hyperevm-mcp

Name: hyperevm-mcp
Author: sand0vvv

by sand0vvv

Overview Schema Related Servers Score Discussions

TypeScript

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-USDC (CL 0.11%) | 30.14% | 0.00% | -29.96pp | $1.8M | yes |

## Protocol vaults
| Vault                         |     TVL |     24h |      7d |     30d |
| ----------------------------- | ------: | ------: | ------: | ------: |
| Hyperliquidity Provider (HLP) | $225.7M | -0.003% | +0.010% | -0.024% |

Note: 3 of the rows above are mostly token emissions rather than earned yield.
Compare the APY and Base columns — emissions stop when the issuing team
decides they stop.

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.

Related MCP server: 0xarchive-mcp

Try asking

what's the best HYPE yield right now
compare lending rates on HyperEVM
which HYPE pools are just token emissions and which actually earn
has that 40% APY held up, or is it decaying
is BTC funding actually stable, or was that one hour
who earns the most fees on this chain
could I actually get out of $500k of HYPE
which protocols grew this week
tell me about HyperLend
what's in this wallet: 0x…
where should I stake HYPE and what does the commission cost me

Tools

Nine tools. Five report the present, three report how it got there, one reads an address.

Tool	What it answers
`hyperevm_yields`	Every yield on HYPE in one table: liquid staking, lending with supply/borrow/utilisation/max LTV, LP and looping, and the HLP vault — with earned yield separated from token emissions
`hyperevm_protocols`	What is deployed on HyperEVM: chain TVL, per-protocol TVL, 1d/7d change, sortable by size or weekly growth; a detail card for any one protocol
`hyperevm_fees`	Fees users actually paid, ranked over 24h/7d/30d. TVL says how much money sits somewhere; this says whether anyone is paying to use it
`hl_market`	Perp mark price, funding hourly and annualised, open interest, 24h volume; spot pairs; predicted funding across Hyperliquid, Binance and Bybit
`hl_staking`	HYPE validators ranked by predicted APR, with commission, uptime and stake share — what the network pays before any wrapper takes its cut
`hyperevm_pool_history`	One pool's APY and TVL over weeks, split into earned versus emitted — so a headline rate can be checked against its own history
`hl_funding`	How funding actually behaved over days: average, range, how much of the time it held its sign, and what the position would have paid
`hl_orderbook`	Spread and resting depth, and whether a given trade size fills inside the visible book — or a plain statement that it does not
`hyperevm_wallet`	Any public address: account value, open positions with entry, unrealised PnL and liquidation price, spot balances, HYPE staking

The pairs are deliberate. hyperevm_yields and hl_market tell you what a number is now; hyperevm_pool_history and hl_funding tell you whether to believe it. A 47% pool that has been 100% emissions for a month and a 20% pool earning fees are not the same product, and only the second pair can tell them apart.

Slash commands

The server also ships MCP prompts, which appear as slash commands in Claude Code:

Prompt	What it does
`yield-report`	Staking, liquid staking, lending and LP in one pass, ranked with emissions called out
`protocol-brief`	One protocol: size, mechanics, where its yield sits, how it compares
`wallet-review`	A public address: exposure, funding cost per day, idle balances
`funding-scan`	Where Hyperliquid funding diverges from Binance and Bybit

What this server does not do

It has no write path. Not "disabled by default" — the code to sign or send anything does not exist.

Nothing here can move money. The code that would sign a transaction is not in this package.
Nothing to configure either: the server reads no environment variables, so there is nothing to leak.
The filesystem is never touched, no process is ever started, and no telemetry leaves the machine.
Talks to exactly four hosts, hardcoded in src/core/http.ts: api.hyperliquid.xyz, api.llama.fi, yields.llama.fi, rpc.hyperliquid.xyz. No tool takes a URL, host or chain as a parameter.

None of that is a promise — it is a test. npm run audit checks every line above against the source and exits non-zero if one stops being true; it runs in CI before publish. Adding a fs import or a second network host fails the build rather than reaching you:

$ npm run audit
capability
  ok    does not read or write the filesystem
  ok    does not spawn processes
  ok    does not open raw sockets or listen
  ok    does not evaluate code at runtime
  ok    reads no environment variables — there is nothing to configure
  ok    no crypto, signing or key handling anywhere
network surface
  ok    contacts exactly 4 hosts, all hardcoded
  ok    no tool accepts a URL, host or endpoint as a parameter
  ok    every outbound call goes through the allowlisted fetch wrapper
type-level guarantee
  ok    the Safe escape hatch exists in exactly one file
  ok    renderers accept only Safe text, so unsanitised output cannot compile
  ok    prompts are authored here, never assembled from network data
data handling
  ok    never reads free-text descriptions from upstream
  ok    stdout carries the MCP protocol only
  ok    every tool answers through the envelope, including on failure
supply chain
  ok    no install-time lifecycle scripts
  ok    exactly 2 direct dependencies
  ok    published tarball contains build output only

every claim in the README is enforced here

The whole server is a few thousand lines of TypeScript. It is meant to be read before you install it.

Three details worth knowing

Lending rates are not where they look like they are. DefiLlama's /pools reports 0.00% for collateral markets — truthfully, since their supply rate really is zero. The rate lives in a second endpoint, /lendBorrow, joined on the pool id. A naive integration prints a table of zeros over a $239M market. This one joins them and shows supply, borrow and utilisation separately.

Missing data is shown as missing. stHYPE ($172M) and beHYPE publish no yield pool on DefiLlama, so their APY appears as n/a next to their real TVL, with the network staking APR printed above as a reference. A zero standing in for "unknown" would be the most expensive thing this tool could print.

Emissions are not yield. The top pools by headline APY are often paying entirely in their own token. The table carries a Base column next to APY, so 48.86% / base 0.00% reads as what it is, and a note names the rows where most of the number is emissions. The 7d column shows the same thing over time: that pool's APY fell 30 percentage points in a week.

Third-party text and prompt injection

This server is read-only and cannot act. But it carries text written by strangers into your agent's context, next to whatever else that agent can do — a wallet, a shell. Validator names on Hyperliquid are free text set by whoever runs the validator; DefiLlama protocol names come from pull requests. So the text is treated as hostile, in three layers.

1. Fields that are not needed are never read. description — 445 characters of free text on a validator, 599 on a DefiLlama protocol — is not parsed anywhere in the code. The audit fails the build if that changes.

2. An allowlist, not a blocklist. Everything printed passes a filter that keeps letters, digits, currency signs and a short list of punctuation, and drops everything else. Not a list of bad sequences to catch — a list of what may pass. So <|im_start|>, [INST], ###, {{, backticks and table pipes cannot survive, because the characters that build them are not on the list. Input is NFKC-normalised first, so full-width lookalikes fold to ASCII before the filter rather than after.

3. The type system, not discipline. Sanitised text has its own type. The renderers accept nothing else, so printing a raw upstream field is a compile error rather than a code-review miss. There is exactly one place where that type can be created from a plain string, and the audit fails the build if a second appears.

A test feeds a poisoned upstream response — chat-template markers, a javascript: URL, an injected instruction, a fence in the slug — through a real tool and asserts that none of it reaches the output in a form that can do anything.

What this does not do: it cannot stop plain English. A validator named "ignore previous instructions" still reads as those words. The answers to that are the field whitelist, the 24-character cap, and the fact that this server exposes no action for such a sentence to trigger — not a cleverer filter. Anyone claiming a filter solves prompt injection is selling something.

Details in SECURITY.md.

Requirements

Node 20 or newer. Two direct dependencies: @modelcontextprotocol/sdk and zod. (The SDK brings its own tree, as it does for every MCP server; nothing else is added on top.)

Development

npm install
npm test          # build, unit tests, behaviour checks — runs offline
npm run verify    # the above plus the self-audit and a real MCP handshake

Individually:

npm run build
node scripts/test.mjs           # units: numbers, tables, the sanitiser, the cache
npm run check     # behaviour: injection end-to-end, allowlist, retry, stale fallback, outage
npm run audit     # enforces every claim in this README against the source
npm run preflight # fails if this repository contains anything that should not be public
npm run smoke     # every tool against the live public APIs
npm run stdio     # spawn the server and speak MCP to it

The unit tests cover the parts that decide what a reader sees: that "unknown" renders as n/a and never as 0, that percentage points and percentages stay different units, that a cell cannot forge a table column, that a failed refresh serves the previous answer and says so. The behaviour checks drive poisoned upstream responses through whole tools.

Disclaimer

Unofficial and community-built. Not affiliated with Hyperliquid or with any protocol listed. Data comes from public APIs and may be delayed or wrong; DefiLlama refreshes roughly every 30 minutes. When a refresh fails the previous answer is served with a visible "REFRESH FAILED, this is N min old" label rather than an error — old data is useful, old data pretending to be fresh is not. Not financial advice.

MIT © sand0vvv

Available Tools

8 tools

hl_fundingFunding historyA

Read-onlyIdempotent

Funding rate history for one Hyperliquid perp — how the rate actually behaved over the past days, not just its value right now: average, range, how much of the time it stayed positive, and what holding the position would have paid. Includes the current predicted rate on Binance and Bybit for comparison. Use this when the question is whether a funding spread is durable rather than what it is this hour. Read-only, public data, no API key.

ParametersJSON Schema

Name	Required	Description	Default
`days`	No	How far back to look. Default 7, maximum 14.
`symbol`	Yes	Perp symbol, e.g. BTC or HYPE.

TDQS

A4.5/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint, openWorldHint, etc., but the description adds context: includes Binance/Bybit comparison, historical behavior details. No contradiction with annotations. Slightly reduced because annotations already cover safety profile.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded paragraph of four sentences. Every sentence provides essential information without redundancy, making it efficient and easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, but description sufficiently explains return data (average, range, positivity, holding cost, Binance/Bybit comparison). For a read-only data retrieval tool with strong annotations, this is complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, baseline 3. The description does not add extra meaning beyond the schema—it only implicitly mentions 'how far back' which is already described in the schema. No additional semantic value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it provides funding rate history for a Hyperliquid perp, specifying metrics like average, range, positivity, and holding cost. It distinguishes from just current rate by highlighting historical behavior, which differentiates it from siblings like hl_market.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly advises 'Use this when the question is whether a funding spread is durable rather than what it is this hour.' Also states it is read-only, public data, no API key needed, providing clear when-to-use and preconditions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

hl_marketHyperliquid marketsA

Read-onlyIdempotent

Prices and market state on Hyperliquid right now: perp mark and oracle price, 24h move, funding (hourly and annualised), open interest, volume and max leverage, plus spot pair prices. Pass a symbol for one market with predicted funding on Hyperliquid, Binance and Bybit side by side. This is the current snapshot; for how funding behaved over past days use hl_funding. Read-only, public data, no API key.

ParametersJSON Schema

Name	Required	Description
`limit`	No	Rows in the list. Default 10.
`market`	No	Which book to read. Default perp.
`symbol`	No	Market symbol, e.g. BTC or PURR. Omitted = top by volume.

TDQS

A4.6/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false. The description adds context: 'Read-only, public data, no API key,' which reinforces safety and accessibility. It also describes the output fields (prices, funding, OI, etc.) beyond what annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, each purposeful: first lists what the tool returns, second explains how to use with a symbol, third gives temporal context and links to alternative. Front-loaded with essential information, no unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description adequately covers return data, usage patterns, and alternative tool. It could mention pagination or sorting but those are minor. With strong annotations, this is sufficiently complete for a read-only data query tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions. The description adds value by providing examples (e.g., 'BTC or PURR') and clarifying default behaviors ('Rows in the list. Default 10,' 'Default perp,' 'Omitted = top by volume'). This goes beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it provides current prices and market state on Hyperliquid for perp and spot, listing specific data points. It distinguishes itself from the sibling hl_funding tool by noting it is a current snapshot versus past funding behavior.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly tells when to use: for current snapshot, and when not: for past funding data, directing to hl_funding. Also explains behavior when symbol is omitted (top by volume) and when symbol is provided (shows predicted funding side by side with Binance and Bybit).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

hl_orderbookOrder book depthA

Read-onlyIdempotent

Resting order book depth for one Hyperliquid market: spread, top of book, and how much size sits on each side. Pass size_usd to walk the book for that trade and get the average fill price and slippage — or a clear statement that the visible book is not deep enough to answer, which is common for large sizes. Answers "can I actually get in or out at this size", which price and volume alone do not. Read-only, public data, no API key.

ParametersJSON Schema

Name	Required	Description
`market`	No	Which book to read. Default perp.
`symbol`	Yes	Market symbol, e.g. HYPE or BTC. For spot pass the pair, e.g. PURR/USDC.
`size_usd`	No	Trade size in USD to simulate against the book. Omitted = depth summary only.

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (readOnlyHint, idempotentHint), the description adds that the tool is public and requires no API key. It also explains the behavior when size_usd is provided, including walking the book and returning slippage or a depth insufficiency statement.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, each adding value. It front-loads the purpose, explains the key parameter behavior, and states the use case. No redundant words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description conceptually covers the outputs (spread, top of book, side sizes, fill price, slippage). It lacks exact format details, but for a market data tool, this is nearly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description adds significant meaning: for size_usd, it explains the trade simulation and output; for market, it notes the default is perp. This enhances understanding beyond the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool provides resting order book depth, including spread, top of book, and side sizes. It distinguishes itself from price and volume alone, making its purpose precise and actionable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use it: to assess trade feasibility ('can I actually get in or out at this size'). While it doesn't explicitly list alternatives, the context is clear and sufficient for correct usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

hl_stakingHYPE stakingA

Read-onlyIdempotent

Staking HYPE directly with a validator: the active set ranked by predicted APR, with each one's commission, uptime and share of stake, and jailed validators named but excluded. This is what the network pays before any liquid staking wrapper takes its cut, so it is the benchmark every kHYPE or stHYPE rate should be judged against — those live in hyperevm_yields. Read-only, public data, no API key.

ParametersJSON Schema

Name	Required	Description	Default
`limit`	No	Validators to show. Default 15.
`include_inactive`	No	Include jailed and inactive validators. Default false.

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds context: it's public data, no API key, and details what data is returned (active set, jailed excluded, etc.), which goes beyond annotations. No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences with no wasted words. It front-loads the core purpose and efficiently provides context about why to use this tool vs liquid staking. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, the description explains what the tool returns (active set sorted by APR, commission, uptime, share of stake, jailed excluded). It contrasts with liquid staking yields. With good annotations and sibling differentiation, the description is fully adequate for a read-only list tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the two parameters, each with descriptions in the schema. The tool description does not add additional meaning beyond the schema, but the baseline is 3 due to high coverage. The description focuses on output context rather than parameter details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it is about staking HYPE directly with a validator, listing active set ranked by predicted APR with commission, uptime, share of stake, and naming jailed validators. It distinguishes from liquid staking wrappers via mention of hyperevm_yields, making the purpose specific and differentiated from siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says this is the benchmark for liquid staking rates and those live in hyperevm_yields, providing clear guidance on when to use this tool vs alternatives. It also states it is read-only public data with no API key.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

hyperevm_feesHyperEVM feesA

Read-onlyIdempotent

Fees actually paid to protocols on Hyperliquid, over 24h, 7d and 30d, ranked. TVL shows how much money sits somewhere; fees show whether anyone is paying to use it, so the two rankings often disagree. Pass a name for one protocol's fee line. Read-only, public data, no API key.

ParametersJSON Schema

Name	Required	Description	Default
`name`	No	Protocol name, e.g. "Hyperliquid Perps". Omitted = ranked list.
`limit`	No	Rows in the list. Default 12.

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint false. Description adds context: 'Read-only, public data, no API key' and explains the semantics of fees vs TVL. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences, front-loaded with purpose, no unnecessary words. Each sentence adds value: purpose, comparison, usage, and safety note.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given simple tool with rich annotations and full schema coverage, description covers data scope and usage. No output schema, but return values are self-explanatory (fee lines). No mention of pagination or errors, but adequate for the tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers both parameters fully (100% description coverage). Description adds minimal extra meaning: clarifies that omitting name yields ranked list. No additional syntax or constraints beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool lists fees paid to protocols on Hyperliquid over three time periods, ranked. It distinguishes from sibling tools like hyperevm_yields by contrasting fees vs TVL, and the name parameter aligns with the resource 'protocols'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear usage: pass a protocol name for a single line, omit for ranked list. Mentions read-only, public data, no API key. Does not explicitly state when to prefer this over alternatives, but the contrast with TVL gives implicit guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

hyperevm_protocolsHyperEVM protocolsA

Read-onlyIdempotent

What is deployed on Hyperliquid / HyperEVM and how big it is: every protocol's TVL on this chain, its category, and how that TVL moved over 1 and 7 days, plus the chain total. Sort by size or by weekly growth. Pass a name for a detail card with audit links, site and socials. Read-only, public data, no API key.

ParametersJSON Schema

Name	Required	Description
`name`	No	Protocol name or slug, e.g. HyperLend. Omitted = ranked list.
`sort`	No	Order of the list: "tvl" for the largest (default), "growth_7d" for the fastest growing.
`limit`	No	Rows in the list. Default 15.

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only, idempotent, non-destructive. Description adds 'Read-only, public data, no API key,' reinforcing safety and accessibility. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with purpose, each sentence adds value. No redundancy, perfectly sized.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers input and output expectations (TVL, growth, chain total, detail card). Lacks explicit return format, but given parameter simplicity and annotations, it's sufficiently complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers 100% of parameters. Description adds functional context: name triggers detail card with audit links, sort options map to enum, limit default is 15. Enhances rather than repeats.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists protocols on HyperEVM with TVL, category, growth, and chain total, with sorting and detail card options. It distinguishes from siblings like hyperevm_yields or hl_market.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains when to use (get protocol data) and how to use (omit name for list, specify name for detail, choose sort order). It lacks explicit when-not-to-use or alternative comparisons, but context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

hyperevm_walletHyperliquid walletA

Read-onlyIdempotent

Look up what any public Hyperliquid address holds: account value, margin, open perp positions with entry price, unrealised PnL and liquidation price, spot balances, and delegated HYPE. Works on any address, including one that is not yours — this reads the public ledger, and the server has no key, no signature and no send path with which to act on an address.

ParametersJSON Schema

Name	Required	Description	Default
`limit`	No	Positions and balances to show. Default 10.
`address`	Yes	Public Hyperliquid address, e.g. 0x0000000000000000000000000000000000000000

TDQS

A4.3/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint false), the description adds critical context: it reads the public ledger, no key/signature/send path, ensuring agents understand it is purely observational and safe. This fully satisfies the transparency requirement.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single paragraph that front-loads the action and efficiently lists returned data. It is concise without being terse, though structured bullet points could improve readability slightly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description comprehensively covers the tool's purpose, usage constraints, and behavioral traits given its low complexity and rich annotations. It lacks an explicit output schema description but lists returned fields sufficiently for agent understanding.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents both parameters (address, limit). The description does not add extra meaning for parameters beyond listing what data is returned. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Look up what any public Hyperliquid address holds' and enumerates specific data returned (account value, margin, positions, etc.). It distinguishes itself from sibling tools like hl_market or hyperevm_yields by focusing on wallet holdings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states it works on any address and explains the read-only nature ('the server has no key, no signature and no send path'), implying when to use (lookup) and when not to (actions requiring write). However, it does not directly reference sibling tools as alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

hyperevm_yieldsHyperEVM yieldsA

Read-onlyIdempotent

Every way to earn on Hyperliquid / HyperEVM, ranked in one table: liquid staking tokens (kHYPE, stHYPE, beHYPE), lending markets with supply and borrow rates, utilisation and max LTV, and LP or looping pools. Separates yield a pool earns from yield paid in emitted tokens, and anchors everything against what the network itself pays for staking. Start here for "where is the best yield"; use hyperevm_pool_history to see whether one of these rates has held. Read-only, public data, no API key.

ParametersJSON Schema

Name	Required	Description
`limit`	No	Rows per section. Default 10.
`min_tvl`	No	Minimum pool TVL in USD. Default 1000000.
`category`	No	lst = liquid staking, lending = money markets, other = LP/looping/PT, all = everything (default)

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, openWorld, idempotent, non-destructive. Description reinforces with 'Read-only, public data, no API key' and explains data structure and separation of yield types, adding value beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences, front-loaded with core purpose, no wasted words. Efficiently conveys purpose, categories, usage guidance, and data characteristics.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, description covers expected output (ranked table with categories, yield separation). Mentions alternative tool. Lacks exact column names but sufficient for an agent to understand what the tool returns.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear parameter descriptions. The tool description sets overall context but does not add individual parameter details beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists all yield opportunities on Hyperliquid/HyperEVM, ranked, covering specific categories (LSTs, lending, LP/looping). It distinguishes from siblings like hyperevm_pool_history (mentioned) and by context from hyperevm_protocols, hl_market, hl_staking.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says 'Start here for where is the best yield' and suggests hyperevm_pool_history for historical verification. Also notes it's read-only, public, no API key, giving clear usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

8 tool updatesv1.4.0Jul 26, 2026
- First observedhl_funding
- First observedhl_market
- First observedhl_orderbook
- First observedhl_staking
- First observedhyperevm_fees
- First observedhyperevm_protocols
- First observedhyperevm_wallet
- First observedhyperevm_yields

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.6/5.0

Disambiguation5/5

Each tool targets a distinct aspect of the Hyperliquid/HyperEVM ecosystem: yields, protocols, market prices, staking, wallet info, fees, funding history, and order book. There is no overlap, and descriptions clearly differentiate them.

Naming Consistency5/5

Tools consistently use 'hyperevm_' for EVM-related data and 'hl_' for native Hyperliquid data, followed by a clear noun describing the resource. The pattern is predictable and logical.

Tool Count5/5

With 8 tools, the server covers the core functionalities expected for a read-only data provider on this ecosystem. The count feels well-scoped—neither too many nor too few for the domain.

Completeness5/5

The tool set covers major data needs (yields, protocols, market state, staking, wallet, fees, funding history, order book) for a read-only interface. No obvious gaps for public data queries; every important area is addressed.

Maintenance

ActivitySlowing

ResponsivenessSyncing

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

0xArchive Market DataOAuth
io.0xarchive
Real-time & historical Hyperliquid/Lighter: L4/L2/L3, fills, funding, OI, liquidations, candles
Cryptocurrency Finance
2
Hyperliquid Market Data — OHLCV, Funding Rates & Positioning (Tessera)A
dev.tesseralytics
Hyperliquid perp market data for LLMs: OHLCV, funding, open interest, positioning & forecasts.
Finance Cryptocurrency Blockchain
52
hyperliquid-mcp A
io.github.junct-bot
Hyperliquid - 2 tools for perpetuals, options, and position data
Finance Blockchain Cryptocurrency
2
VaultVision Hyperliquid Vault Research A
io.github.0xkayser
Read-only Hyperliquid vault search, risk, drawdown, rankings, TVL, alerts, and comparisons.
Cryptocurrency Blockchain Finance
91

Related MCP Servers

hyperliquid-info-mcp
Cryptocurrency Finance Blockchain
kukapay
A
license
A
quality
F
maintenance
An MCP server that provides real-time data and insights from the Hyperliquid perp DEX for use in bots, dashboards, and analytics.
Updated a year ago (2025-05-31 08:00 UTC)
17
29
MIT
0xarchive-mcp
Cryptocurrency Finance Blockchain
0xArchiveIO
A
license
A
quality
F
maintenance
MCP server for querying historical and real-time crypto market data across Hyperliquid, Hyperliquid HIP-3, and Lighter.xyz - orderbooks, trades, candles, funding, open interest, liquidations, and data quality metrics.
Updated 5 days ago (2026-08-31 23:22 UTC)
100
27
11
MIT
polskidegen-hl-trackerofficial
Cryptocurrency Finance Blockchain
polskidegen
A
license
A
quality
D
maintenance
MCP server for Hyperliquid that provides read-only on-chain wallet analytics. Enables natural-language queries about positions, fills, funding, and realized PnL for any public address.
Updated 4 months ago (2026-04-24 12:32 UTC)
8
18
MIT
hl-read
Cryptocurrency Blockchain Finance
akagifreeez
A
license
Not graded
quality
B
maintenance
A read-only MCP server for Hyperliquid that provides public market data (prices, order books, funding) and any wallet's positions, orders, and fills via MCP tools, without requiring a private key.
Updated 14 days ago (2026-08-23 04:51 UTC)
MIT

Appeared in Searches

A server for finding information about Hyperliquid (cryptocurrency exchange/DeFi platform)

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/sand0vvv/hyperevm-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

hyperevm-mcp

Install

Try asking

Tools

Slash commands

What this server does not do

Three details worth knowing

Third-party text and prompt injection

Requirements

Development

Disclaimer

Available Tools

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

polskidegen-hl-trackerofficial

Appeared in Searches

Latest Blog Posts

MCP directory API