SQD

Official

by subsquid-labs

Overview Schema Related Servers Score Discussions

TypeScript

Remote

Find Hyperliquid trades

portal_hyperliquid_query_fills

Read-only

Retrieve raw Hyperliquid trade fills filtered by trader, coin, direction, builder, or fee token to analyze individual transactions with PnL and fee details.

Instructions

Query raw individual Hyperliquid fills with trader, coin, fee, PnL, and builder context.

COMMON USER ASKS:

Recent BTC fills

WHEN TO USE:

You need raw fill records on Hyperliquid.
You want to filter by trader, coin, direction, builder, or fee token.

DON'T USE:

You want the big picture, top traders, grouped aggregates, or candles instead of raw fill rows.

EXAMPLES:

Recent BTC fills: {"network":"hyperliquid-fills","timeframe":"1h","coin":["BTC"],"limit":20}

Input Schema

TableJSON Schema

Name	Required	Description	Default
`dir`	No	Trade direction: "Open Long", "Close Long", "Open Short", "Close Short"
`coin`	No	Asset symbols (e.g., "ETH", "BTC", "SOL")
`user`	No	Trader wallet addresses (0x-prefixed, lowercase)
`cloid`	No	Client order IDs (0x-prefixed hex)
`limit`	No	Max fills to return (default: 50, max: 200)
`cursor`	No	Continuation cursor from a previous response
`builder`	No	Builder addresses (0x-prefixed, lowercase)
`network`	No	Network name (default: 'hyperliquid-fills'). Optional when continuing with cursor.	hyperliquid-fills
`to_block`	No	Ending block number
`fee_token`	No	Fee token symbols
`timeframe`	No	Time range (e.g., '1h', '24h'). Alternative to from_block/to_block.
`from_block`	No	Starting block number (use this OR timeframe)
`include_pnl`	No	Include closedPnl and startPosition fields
`to_timestamp`	No	Ending timestamp. Accepts Unix seconds, Unix milliseconds, ISO datetime, or relative input like "now".
`finalized_only`	No	Only query finalized blocks
`from_timestamp`	No	Starting timestamp. Accepts Unix seconds, Unix milliseconds, ISO datetime, or relative input like "1h ago".
`response_format`	No	Response format: defaults to 'compact' for chat-friendly output. Use 'summary' for aggregate stats or 'full' when you truly need every fill field.
`include_builder_info`	No	Include builder and builderFee fields

Output Schema

TableJSON Schema

Name	Required	Description
`_ui`	No	Optional chart, table, and follow-up presentation metadata.
`_llm`	No	Hints that help an AI client locate the primary evidence.
`_meta`	No	Network, block range, timing, and row-count metadata.
`error`	No	Structured failure details when the tool cannot complete the request.
`items`	No	Primary result rows when the tool returns a list.
`value`	No	Primary result when the tool returns a scalar value.
`answer`	No	Concise answer grounded in the returned blockchain data.
`_notice`	No	Important limitation or truncation notice.
`display`	No	Plain-language labels for presenting the result.
`_notices`	No	Important limitations or truncation notices.
`_summary`	No	Human-readable summary of the result.
`_coverage`	No	Completeness of the requested window and result set.
`_evidence`	No	Replayable arguments, exact-data digest, row count, and completeness receipt.
`_ordering`	No	Ordering guarantees for the returned data.
`_execution`	No	Bounded execution and scan details.
`_freshness`	No	Freshness and finality information for the returned data.
`next_steps`	No	Safe follow-up actions and continuation guidance.
`_pagination`	No	Pagination state and an optional continuation cursor.
`investigation`	No	Evidence paths, useful pivots, and result limitations.
`pipes_handoff`	No	Optional SQD Pipes guidance for custom data needs.
`_tool_contract`	No	Tool identity, intent, and supported blockchain families.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed1 schema field changedv0.8.3Aug 30, 2026

addedOutput schema / properties / _evidence

Added value: +{
+  "additionalProperties": {},
+  "description": "Replayable arguments, exact-data digest, row count, and completeness receipt.",
+  "propertyNames": {
+    "type": "string"
+  },
+  "type": "object"
+}

Changed7 schema fields changedv0.8.2Aug 29, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

removedInput schema / additionalProperties
```
Removed value: -false
```

addedInput schema / properties / from_timestamp / anyOf

Added value: +[
+  {
+    "type": "number"
+  },
+  {
+    "type": "string"
+  }
+]

removedInput schema / properties / from_timestamp / type
```
Removed value: -[
-  "number",
-  "string"
-]
```

addedInput schema / properties / to_timestamp / anyOf

Added value: +[
+  {
+    "type": "number"
+  },
+  {
+    "type": "string"
+  }
+]

removedInput schema / properties / to_timestamp / type
```
Removed value: -[
-  "number",
-  "string"
-]
```

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": {},
+  "properties": {
+    "_coverage": {
+      "description": "Completeness of the requested window and result set."
+    },
+    "_execution": {
+      "additionalProperties": {},
+      "description": "Bounded execution and scan details.",
+      "propertyNames": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    "_freshness": {
+      "description": "Freshness and finality information for the returned data."
+    },
+    "_llm": {
+      "description": "Hints that help an AI client locate the primary evidence."
+    },
+    "_meta": {
+      "additionalProperties": {},
+      "description": "Network, block range, timing, and row-count metadata.",
+      "propertyNames": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    "_notice": {
+      "description": "Important limitation or truncation notice.",
+      "type": "string"
+    },
+    "_notices": {
+      "description": "Important limitations or truncation notices.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "_ordering": {
+      "description": "Ordering guarantees for the returned data."
+    },
+    "_pagination": {
+      "additionalProperties": {},
+      "description": "Pagination state and an optional continuation cursor.",
+      "propertyNames": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    "_summary": {
+      "description": "Human-readable summary of the result.",
+      "type": "string"
+    },
+    "_tool_contract": {
+      "additionalProperties": {},
+      "description": "Tool identity, intent, and supported blockchain families.",
+      "propertyNames": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    "_ui": {
+      "description": "Optional chart, table, and follow-up presentation metadata."
+    },
+    "answer": {
+      "description": "Concise answer grounded in the returned blockchain data.",
+      "type": "string"
+    },
+    "display": {
+      "additionalProperties": {},
+      "description": "Plain-language labels for presenting the result.",
+      "propertyNames": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    "error": {
+      "additionalProperties": {},
+      "description": "Structured failure details when the tool cannot complete the request.",
+      "properties": {
+        "code": {
+          "type": "string"
+        },
+        "origin": {
+          "type": "string"
+        },
+        "retry_after_ms": {
+          "type": "number"
+        },
+        "retryable": {
+          "type": "boolean"
+        },
+        "suggestions": {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "summary": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "code",
+        "origin",
+        "summary",
+        "retryable",
+        "suggestions"
+      ],
+      "type": "object"
+    },
+    "investigation": {
+      "additionalProperties": {},
+      "description": "Evidence paths, useful pivots, and result limitations.",
+      "propertyNames": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    "items": {
+      "description": "Primary result rows when the tool returns a list.",
+      "items": {},
+      "type": "array"
+    },
+    "next_steps": {
+      "additionalProperties": {},
+      "description": "Safe follow-up actions and continuation guidance.",
+      "properties": {
+        "actions": {
+          "items": {
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string"
+            },
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "continuation": {
+          "additionalProperties": {},
+          "propertyNames": {
+            "type": "string"
+          },
+          "type": "object"
+        },
+        "custom_data": {
+          "additionalProperties": {},
+          "propertyNames": {
+            "type": "string"
+          },
+          "type": "object"
+        }
+      },
+      "required": [
+        "actions"
+      ],
+      "type": "object"
+    },
+    "pipes_handoff": {
+      "description": "Optional SQD Pipes guidance for custom data needs."
+    },
+    "value": {
+      "description": "Primary result when the tool returns a scalar value."
+    }
+  },
+  "type": "object"
+}

First observedv0.7.9Jun 25, 2026

TDQS

A4.5/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description doesn't need to restate safety. It adds the 'raw individual' nature of the data, but doesn't disclose other behavioral traits such as pagination via cursor, potential large result sizes, or any rate limits. Given the annotations cover the safety profile, this is an adequate but not rich disclosure.

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 well-structured with short labeled sections (COMMON USER ASKS, WHEN TO USE, DON'T USE, EXAMPLES). It front-loads the core purpose and every sentence earns its place. No repetition or fluff.

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 having 18 parameters, all are documented in the schema (100% coverage), an output schema exists, and the description provides selection criteria, exclusions, and an example. The description is complete enough for an agent to decide when to use it and how to invoke it correctly.

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 description coverage is 100%, so baseline is 3. The description adds value by showing a real invocation example ("Recent BTC fills": network, timeframe, coin, limit) and by listing the filtering dimensions (trader, coin, direction, builder, fee token) that map directly to schema parameters. This helps an agent construct calls correctly beyond what the schema alone provides.

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 opens with a precise verb and resource: "Query raw individual Hyperliquid fills" and lists the specific context fields (trader, coin, fee, PnL, builder). It clearly distinguishes this tool from siblings like portal_hyperliquid_get_analytics and portal_hyperliquid_get_ohlc by emphasizing raw fill rows versus aggregates/candles.

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 has explicit WHEN TO USE and DON'T USE sections, naming concrete conditions (need raw fills, filter by trader/coin/direction) and exclusions (big picture, top traders, grouped aggregates, candles). It also provides a concrete example for a common user ask, leaving no ambiguity about when this tool is appropriate.

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

Install Server

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/subsquid-labs/portal-mcp-server'

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