How do I use MCP-Coinglass?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP-Coinglass Show me BTC open interest on Binance." That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

MCP-Coinglass

by GPSxtreme

Overview Schema Related Servers Score Discussions

TypeScript

Remote

MCP-Coinglass

This project implements a Model Context Protocol (MCP) server for the CoinGlass API (v4). It lets MCP-compatible clients (AI assistants, IDE extensions, or custom apps) access futures market analytics such as Open Interest, Liquidations, Long/Short Ratio, and Funding Rates.

Features (MCP Tools)

The server exposes the following tools that MCP clients can call:

COINGLASS_OPEN_INTEREST: Open interest exchange list for a symbol; optional history
- Parameters: symbol (string), exchange? (string), includeHistory? (boolean), period? ("1h" | "4h" | "12h" | "24h")
COINGLASS_LIQUIDATIONS_PAIR: Historical pair liquidations (v4 /api/futures/liquidation/history)
- Parameters: exchange (string), symbol (string), interval? ("1m"|"3m"|"5m"|"15m"|"30m"|"1h"|"4h"|"6h"|"8h"|"12h"|"1d"|"1w"), limit?, start_time?, end_time?, prettyFormat? (default: true)
COINGLASS_LIQUIDATIONS_COIN: Aggregated coin liquidations (v4 /api/futures/liquidation/aggregated-history)
- Parameters: exchange_list (string), symbol (string), interval? (same as above), limit?, start_time?, end_time?, prettyFormat? (default: true)
COINGLASS_LONG_SHORT_RATIO: Global account long/short ratio snapshot
- Parameters: symbol (string), exchange? (string), period? ("1h" | "4h" | "12h" | "24h"), prettyFormat? (boolean, default: true)
COINGLASS_FUNDING_RATE: Current funding rate across exchanges
- Parameters: symbol (string), exchange? (string), prettyFormat? (boolean, default: true)
COINGLASS_HYPERLIQUID_WHALE_ALERT: Real-time Hyperliquid whale alerts (>$1M)
Parameters: prettyFormat? (boolean, default: true)
COINGLASS_HYPERLIQUID_WHALE_POSITION: Real-time Hyperliquid whale positions (>$1M)
Parameters: prettyFormat? (boolean, default: true)

Tool call responses always return a success code even in case of api errors. In case of error tool response includes the raw api response.

Related MCP server: CryptoQuant MCP Server

Prerequisites

Node.js v20+ (CI uses Node 22)
pnpm (https://pnpm.io/installation)

Installation

There are a few ways to run mcp-coinglass:

Using pnpm dlx (recommended for most MCP client setups)

Run the published package directly without a global install. See the MCP client config example below.

Global installation from npm (via pnpm)

pnpm add -g mcp-coinglass

Building from source (development)

pnpm install
pnpm run build
pnpm run start

For testing and development purposes use mcp inspector

# in the project root run,
pnpm run build
npx @modelcontextprotocol/inspector node dist/index.js

Configuration (Environment Variables)

This server requires a CoinGlass API key. All CoinGlass v4 endpoints require the CG-API-KEY header. Generate your API key from your account dashboard and supply it via environment variables. References:

Authentication docs: https://docs.coinglass.com/reference/authentication
Account/API key dashboard: https://www.coinglass.com/account

Create a .env file (or configure env in your MCP client) with:

COINGLASS_API_KEY=your_api_key_here

An .env.sample file is included as a reference; copy it to .env and fill in your key.

NOTE: All the available tools require an upgraded coinglass api plan to work

Running the Server with an MCP Client

MCP clients (assistants, IDE extensions) run this server as a background process. Configure your client with a server entry similar to the following.

Using pnpm dlx:

{
  "mcpServers": {
    "coinglass-mcp-server": {
      "command": "pnpm",
      "args": ["dlx", "mcp-coinglass"],
      "env": {
        "COINGLASS_API_KEY": "your_api_key_here"
      }
    }
  }
}

If globally installed (pnpm add -g mcp-coinglass):

{
  "mcpServers": {
    "coinglass-mcp-server": {
      "command": "mcp-coinglass",
      "args": [],
      "env": {
        "COINGLASS_API_KEY": "your_api_key_here"
      }
    }
  }
}

Example Tool Invocations

MCP clients pass JSON parameters to tools. Examples:

{ "tool": "COINGLASS_OPEN_INTEREST", "params": { "symbol": "BTC", "includeHistory": true, "period": "24h" } }

{ "tool": "COINGLASS_LIQUIDATIONS", "params": { "symbol": "BTCUSDT", "timeframe": "4h" } }

{ "tool": "COINGLASS_LIQUIDATIONS_PAIR", "params": { "exchange": "Binance", "symbol": "BTCUSDT", "interval": "4h" } }

{ "tool": "COINGLASS_LIQUIDATIONS_COIN", "params": { "exchange_list": "Binance,OKX,Bybit", "symbol": "BTC", "interval": "1d" } }

{ "tool": "COINGLASS_LONG_SHORT_RATIO", "params": { "symbol": "ETH", "period": "1h" } }

{ "tool": "COINGLASS_FUNDING_RATE", "params": { "symbol": "SOL" } }

{ "tool": "COINGLASS_HYPERLIQUID_WHALE_ALERT", "params": {} }

{ "tool": "COINGLASS_HYPERLIQUID_WHALE_POSITION", "params": {} }

Default Human-Readable Output Examples (prettyFormat=true)

These are the default formatted outputs. Set prettyFormat to false to receive raw API-shaped responses.

Funding Rate

Funding Rate for BTCUSDT:
Average: 0.0100% | Next Funding: 2024-08-06T08:00:00.000Z
Exchanges: 12

{
  "averageRate": 0.0001,
  "nextFundingTime": 1722960000000,
  "exchanges": [
    { "exchange": "Binance", "rate": -0.0000335, "predictedRate": -0.00002, "nextFundingTime": 1722960000000 }
    // ...
  ]
}

Open Interest

Open Interest for BTCUSDT:
Total OI (All): $123456789
24h Change: 2.34%

{
  "exchangeList": [ /* ... */ ],
  "history": { /* optional when includeHistory=true */ }
}

Liquidations (Pair)

Liquidations (Pair) for BTCUSDT [48 points]:
Latest: Long $1.23M | Short $2.34M
Totals: Long $56.78M | Short $67.89M

{
  "latest": { /* latest data point */ },
  "totals": { "long": 56780000, "short": 67890000 },
  "points": [ /* ... */ ]
}

Liquidations (Coin Aggregated)

Liquidations (Coin Aggregated) for BTC [48 points]:
Latest: Long $1.23M | Short $2.34M
Totals: Long $56.78M | Short $67.89M

{
  "latest": { /* latest data point */ },
  "totals": { "long": 56780000, "short": 67890000 },
  "points": [ /* ... */ ]
}

Global Long/Short Account Ratio

Long/Short Ratio for BTCUSDT:
Long: 73.24% | Short: 26.76% | Ratio: 2.74

{
  "latest": { /* latest data point */ },
  "points": [ /* ... */ ]
}

Hyperliquid Whale Alert

Hyperliquid Whale Alerts: 8 events
Top 5 by position value:

{
  "top": [
    { "user": "0xabc...", "symbol": "BTC", "positionValueUsd": 2936421.48, "positionAction": 2, "createTime": 1745219477000 }
    // ...
  ],
  "events": [ /* ... */ ]
}

Hyperliquid Whale Position

Hyperliquid Whale Positions: 6 positions (top 5 by value)

{
  "top": [
    { "user": "0xdef...", "symbol": "ETH", "positionSize": -44727.13, "positionValueUsd": 73589542.55, "leverage": 25, "unrealizedPnl": 27033236.42, "marginMode": "cross", "updateTime": 1745219966000 }
    // ...
  ],
  "positions": [ /* ... */ ]
}

Scripts

pnpm run build: Compile TypeScript to dist/ and make output executable
pnpm run start: Run the built server over stdio (for MCP)
pnpm run lint: Lint via Biome
pnpm run format: Format via Biome

Endpoint References (v4)

This server calls these REST endpoints:

Open Interest Exchange List: GET /api/futures/open-interest/exchange-list
Open Interest History (OHLC): GET /api/futures/open-interest/history
Liquidations History: GET /api/futures/liquidation/history
Global Long/Short Account Ratio History: GET /api/futures/global-long-short-account-ratio/history
Funding Rate Exchange List: GET /api/futures/funding-rate/exchange-list

Refer to the official docs for authentication and rate limits:

https://docs.coinglass.com/reference/authentication

Available Tools

7 tools

COINGLASS_FUNDING_RATEB

Get current funding rate across exchanges for a symbol

ParametersJSON Schema

Name	Required	Description
`symbol`	Yes	Base asset symbol, e.g., BTC or BTCUSDT
`exchange`	No	Optional exchange filter, e.g., Binance
`prettyFormat`	No	When true (default), returns a human-readable summary; when false, returns raw API-shaped data.

TDQS

B3.4/5.0

Behavior2/5

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

No annotations are provided, so the description must disclose behavioral traits. It only states the basic operation, omitting details about authentication, rate limits, error handling, or output format. The agent is left with significant unknowns.

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, concise sentence that is front-loaded with key information. No extraneous words or repetition.

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

Completeness2/5

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

The tool lacks an output schema and has 3 parameters, yet the description does not clarify the return format (especially with the prettyFormat parameter) or handling of errors. The description is too minimal to fully guide an agent.

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 description adds no additional meaning beyond the schema. Baseline score of 3 is appropriate; the description does not enhance parameter understanding.

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 action ('Get'), the resource ('current funding rate'), and the scope ('across exchanges for a symbol'). It effectively distinguishes from sibling tools which focus on whale alerts, positions, liquidations, open interest, and long-short ratio.

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

Usage Guidelines3/5

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

The description implies usage (to fetch funding rate data) but provides no explicit guidance on when to use this tool versus alternatives or what prerequisites exist. Sibling tools are distinct, so no confusion, but context is missing.

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

COINGLASS_HYPERLIQUID_WHALE_ALERTA

Get real-time Hyperliquid whale alerts (positions over $1M)

ParametersJSON Schema

Name	Required	Description	Default
`prettyFormat`	No	When true (default), returns a human-readable summary; when false, returns raw API-shaped data.

TDQS

A3.6/5.0

Behavior2/5

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

With no annotations provided, the description must fully disclose behavioral traits. It mentions 'real-time' and a threshold but fails to specify polling behavior, data freshness, pagination, or side effects. The lack of disclosure is a significant gap.

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 sentence with no wasted words. It efficiently conveys the tool's core purpose.

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 tool is simple (one parameter, no output schema) and the description covers the essential purpose. However, it could be improved by briefly noting the typical content of alerts (e.g., direction, size, entry price) to fully prepare the agent.

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% for the single parameter (prettyFormat), so the description adds no additional meaning beyond the schema. This meets the baseline expectation of 3.

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 retrieves 'real-time Hyperliquid whale alerts' with a specific threshold ($1M positions), using a specific verb ('Get') and resource ('whale alerts'). It naturally distinguishes from sibling tools like COINGLASS_HYPERLIQUID_WHALE_POSITION and COINGLASS_LIQUIDATIONS_COIN.

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

Usage Guidelines3/5

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

While the description implies usage for monitoring large positions in real time, it does not explicitly explain when to use this tool versus alternatives (e.g., COINGLASS_HYPERLIQUID_WHALE_POSITION for individual positions). There is no guidance on context or exclusions.

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

COINGLASS_HYPERLIQUID_WHALE_POSITIONA

Get Hyperliquid whale positions (value over $1M)

ParametersJSON Schema

Name	Required	Description	Default
`prettyFormat`	No	When true (default), returns a human-readable summary; when false, returns raw API-shaped data.

TDQS

A3.5/5.0

Behavior2/5

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

No annotations are provided, so the description must convey behavioral traits. It mentions the value threshold but omits details like data freshness, pagination, rate limits, or whether the data is real-time or historical. The description does not disclose any significant behavioral aspects beyond the basic query.

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, concise sentence that conveys the essential purpose. It is front-loaded and contains no extraneous information. Every word is necessary.

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

Completeness3/5

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

Given the tool has only one optional parameter and no output schema, the description is fairly complete. However, it lacks details about the returned data structure (e.g., fields, format) and any usage constraints. For a low-complexity tool, it is adequate but not thorough.

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?

The input schema has 100% coverage with a description for 'prettyFormat'. The tool description does not add any additional meaning beyond the schema. Since schema coverage is complete, a baseline score of 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 what the tool does: 'Get Hyperliquid whale positions (value over $1M)'. It specifies the exact resource ('Hyperliquid whale positions') and a specific threshold ('value over $1M'), which distinguishes it from sibling tools like COINGLASS_HYPERLIQUID_WHALE_ALERT or COINGLASS_FUNDING_RATE.

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

Usage Guidelines3/5

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

The description implies usage when needing large positions on Hyperliquid, but it provides no explicit guidance on when to use this tool versus alternatives (e.g., COINGLASS_HYPERLIQUID_WHALE_ALERT for alerts). No exclusion criteria or context is given.

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

COINGLASS_LIQUIDATIONS_COINB

Get aggregated liquidation history for a coin across exchanges

ParametersJSON Schema

Name	Required	Description	Default
`exchange_list`	Yes	Comma-separated exchanges to aggregate, e.g., Binance,OKX,Bybit
`symbol`	Yes	Coin symbol, e.g., BTC
`interval`	No		1d
`limit`	No
`start_time`	No
`end_time`	No
`prettyFormat`	No	When true (default), returns a human-readable summary; when false, returns raw API-shaped data.

TDQS

B3.1/5.0

Behavior2/5

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

No annotations provided, and the description only says 'Get aggregated liquidation history', implying a read operation. It does not disclose behavioral traits such as data freshness, pagination, rate limits, or the structure of the response. For a tool with 7 parameters and no output schema, more transparency is needed.

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

Conciseness3/5

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

The description is a single sentence, making it concise. However, for a tool with 7 parameters, it lacks important structure and critical details. It could be slightly longer to front-load key information about required parameters or aggregation behavior.

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

Completeness2/5

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

Given the high parameter count (7), lack of annotations, and no output schema, the description is incomplete. It does not explain the roles of interval, limit, start_time, end_time, or how aggregation works across exchanges. It also does not clarify the difference from the sibling tool COINGLASS_LIQUIDATIONS_PAIR.

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

Parameters2/5

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

Schema description coverage is 43% (only 3 of 7 parameters have descriptions: exchange_list, symbol, prettyFormat). The tool description adds no extra meaning beyond repeating 'aggregated liquidation history for a coin across exchanges'. It fails to compensate for the missing schema descriptions of interval, limit, start_time, end_time, which are essential for correct usage.

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 'Get aggregated liquidation history for a coin across exchanges', which specifies the verb (Get), resource (aggregated liquidation history), and scope (for a coin across exchanges). This differentiates it from siblings like COINGLASS_LIQUIDATIONS_PAIR (likely pair-specific) and other non-liquidation tools.

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

Usage Guidelines3/5

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

No explicit guidance on when to use this tool versus alternatives. The description implies it's for coin-level aggregated data, but does not mention exclusions or comparisons with siblings like COINGLASS_LIQUIDATIONS_PAIR. Usage is implied but not clarified.

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

COINGLASS_LIQUIDATIONS_PAIRC

Get liquidation history for a specific futures pair

ParametersJSON Schema

Name	Required	Description	Default
`exchange`	Yes	Futures exchange, e.g., Binance
`symbol`	Yes	Trading pair, e.g., BTCUSDT
`interval`	No		1d
`limit`	No
`start_time`	No
`end_time`	No
`prettyFormat`	No	When true (default), returns a human-readable summary; when false, returns raw API-shaped data.

TDQS

C2.7/5.0

Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only states that the tool gets liquidation history but omits critical details such as default interval (1d), maximum limit (4500), pagination behavior, rate limits, or that prettyFormat controls output format. The description adds minimal transparency beyond the basic action.

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 sentence that efficiently communicates the core purpose. It is front-loaded and contains no fluff. However, it may be too minimal given the tool's complexity, bordering on under-specification rather than conciseness.

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

Completeness2/5

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

Given the tool has 7 parameters, no annotations, and no output schema, the description lacks essential context. It does not clarify output format (raw vs pretty), time range behavior, or how to handle pagination. Agents would have to infer too much from the schema alone.

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

Parameters2/5

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

Schema description coverage is only 43%, meaning many parameters lack descriptions in the schema. The tool description does not add any parameter-level details, forcing agents to rely solely on parameter names and the sparse schema descriptions. Key parameters like start_time and end_time have no explanation.

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

Purpose4/5

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

The description clearly states the tool retrieves liquidation history for a specific futures pair, using a clear verb and resource. However, it does not explicitly distinguish itself from its sibling tool COINGLASS_LIQUIDATIONS_COIN, which might have a different scope (e.g., per coin vs per pair).

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives like COINGLASS_LIQUIDATIONS_COIN or other CoinGlass tools. The description simply states the function without contextual usage advice.

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

COINGLASS_LONG_SHORT_RATIOA

Get global account long/short ratio history snapshot for a symbol

ParametersJSON Schema

Name	Required	Description	Default
`symbol`	Yes	Trading pair, e.g., BTCUSDT or BTC
`exchange`	No	Futures exchange, e.g., Binance
`period`	No	Aggregation period: 1h, 4h, 12h, 24h (maps to 1h/4h/12h/1d)	24h
`prettyFormat`	No	When true (default), returns a human-readable summary; when false, returns raw API-shaped data.

TDQS

A3.5/5.0

Behavior2/5

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

With no annotations, the description must disclose behavioral traits. It only states it returns a 'history snapshot' and does not mention data freshness, rate limits, aggregation behavior, or the effect of the prettyFormat parameter on output.

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 sentence with no wasted words.

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

Completeness3/5

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

Given no output schema, the description should explain what 'history snapshot' means and how 'prettyFormat' affects output. It is adequate but leaves gaps about return format and period default behavior.

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%, so the baseline is 3. The description adds no additional parameter meaning beyond what the schema already 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 clearly states the action ('Get'), the resource ('global account long/short ratio history snapshot'), and the target ('for a symbol'). It effectively distinguishes from sibling tools that handle funding rates, liquidations, open interest, etc.

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

Usage Guidelines3/5

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

The description provides a clear context for when to use the tool (when needing long/short ratio data), but does not specify when not to use it or offer explicit alternatives among siblings.

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

COINGLASS_OPEN_INTERESTB

Get open interest exchange list and optional OI history for a symbol

ParametersJSON Schema

Name	Required	Description
`symbol`	Yes	Base asset symbol, e.g., BTC or BTCUSDT
`exchange`	No	Optional exchange filter, e.g., Binance
`includeHistory`	No
`period`	No
`prettyFormat`	No	When true (default), returns a human-readable summary; when false, returns raw API-shaped data.

TDQS

B3.1/5.0

Behavior2/5

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

With no annotations, the description must convey behavioral traits. It only says 'Get', implying a read operation, but does not explicitly state that it is non-destructive, nor does it mention authentication, rate limits, or any side effects.

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 11-word sentence that is perfectly front-loaded and contains no redundant information. It efficiently conveys the core functionality.

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

Completeness2/5

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

Given 5 parameters and no output schema, the description omits details about output format (besides prettyFormat), behavior when exchange is omitted, and how history data is structured. It is insufficient for an agent to fully understand the tool's capabilities.

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

Parameters2/5

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

Schema description coverage is only 60% (3 of 5 parameters have descriptions). The description adds context only for 'includeHistory' (via 'optional OI history'), leaving 'period' entirely unexplained. It does not compensate for the missing schema descriptions.

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 action ('Get'), the resource ('open interest exchange list and optional OI history'), and the scope ('for a symbol'). It distinguishes from sibling tools like funding rate or liquidations, which cover different metrics.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives (e.g., COINGLASS_FUNDING_RATE) or when not to use it. The description only states what it does, not the context of its use.

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.

7 tool updatesv0.1.0Jun 3, 2026
- First observedCOINGLASS_FUNDING_RATE
- First observedCOINGLASS_HYPERLIQUID_WHALE_ALERT
- First observedCOINGLASS_HYPERLIQUID_WHALE_POSITION
- First observedCOINGLASS_LIQUIDATIONS_COIN
- First observedCOINGLASS_LIQUIDATIONS_PAIR
- First observedCOINGLASS_LONG_SHORT_RATIO
- First observedCOINGLASS_OPEN_INTEREST

Install Server

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

TDQS

A3.6/5.0

Disambiguation5/5

Each tool targets a distinct data type: funding rate, whale alerts/positions, liquidations (by coin and pair), long/short ratio, and open interest. No overlap in purpose.

Naming Consistency5/5

All tools follow the uniform pattern COINGLASS_<DOMAIN> with uppercase and underscores, making them predictable and easy to parse.

Tool Count5/5

Seven tools cover the core Coinglass API metrics without unnecessary bloat, well-scoped for a data retrieval server.

Completeness4/5

Covers major Coinglass indicators (funding, whales, liquidations, long/short, OI). Minor gap: funding rate history is not explicitly provided, but core functionality is present.

Maintenance

ActivityInactive

ResponsivenessNo issues

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

Coinfuty A
com.coinfuty
Free crypto futures data: open interest, funding, long/short, liquidations, volume. No API key.
Cryptocurrency Finance
71
CryptoQuantOAuth
com.cryptoquant
Query cryptocurrency on-chain data, OHLCV prices, market data, and Research & QuickTake insights.
Cryptocurrency Blockchain
2
TraderSpy A
app.traderspy
AI crypto signals, smart money whale positions, live futures prices and indicators
Cryptocurrency Finance
151
MarketTrace agent-feedOAuth
ai.markettrace
Crypto perps data for AI agents: funding rates, open interest, liquidations, order book, CVD.
Cryptocurrency Finance
5

Related MCP Servers

CoinGlass MCP Server
Cryptocurrency Finance Research & Data
forgequant
F
license
A
quality
D
maintenance
Provides AI agents access to cryptocurrency derivatives analytics through 22 unified tools covering 80+ CoinGlass API endpoints. Enables analysis of open interest, funding rates, liquidations, whale positions, order book data, and market sentiment indicators with plan-aware feature gating.
Updated 9 months ago (2025-12-01 13:06 UTC)
24
1
-
CryptoQuant MCP Serverofficial
Blockchain Cryptocurrency Finance
CryptoQuantOfficial
A
license
A
quality
C
maintenance
Enables AI assistants to access real-time on-chain crypto analytics, whale tracking, and market metrics through natural language queries. It provides access to over 245 endpoints for comprehensive data analysis of assets like Bitcoin, Ethereum, and stablecoins.
Updated 7 months ago (2026-02-03 08:13 UTC)
7
17
7
MIT
coinglass-mcp
Cryptocurrency Finance Search
aviman1109
A
license
Not graded
quality
D
maintenance
Provides access to CoinGlass cryptocurrency derivatives data, including funding rates, open interest, and liquidation metrics. It enables LLMs to analyze real-time and historical market structure context through a standardized toolset.
Updated 5 months ago (2026-03-26 02:38 UTC)
MIT
Simsar MCP
Cryptocurrency Finance
miratcan
A
license
C
quality
D
maintenance
Enables AI assistants to access comprehensive cryptocurrency market analysis, including real-time prices, 35+ technical indicators, market sentiment, futures data, and economic events.
Updated 6 months ago (2026-03-01 22:05 UTC)
50
2
MIT

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/GPSxtreme/mcp-coinglass'

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

MCP-Coinglass

Features (MCP Tools)

Prerequisites

Installation

Configuration (Environment Variables)

Running the Server with an MCP Client

Example Tool Invocations

Default Human-Readable Output Examples (prettyFormat=true)

Funding Rate

Open Interest

Liquidations (Pair)

Liquidations (Coin Aggregated)

Global Long/Short Account Ratio

Hyperliquid Whale Alert

Hyperliquid Whale Position

Scripts

Endpoint References (v4)

Available Tools

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

CryptoQuant MCP Serverofficial

Latest Blog Posts

MCP directory API