Hyperliquid / HyperEVM MCP server

hyperevm-mcp

Ask your AI assistant about the Hyperliquid ecosystem in plain English. It reads. There is nowhere to put a private key, and that is the whole security model.

"what's the best HYPE yield right now"

Network HYPE staking APR: 1.80%–2.25% across 27 active validators.
Anything far above this is a reward or a risk premium.

## Liquid staking (HYPE LSTs)
| Protocol       | Token |   APY |  7d |     TVL |
| -------------- | ----- | ----: | --: | ------: |
| Kinetiq kHYPE  | KHYPE | 1.94% | n/a | $825.9M |
| stHYPE         | —     |   n/a | n/a | $173.9M |
| Kinetiq kmHYPE | —     |   n/a | n/a |  $36.1M |

## Lending markets
| Protocol         | Asset | Supply | Borrow |  Util | Max LTV |    TVL |
| ---------------- | ----- | -----: | -----: | ----: | ------: | -----: |
| HyperLend Pooled | USDC  |  5.84% |  7.36% | 88.2% |   62.0% | $12.1M |
| HyperLend Pooled | USD₮0 |  5.15% |  7.94% | 72.2% |   62.0% |  $1.8M |
| HyperLend Pooled | WHYPE |  0.61% |  0.98% | 78.0% |   60.0% | $42.1M |

## Other HYPE yield (LP, looping, fixed-term)
| Protocol     | Pool                  |    APY |  Base |       7d |   TVL | IL  |
| ------------ | --------------------- | -----: | ----: | -------: | ----: | --- |
| nest CL      | WHYPE-USDC (0.0638%)  | 38.80% |   n/a |  +0.33pp | $5.9M | yes |
| nest CL      | WHYPE-UBTC (0.2%)     | 32.78% |   n/a |  -9.93pp | $1.7M | yes |
| Ramses CL V2 | WHYPE-

Four of those cells read n/a. That is the point: stHYPE publishes no yield pool, and kHYPE's weekly delta came back from the source implying the pool paid nothing seven days ago, which its own daily history contradicts. A number we cannot stand behind is not printed.

The vault row shows the same rule twice over. HLP has no pool on DefiLlama at all, so a table built from that source alone silently omits the largest single place to deposit on the chain — it is read from Hyperliquid instead. And Hyperliquid's own APR field for it is not shown, because the same value means one thing as an annual rate and something 365 times larger as a daily one, and the vault's history does not settle which. What is shown is realised profit and loss per window, divided here, where the arithmetic is ours to defend.

Then ask whether to believe one of those rates:

"has that Ramses WHYPE-USDC pool actually been paying 100%?"

## Pool history
Pool:                   WHYPE-USDC
Project:                Ramses CL V2
APY now:                16.86%
APY 7d ago:             144.75%
APY 30d ago:            107.77%
Earned vs emitted now:  0.00% earned · 16.86% emitted
TVL change over window: -10.7%

| Date (UTC) |     APY | Earned | Emitted |   TVL |
| ---------- | ------: | -----: | ------: | ----: |
| 2026-06-27 | 107.77% |  0.00% | 107.77% | $1.9M |
| 2026-07-09 |  70.09% |  0.00% |  70.09% | $2.0M |
| 2026-07-21 |  58.80% |  0.00% |  58.80% | $1.8M |
| 2026-07-26 |  16.86% |  0.00% |  16.86% | $1.7M |

Zero earned, every day, for a month.

Install

Claude Code

claude mcp add hyperevm -- npx -y @sand0vvv/hyperevm-mcp

Cursor, Claude Desktop, or any MCP client — add to the config file:

{
  "mcpServers": {
    "hyperevm": {
      "command": "npx",
      "args": ["-y", "@sand0vvv/hyperevm-mcp"]
    }
  }
}

That is the whole setup. Nothing to fill in afterwards — there is no account to authenticate against.

Try asking

Shortened. The full README is on GitHub.