hypersignal
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HL_NETWORK | No | Hyperliquid network (mainnet or testnet) | mainnet |
| X402_ENABLED | No | Enable x402 pay-per-call | false |
| HL_ENABLE_TRADING | No | Enable trading tools (only for local stdio) | false |
| HL_BUILDER_ADDRESS | No | Builder address for Hyperliquid order routing | |
| NODE_USE_ENV_PROXY | No | Set to 1 to honor HTTPS_PROXY environment variable | 0 |
| HL_AGENT_PRIVATE_KEY | No | Agent private key for signing orders (required if HL_ENABLE_TRADING=true) | |
| HYPERSIGNAL_PRO_KEYS | No | Comma-separated pro API keys | |
| HYPERSIGNAL_FREE_KEYS | No | Comma-separated free API keys | |
| HYPERSIGNAL_ADMIN_SECRET | No | Admin secret for admin stats tool | |
| HL_BUILDER_FEE_TENTHS_BPS | No | Builder fee in tenths of basis points | 5 |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| hl_request_free_keyA | Issue yourself a free API key, instantly and with no signup. The key grants 100 premium calls per month — enough to evaluate every premium tool. Send it as the X-API-Key header on later requests. Call this first if a premium tool says it needs a key. One active key per requester: calling again replaces the previous key and keeps the same monthly usage, so it is safe to call if you lost your key but is not a way to reset the quota. |
| hl_get_markets | List Hyperliquid perpetual markets with mark/oracle price, hourly + annualized funding, open interest, and 24h volume. Use to discover valid coin symbols and scan the board. Supports name filter, sorting, and pagination. |
| hl_get_orderbookA | Level-2 order book for a coin: top-N bid/ask levels with price, size, and order count, plus spread and mid. Use for microstructure, spread, and near-touch liquidity. If the coin is unknown, call hl_get_markets first. |
| hl_get_candlesA | OHLCV candlestick history for a coin at a given interval. Provide either an explicit [startTime,endTime] (ms epoch) or a |
| hl_get_funding_historyA | Historical hourly funding rates for a coin over a time window, with cumulative and average annualized funding. Use for carry analysis and funding trend. Defaults to the last 7 days if no window is given. |
| hl_get_accountA | Perp account snapshot for any address: equity, margin usage, withdrawable, and open positions (size, entry, uPnL, leverage, liquidation price). Read-only; works for any public 0x address. |
| hl_get_open_ordersA | Open resting orders for an address: coin, side, price, size, order id, type, and trigger info. Read-only; paginated. Use to inspect any wallet's live order book footprint. |
| hl_signal_pubkeyA | Returns the server's Ed25519 public key (SPKI DER, base64) used to sign emitted signals, so anyone can independently verify a signal's authenticity and timestamp. Canonicalization: JSON with recursively sorted keys over {payload, ts}; signature is base64 Ed25519. |
| hl_admin_statsA | OPERATOR ONLY. Requires |
| hl_score_calibrationA | Out-of-sample evidence for whether the hl_smart_money_score actually predicts anything: Spearman rank correlation between each wallet's score and the realized PnL it went on to earn over the forward window, plus mean forward PnL per score quartile. Verdicts: insufficient_data (not enough resolved observations yet), inverted (significantly NEGATIVE — higher-scored wallets did worse), no_evidence, weak_positive, positive. Only server-selected cohorts enter the sample, so a caller cannot steer this figure. Read this before treating the score as a forecast. |
| hl_place_orderA | Place a limit or market perp order through YOUR local agent wallet, with the HyperSignal builder code attached. Dry-run by default (previews the exact signed action without sending). Set confirm=true AND dryRun=false to submit. ⚠️ Places a REAL order via your agent wallet when confirm=true and dry-run is off. Trades are risky and irreversible; this is not investment advice. Test on testnet first. The customer builder code is attached to earn a small builder fee. |
| hl_cancel_orderA | Cancel a resting order by coin + order id via your local agent wallet. Dry-run by default; set confirm=true AND dryRun=false to submit. Analytics/execution helper, not investment advice. |
| hl_close_positionA | Close an open perp position with a reduce-only market (IOC) order via your local agent wallet, builder code attached. Dry-run by default; set confirm=true AND dryRun=false to submit. Irreversible; not investment advice. |
| hl_approve_builder_fee_guideA | Read-only. Generates the exact approveBuilderFee action payload and step-by-step instructions for the user to authorize the HyperSignal builder code with their MAIN wallet. This tool never signs and never sees your main key. Not investment advice. |
| hl_twap_orderA | Accumulate/reduce a position by slicing it into evenly-spaced child orders over a duration (TWAP), minimizing market impact, with the builder code on every child. Dry-run returns the schedule; live schedules it and returns a plan id (poll with hl_execution_status). A live plan keeps the server process alive until every slice has fired; plan state is in-memory, so if the process is killed mid-run the already-submitted slices remain open on the exchange and the remainder is abandoned (logged on shutdown). ⚠️ Executes REAL child orders on your agent wallet when confirm=true & dryRun=false (builder code attached). Dry-run by default. Irreversible; not investment advice. Test on testnet first. |
| hl_copy_wallet | Bring your perp positioning into line with a target wallet's, scaled to your equity, using the builder code. Orders are DELTAS against what you already hold, so calling this repeatedly keeps you in sync instead of compounding the position — once matched, a repeat call submits nothing. Coins the target has exited are unwound. A pre-trade cap (maxLeverage, default 3x equity) bounds the notional before anything is signed. Dry-run returns the plan; live submits it. ⚠️ Executes REAL child orders on your agent wallet when confirm=true & dryRun=false (builder code attached). Dry-run by default. Irreversible; not investment advice. Test on testnet first. |
| hl_execution_status | Status of TWAP/execution plans: child order progress. Pass planId for one plan, or omit to list all. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/johnsmithxy1mmm-sys/HyperliquidMCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server