Median across 25,738 counted servers: 2,858 tokens. How it is counted

How a client gets in

Connects without signing in

Read from the server's public metadata on 2026-11-03 (mcp.ironflow.sh), in our read-only connection; no tool was called. It may have changed since. How it is read

Tool list at the three APIs

Not sent yet for this version (0.11.2).

Add to your client

Worth knowing before you connect it

  • 2 packages with a critical or high advisory (0 critical, 2 high) in its dependencies (as resolved on 2026-11-03).

Each line comes from a section below, with its source and date.

How fresh this is

Live-tested
yes, a real session (not a text-only review)
Last tested
2026-11-03
Mode
read-only (no tool calls)
Latest version
0.11.2, published 2026-11-03 (registry, as of the 2026-11-03 snapshot)
First listed version
2026-11-03 (earliest version still in the registry; older removed versions would be earlier)
Registry data
snapshot 2026-11-03
Package and repository
checked 2026-11-03
Engine
mcp-runtime-engine@0.1.0 · sdk@1.32.0

Dead or stale signals

None found in the records we hold

Looked for and not found: deprecated in the registry; listed version cannot be installed or is withdrawn; repository link does not open; repository archived; no push in over 365 days. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.

Changes since the last refresh

New in the registry: not in the list of 2026-11-02, listed on 2026-11-03 with version 0.11.2 (published 2026-11-03).

Source: the official MCP Registry list on 2026-11-02 and on 2026-11-03.

What it is

What does this server offer?

Observed inventory
36tools
0resources
0prompts

None of its 36 tools are described as changing anything. For 36 the reading was uncertain, so no mark is shown.

  • describe_dataon 2 other servers

    “Returns the SQL tables of Ironflow's Hyperliquid data (every fill, per-wallet daily totals, wallet behaviour labels, funding, mark and oracle prices, open interest, liquidations, builder-code fills, …”

    Publisher declares: read-only yes · open-world yes

    Takes no inputs.

  • “Run one read-only ClickHouse SELECT over Ironflow's Hyperliquid tables (hl.fills, hl.wallet_daily, hl.wallet_behavior, hl.funding, hl.mark_prices, hl.oracle_prices, hl.open_interest, hl.liquidations,…”

    Publisher declares: read-only yes · open-world yes

    2 inputs, 1 required
    • sqlstringrequired“One ClickHouse SELECT (or WITH ...”
    • max_rowsnumber“Most rows to return (default 200, capped by your tier)”
  • get_wallet_behavior

    “How Hyperliquid wallets trade, from their last 30 days: labels (market_maker, high_frequency, whale, directional, consistent_winner, big_loser, revenge_sizing, often_liquidated, hip3_trader, spot_tra…”

    Publisher declares: read-only yes · open-world yes

    5 inputs
    • addressesstring“Comma-separated wallet addresses (up to 50).”
    • labelstring“Only wallets carrying this label”
    • sort_bystring“Sort order when listing (default volume)”
    • min_volume_usdnumber“Only wallets with at least this 30-day volume”
    • limitnumber“Wallets to return (default 20, max 100)”
  • “Latest mark price of one Hyperliquid market as a single number: native perps, HIP-3 builder perps (e.g.”

    Publisher declares: read-only yes · open-world yes

    1 input, 1 required
    • marketstringrequired“Market: BTC-PERP, xyz:NVDA-PERP, HYPE/USDC, or a Hyperliquid name (BTC, @107, xyz:NVDA)”
  • get_recent_tradeson 8 other servers

    “Latest tick-level trades on a Hyperliquid market from our own nodes: price, size, side and block time.”

    Publisher declares: read-only yes · open-world yes

    2 inputs, 1 required
    • marketstringrequired“Market: BTC-PERP, xyz:NVDA-PERP, HYPE/USDC, or a Hyperliquid name (BTC, @107, xyz:NVDA)”
    • limitnumber“Number of trades to return (1-100, default 20)”
  • “OHLCV candles for one Hyperliquid market, built from every trade: open, high, low, close, volume and trade count per candle, oldest first.”

    Publisher declares: read-only yes · open-world yes

    3 inputs, 1 required
    • marketstringrequired“Market: BTC-PERP, xyz:NVDA-PERP, HYPE/USDC, or a Hyperliquid name (BTC, @107, xyz:NVDA)”
    • intervalstring“Candle interval (1m, 5m, 15m, 1h, 4h, 1d).”
    • limitnumber“Number of candles to return (1-500, default 24)”
  • get_funding_rateson 15 other servers

    “Hourly funding rate history for a Hyperliquid perp, including HIP-3 builder perps.”

    Publisher declares: read-only yes · open-world yes

    2 inputs, 1 required
    • marketstringrequired“Market: BTC-PERP, xyz:NVDA-PERP, HYPE/USDC, or a Hyperliquid name (BTC, @107, xyz:NVDA)”
    • limitnumber“Number of funding rate entries (1-100, default 10)”
  • get_open_intereston 7 other servers

    “Latest open interest of one Hyperliquid perp in units of the base asset (BTC for BTC-PERP), with its 24-hour traded volume in USD and the time of the reading.”

    Publisher declares: read-only yes · open-world yes

    1 input, 1 required
    • marketstringrequired“Market: BTC-PERP, xyz:NVDA-PERP, HYPE/USDC, or a Hyperliquid name (BTC, @107, xyz:NVDA)”
  • get_liquidationson 7 other servers

    “Liquidations on a Hyperliquid perp, read from our own nodes: price, size, side and the liquidated wallet.”

    Publisher declares: read-only yes · open-world yes

    2 inputs, 1 required
    • marketstringrequired“Market: BTC-PERP, xyz:NVDA-PERP, HYPE/USDC, or a Hyperliquid name (BTC, @107, xyz:NVDA)”
    • limitnumber“Number of liquidation events (1-100, default 20)”
  • get_liquidation_summary

    “Liquidations on Hyperliquid over a trailing window, totalled across every market or the ones named: count, wallets, notional, longs vs shorts liquidated, the top markets and the largest single liquid…”

    Publisher declares: read-only yes · open-world yes

    3 inputs
    • windowstring“Trailing window.”
    • marketstring“Optional: one market or a comma list (BTC-PERP,ETH-PERP); Hyperliquid names work (BTC, xyz:NVDA)”
    • minutesnumber“Older form of window, rounded up to the next one (90 becomes 4h)”
  • “Every fill for one Hyperliquid wallet, optionally for one market, from indexed history: price, size, side, fee and realized PnL.”

    Publisher declares: read-only yes · open-world yes

    3 inputs, 1 required
    • addressstringrequired“Wallet address (e.g.”
    • marketstring“Optional market filter: BTC-PERP or a Hyperliquid name (BTC, xyz:NVDA)”
    • limitnumber“Number of fills (1-100, default 20)”
  • get_mark_prices

    “Latest mark price, oracle price and current hourly funding rate of one Hyperliquid perp, with the time of the reading.”

    Publisher declares: read-only yes · open-world yes

    1 input, 1 required
    • marketstringrequired“Market: BTC-PERP, xyz:NVDA-PERP, HYPE/USDC, or a Hyperliquid name (BTC, @107, xyz:NVDA)”
Show 24 more tools
  • get_vault_operations

    “Deposits into and withdrawals from one Hyperliquid vault or one depositor.”

    Publisher declares: read-only yes · open-world yes

    3 inputs
    • vaultstring“Vault address (vault or address is required)”
    • addressstring“Depositor address (vault or address is required)”
    • limitnumber“Number of events (1-100, default 20)”
  • get_liquidation_levelson 2 other servers

    “Liquidated notional on a Hyperliquid perp bucketed by price: where longs and shorts were wiped out.”

    Publisher declares: read-only yes · open-world yes

    2 inputs, 1 required
    • marketstringrequired“Market: BTC-PERP, xyz:NVDA-PERP, HYPE/USDC, or a Hyperliquid name (BTC, @107, xyz:NVDA)”
    • bucket_sizestring“Price bucket size (1, 5, 10, 50, 100, 500, 1000, 5000).”
  • get_vault_leaderboard

    “Hyperliquid vaults ranked by net deposits (deposits minus withdrawals) over the last 7 days, with depositor counts.”

    Publisher declares: read-only yes · open-world yes

    1 input
    • limitnumber“Number of vaults (default 10, max 1000)”
  • get_funding_stats

    “Funding statistics per time bucket for a Hyperliquid perp: average, minimum, maximum and annualized rate.”

    Publisher declares: read-only yes · open-world yes

    3 inputs, 1 required
    • marketstringrequired“Market: BTC-PERP, xyz:NVDA-PERP, HYPE/USDC, or a Hyperliquid name (BTC, @107, xyz:NVDA)”
    • intervalstring“Time interval (1h, 4h, 8h, 1d, 7d).”
    • limitnumber“Number of data points (default 7)”
  • get_user_stateon 1 other server

    “Open positions and unrealized PnL for a Hyperliquid wallet right now, across native and HIP-3 perps.”

    Publisher declares: read-only yes · open-world yes

    1 input, 1 required
    • addressstringrequired“0x-prefixed 20-byte hex address”
  • get_user_funding

    “Funding a Hyperliquid wallet paid or received, per market per bucket.”

    Publisher declares: read-only yes · open-world yes

    6 inputs, 1 required
    • addressstringrequired“0x-prefixed 20-byte hex address”
    • marketstring“Optional market filter: BTC-PERP or a Hyperliquid name (BTC, xyz:NVDA)”
    • fromstring“Window start: Unix ms or seconds, or ISO 8601 (2026-10-01T00:00:00Z)”
    • tostring“Window end: Unix ms or seconds, or ISO 8601 (2026-10-01T00:00:00Z)”
    • bucketstring“Aggregation bucket; default 1d”
    • limitnumber“Most recent rows to return (default 200)”
  • get_user_maker_taker

    “Maker vs taker breakdown of a Hyperliquid wallet's fills per market: volume, fees and rebates.”

    Publisher declares: read-only yes · open-world yes

    4 inputs, 1 required
    • addressstringrequired“0x-prefixed 20-byte hex address”
    • marketstring“Optional market filter: BTC-PERP or a Hyperliquid name (BTC, xyz:NVDA)”
    • fromstring“Window start: Unix ms or seconds, or ISO 8601 (2026-10-01T00:00:00Z)”
    • tostring“Window end: Unix ms or seconds, or ISO 8601 (2026-10-01T00:00:00Z)”
  • get_user_ledger

    “Vault deposits, withdrawals and transfers for a Hyperliquid wallet.”

    Publisher declares: read-only yes · open-world yes

    5 inputs, 1 required
    • addressstringrequired“0x-prefixed 20-byte hex address”
    • fromstring“Window start: Unix ms or seconds, or ISO 8601 (2026-10-01T00:00:00Z)”
    • tostring“Window end: Unix ms or seconds, or ISO 8601 (2026-10-01T00:00:00Z)”
    • event_typesstring“Comma-separated type filter (deposit,withdrawal,vault_deposit,vault_withdraw,vault_transfer_in,vault_transfer_out)”
    • limitnumber“Max entries, default 1000, cap 10000”
  • get_pnl_leaderboard

    “Every Hyperliquid wallet ranked by realized PnL, biggest losses or volume over a window.”

    Publisher declares: read-only yes · open-world yes

    4 inputs
    • fromstring“Window start: Unix ms or seconds, or ISO 8601 (2026-10-01T00:00:00Z).”
    • tostring“Window end: Unix ms or seconds, or ISO 8601 (2026-10-01T00:00:00Z).”
    • limitnumber“Number of rows, max 200, default 50”
    • sort_bystring“Ranking metric”
  • get_market_top_wallets

    “Top wallets on one Hyperliquid market by volume or realized PnL, up to 200 rows.”

    Publisher declares: read-only yes · open-world yes

    5 inputs, 1 required
    • marketstringrequired“Market: BTC-PERP, xyz:NVDA-PERP, HYPE/USDC, or a Hyperliquid name (BTC, @107, xyz:NVDA)”
    • fromstring“Window start: Unix ms or seconds, or ISO 8601 (2026-10-01T00:00:00Z).”
    • tostring“Window end: Unix ms or seconds, or ISO 8601 (2026-10-01T00:00:00Z).”
    • limitnumber“Number of rows, max 200, default 25”
    • sort_bystring“Ranking metric”
  • get_markets_snapshot

    “Active Hyperliquid markets ranked in one call: mark price, 24h change, 24h volume, open interest and current hourly funding.”

    Publisher declares: read-only yes · open-world yes

    6 inputs
    • market_classstring“Filter to one class”
    • issuerstring“HIP-3 builder code (e.g.”
    • sort_bystring“Ranking key (default volume).”
    • orderstring“desc (default) or asc”
    • limitnumber“Rows to return (1-200, default 25)”
    • min_volume_usdnumber“Skip markets with less 24h volume than this (USD)”
  • get_user_summaryon 1 other server

    “Totals for one Hyperliquid wallet over a time range (default the last 24 hours): fill count, volume in USD, realized PnL, fees, wins, losses, win rate and maker versus taker share, plus its current a…”

    Publisher declares: read-only yes · open-world yes

    3 inputs, 1 required
    • addressstringrequired“0x-prefixed 20-byte hex address”
    • fromstring“Window start: Unix ms or seconds, or ISO 8601 (2026-10-01T00:00:00Z).”
    • tostring“Window end: Unix ms or seconds, or ISO 8601 (2026-10-01T00:00:00Z).”
  • get_wallet_labels

    “Labels for notable Hyperliquid wallets: top whales by 24h volume, top traders by 30-day realized PnL, vaults and vault leaders.”

    Publisher declares: read-only yes · open-world yes

    3 inputs
    • addressesstring“Comma-separated wallet addresses to look up”
    • whale_top_nnumber“Top N whales to include (max 500, default 100)”
    • smart_top_nnumber“Top N smart-money wallets to include (max 500, default 100)”
  • get_user_pnl_series

    “Realized PnL of one Hyperliquid wallet over time: buckets with realized PnL and fees paid in each, by default daily over the last 30 days.”

    Publisher declares: read-only yes · open-world yes

    4 inputs, 1 required
    • addressstringrequired“0x-prefixed 20-byte hex address”
    • fromstring“Window start: Unix ms or seconds, or ISO 8601 (2026-10-01T00:00:00Z).”
    • tostring“Window end: Unix ms or seconds, or ISO 8601 (2026-10-01T00:00:00Z).”
    • bucket_msnumber“Bucket size in milliseconds: 3600000 for hourly, 86400000 for daily (default)”
  • get_top_traderson 4 other servers

    “Hyperliquid traders ranked across all markets by results over 7, 30 or 90 days: win rate, profit factor, realized PnL, max drawdown and best markets.”

    Publisher declares: read-only yes · open-world yes

    3 inputs
    • windowstring“Lookback window.”
    • sortstring“Ranking.”
    • limitnumber“Number of traders (1-50, default 20)”
  • get_market_leaderson 1 other server

    “The best traders on one Hyperliquid market, ranked by profit factor then win rate, among wallets with at least 5 closed trades there.”

    Publisher declares: read-only yes · open-world yes

    3 inputs, 1 required
    • marketstringrequired“Market: BTC-PERP, xyz:NVDA-PERP, HYPE/USDC, or a Hyperliquid name (BTC, @107, xyz:NVDA)”
    • windowstring“Lookback window.”
    • limitnumber“Number of traders (1-50, default 20)”
  • get_early_movers

    “Wallets whose large orders (at least $10k) on one Hyperliquid market tended to come before price moved their way within 30 minutes, over the last 7 or 30 days.”

    Publisher declares: read-only yes · open-world yes

    3 inputs, 1 required
    • marketstringrequired“Market: BTC-PERP, xyz:NVDA-PERP, HYPE/USDC, or a Hyperliquid name (BTC, @107, xyz:NVDA)”
    • windowstring“Lookback window.”
    • limitnumber“Number of wallets (1-25, default 10)”
  • get_trader_profileon 3 other servers

    “How good and how risky one Hyperliquid trader is over 7, 30 or 90 days, rebuilt from its fills: overall win rate, profit factor, trade count, realized PnL and max drawdown; the same numbers per marke…”

    Publisher declares: read-only yes · open-world yes

    2 inputs, 1 required
    • addressstringrequired“0x-prefixed 20-byte hex address”
    • windowstring“Lookback window.”
  • list_cohortson 3 other servers

    “List available address cohorts: six predefined groups (top_pnl_30d, high_volume_30d, whale_fills, net_withdrawers_7d, liquidation_prone, vault_whales) plus any custom cohorts the caller has created”

    Publisher declares: read-only yes · open-world yes

    Takes no inputs.

  • get_cohort_addresses

    “Wallet addresses in one named cohort: up to 100, each with the value the cohort ranks by (realized PnL in USD for top_pnl_30d, volume in USD for high_volume_30d), and fetched_at, when the cohort was …”

    Publisher declares: read-only yes · open-world yes

    1 input, 1 required
    • namestringrequired“Cohort name from list_cohorts: top_pnl_30d, high_volume_30d, whale_fills, net_withdrawers_7d, liquidation_prone, vault_whales, or a custom cohort you created”
  • “Ironflow service status right now: overall state, data freshness per venue and component health.”

    Publisher declares: read-only yes · open-world yes

    Takes no inputs.

  • get_status_metrics

    “Ironflow performance over rolling windows: API latency and error rate, ingestion lag and synthetic probe timings.”

    Publisher declares: read-only yes · open-world yes

    Takes no inputs.

  • get_status_history

    “Ironflow's own uptime over the last 24 hours (default) or 7 days: points over the period, each with the service status and how fresh the data was in seconds, plus the overall uptime percent.”

    Publisher declares: read-only yes · open-world yes

    1 input
    • periodstring“Lookback window.”
  • “Find how a Hyperliquid market is named: perps (native and HIP-3), spot and live HIP-4 outcomes, with symbol, class, issuer, base asset and Hyperliquid coin.”

    Publisher declares: read-only yes · open-world yes

    7 inputs
    • qstring“Case-insensitive search over symbol, base asset, Hyperliquid coin and issuer”
    • market_classstring“Only this class.”
    • issuerstring“HIP-3 issuer code (e.g.”
    • include_inactiveboolean“Also return closed markets (delisted, settled HIP-4 outcomes), which carry active_to_ms.”
    • limitnumber“Rows per page (default 100, max 100)”
    • cursorstring“pagination.next_cursor from the previous page, with the same filters”
    • sourcestring“Venue.”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-11-03.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).

Counted from the listing

Parameters with a description
100% of 95
Tools with a description
100% of 36
Typical description length
272 characters

The tool set

Counted from the listing

Tools
36
Size of the list
about 17,304 tokens for an agent to load (characters ÷ 4)
Naming
36 of 36 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 0 of 36 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the npm package @ironflowsh/mcp

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below. The command runs the publisher’s code on your machine.

Claude Desktop · claude_desktop_config.json (Settings → Developer → Edit Config)
{
  "mcpServers": {
    "hyperliquid": {
      "command": "npx",
      "args": [
        "-y",
        "@ironflowsh/mcp@0.11.2"
      ]
    }
  }
}
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "hyperliquid": {
      "command": "npx",
      "args": [
        "-y",
        "@ironflowsh/mcp@0.11.2"
      ]
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "hyperliquid": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@ironflowsh/mcp@0.11.2"
      ]
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"hyperliquid","type":"stdio","command":"npx","args":["-y","@ironflowsh/mcp@0.11.2"]}'
Claude Code
claude mcp add --transport stdio hyperliquid -- npx -y @ironflowsh/mcp@0.11.2
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
  "mcpServers": {
    "hyperliquid": {
      "command": "npx",
      "args": [
        "-y",
        "@ironflowsh/mcp@0.11.2"
      ],
      "disabled": false,
      "autoApprove": []
    }
  }
}
Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
  "mcpServers": {
    "hyperliquid": {
      "command": "npx",
      "args": [
        "-y",
        "@ironflowsh/mcp@0.11.2"
      ]
    }
  }
}
OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.hyperliquid]
command = "npx"
args = ["-y", "@ironflowsh/mcp@0.11.2"]
Zed · Zed settings file (command: zed: open settings file)
{
  "context_servers": {
    "hyperliquid": {
      "command": "npx",
      "args": [
        "-y",
        "@ironflowsh/mcp@0.11.2"
      ]
    }
  }
}
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 -- npx -y @ironflowsh/mcp@0.11.2
  • Optional settings the entry also lists (left out above): IRONFLOW_API_KEY.
  • This runs the publisher's code on your machine (npx). Read its README first.
  • The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

From the remote endpoint (Streamable HTTP)

We connected to this URL on 2026-11-03 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste:
https://mcp.ironflow.sh/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
  "mcpServers": {
    "hyperliquid": {
      "url": "https://mcp.ironflow.sh/mcp"
    }
  }
}
VS Code · .vscode/mcp.json
{
  "servers": {
    "hyperliquid": {
      "type": "http",
      "url": "https://mcp.ironflow.sh/mcp"
    }
  }
}
VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"hyperliquid","type":"http","url":"https://mcp.ironflow.sh/mcp"}'
Claude Code
claude mcp add --transport http hyperliquid https://mcp.ironflow.sh/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
  "mcpServers": {
    "hyperliquid": {
      "type": "streamableHttp",
      "url": "https://mcp.ironflow.sh/mcp",
      "disabled": false,
      "autoApprove": []
    }
  }
}
Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
  "mcpServers": {
    "hyperliquid": {
      "httpUrl": "https://mcp.ironflow.sh/mcp"
    }
  }
}
OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.hyperliquid]
url = "https://mcp.ironflow.sh/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
  "context_servers": {
    "hyperliquid": {
      "url": "https://mcp.ironflow.sh/mcp"
    }
  }
}
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://mcp.ironflow.sh/mcp --transport http
  • The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
  • Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
  • The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

Can it be installed, and is it up to date?

Version pin · advisories

Listed version

Registry lists
0.11.2
Latest stable
0.11.2
Status
current
Withdrawn
no

Source: registry.npmjs.org · 2026-11-03. About the version the registry lists; a manual install may resolve to a different one.

Dependency advisories

critical0high2moderate1low0

Counted in the full dependency tree as resolved on 2026-11-03 (npm audit; each bar counts packages with an advisory, not advisories). Bars share one scale. The package itself has no known vulnerability (OSV.dev).

Integrity, provenance, license

Integrity
sha512-LrOCKVKiPxZGa88Lc…
Signature
signed
License
MIT

Source: the package registry · 2026-11-03.

Usage

Downloads
922 in the last month

Source: api.npmjs.org · 2026-11-03.

Does the registry listing match what we found?

Feature #6

The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.

Registry saysWe foundResultSource · date
Remote endpoint mcp.ironflow.sh/mcpSession openedmatchesour test · 2026-11-03
No credential declared as requiredOpened a session without any credentialmatchesour test · 2026-11-03
Version 0.11.2 on npmExists and can be installedmatchesnpm · 2026-11-03
Repository github.com/ironflowsh/mcpOpens publiclymatchesapi.github.com · 2026-11-03

Who made it?

Feature #7 · lineage

Facts about the publisher. We do not turn them into a trust score.

Namespace
io.github.ironflowsh
GitHub owner
an organization (ironflowsh)
Build record
signed
Repository
github.com/ironflowsh/mcp
Stars
0
Repository age
181–365 days
Last push
0–30 days ago
Archived
no
Security policy
none found (we looked for SECURITY.md in the repository and in its owner’s .github repository)

Source: the registry entry and api.github.com · 2026-11-03; security policy read from GitHub · 2026-11-03.

Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.

Choosing

Record checks

Public records · not a safety rating

6 of 9 record checks met

  • #3,117 of 18,234 packages by monthly downloads, tied with 4 others
  • Not ranked by stars: 0 stars (ranked from 10)
  • MetRegistry entry is active and says how to run itActive, with a package or a remote address.
  • MetSource repository link opensThe linked GitHub repository is public.
  • MetRepository is not archivedNot archived.
  • MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
  • Not metRepository publishes a security policy (SECURITY.md)No SECURITY.md in the places GitHub reads it from.What changes this check: GitHub's documentation describes adding a SECURITY.md from the repository's security settings: under Reporting, Security policy, Start setup. GitHub: adding a security policy
  • MetPackage names its licence with a standard (SPDX) identifierMIT
  • MetThe version the registry lists can be installed and is not withdrawnThe listed version exists and is current.
  • Not metnpm package carries build provenance (attestation)Signed by npm, but no build attestation.What changes this check: npm's documentation describes publishing with provenance from a cloud-hosted runner of a supported CI/CD provider, using npm CLI 9.5.0 or newer and npm publish --provenance. npm: generating provenance statements
  • Not metNo known critical or high advisory in the package or its dependencies2 packages in its dependencies with a critical or high advisory (npm audit counts packages, not advisories).What changes this check: npm's documentation describes listing a project's dependency advisories with npm audit and applying compatible dependency updates. npm: npm audit

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-11-03 (security policy 2026-11-03). No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral

Common questions about io.github.ironflowsh/hyperliquid

Answered from the data above

Who publishes io.github.ironflowsh/hyperliquid?

The registry ties the namespace io.github.ironflowsh to the GitHub account ironflowsh; only its owner can publish under it. Its linked repository, github.com/ironflowsh/mcp, belongs to the same GitHub account. These are facts from the registry and GitHub, not a rating.

Is io.github.ironflowsh/hyperliquid safe to install?

We do not rate servers as safe or unsafe. 6 of its 9 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. The listed version is the latest stable release. The package itself has no known vulnerability (OSV.dev). Its full dependency tree has packages with advisories (2 high and 1 moderate; npm audit). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Does io.github.ironflowsh/hyperliquid need an API key or sign-in?

It opened a session without any credential on 2026-11-03. The registry entry declares no required credential; no declaration is not a guarantee.

Has io.github.ironflowsh/hyperliquid been security tested?

Partly. 2 of the 14 checks that apply to it were exercised. We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. This is our choice, not a block by the server. ProtocolProbe publishes no security verdict for a named server.

Does io.github.ironflowsh/hyperliquid publish a security policy?

We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.

Is the listed version current?

Yes. The registry lists 0.11.2, the latest stable release on npm.

Where is the source code of io.github.ironflowsh/hyperliquid?

In github.com/ironflowsh/mcp, which opens publicly.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Not probed (we call no server's tools)

We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. This is our choice, not a block by the server. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-11-03
  1. Inventory: exercised
  2. Hidden instructions: exercised
  3. Real execution: not run · our policy
  4. Secret leak: not run · nothing to check it against
  5. Internal addresses: not run · our policy
  6. Unconfirmed changes: not run · our policy
  7. Bad input: not run · our policy
  8. Model requests: not run · nothing to check it against
  9. Sensitive questions: not run · nothing to check it against
  10. Folder boundary: not run · our policy
  11. Log leaks: not run · nothing to check it against
  12. Hidden content: not run · nothing to check it against
  13. Fake assistant turns: not applicable
  14. Token passthrough: not applicable
  15. Token audience: not applicable
  16. Sign-in redirect: not run · our policy
  17. Consent handling: not testable from outside
  18. Sign-in metadata: not applicable

2 exercised12 not run (reason given)4 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 14 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 2
  • 1Inventory
    tool-list
    Reads the declared tools, resources and prompts.exercised
  • 2Hidden instructions
    description-poisoning
    Looks for hidden instructions in tool descriptions.exercised
Not run, with the reason · 12
  • 3Real execution
    real-execution
    Calls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 4Secret leak
    canary-leak
    Plants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 5Internal addresses
    ssrf
    Checks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 6Unconfirmed changes
    write-without-confirmation
    Checks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 7Bad input
    error-handling
    Sends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 8Model requests
    sampling
    Checks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 9Sensitive questions
    elicitation-sensitive-data
    Checks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 10Folder boundary
    root-boundary
    Checks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
  • 11Log leaks
    logging-side-channel
    Checks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
  • 12Hidden content
    audience-hiding
    Checks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against
  • 16Sign-in redirect
    open-redirect
    Checks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy
  • 17Consent handling
    confused-deputy
    Checks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
Does not apply to this server · 4
  • 13Fake assistant turns
    fake-assistant-turn
    Checks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
  • 14Token passthrough
    token-passthrough
    Checks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable
  • 15Token audience
    token-audience-validation
    Checks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable
  • 18Sign-in metadata
    oauth-url-scheme
    Checks the published sign-in metadata for unsafe URLs.No sign-in (OAuth) metadata is published, so there are no sign-in addresses to check.not applicable

Source: our own test, 2026-11-03, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

  1. 0 msStarted a read-only session with the server's remote endpoint
  2. 1,721 msConnected after 0 redirects. No credential was sent or needed.
  3. Read the inventory: 36 tools, 0 resources, 0 prompts.
  4. 6,274 msFinished: 2 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified
pending: added in the weekly update
listed 2026-11-03; not classified yet
Pricing modelAI-classified
not checked
no website in the registry entry
Programming language
api.github.com · 2026-11-03
Hosting type
registry · 2026-11-03
MCP capability
tools
our test · 2026-11-03
Transport
standard input/output, streamable HTTP
registry · 2026-11-03
Required credentials
none declared
registry · 2026-11-03 · no declaration is not a guarantee
Package registry
registry · 2026-11-03
Freshness
0–30 days
registry updatedAt · 2026-11-03
Lifecycle status
registry · 2026-11-03
License class
package registry · 2026-11-03
Integrity hash
declared (sri)
package registry · 2026-11-03
Signature / provenance
signed
package registry · 2026-11-03
Dependency advisories
high
npm audit · 2026-11-03
Popularity
922 downloads a month
package registry · 2026-11-03
Publisher signals
owner: an organization · repository age: 181–365 days · stars: 0–9 · build record: signed
api.github.com · 2026-11-03
Maintenance
api.github.com · 2026-11-03
Environment
either (remote or your machine)
where it runs, from the hosting type · 2026-11-03

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “io.github.ironflowsh/hyperliquid: MCP server record.” Data checked 2026-11-03. https://protocolprobe.com/mcp/servers/io.github.ironflowsh/hyperliquid

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

ProtocolProbe: 6 of 9 record checks met

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/io.github.ironflowsh/hyperliquid)](https://protocolprobe.com/mcp/servers/io.github.ironflowsh/hyperliquid)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.

Write to hello@protocolprobe.com · corrections log · methodology