用于与 Polymarket Gamma Markets API 交互的 MCP 服务器——获取预测市场、事件和分析数据。
热门市场 - 获取高交易量的热门市场
市场搜索 - 在问题和描述中按文本搜索
按类别筛选 - 按标签（Politics、Sports、Crypto）筛选市场
市场详情 - 特定市场的完整信息
事件 - 获取关联市场的事件
API 使用情况 - 跟踪请求使用量
无需 API 密钥 - Gamma API 的公共访问
TypeScript - 严格类型化和数据验证
重试逻辑 - 网络错误时自动重试
格式化输出 - 以俄语方便地显示数据
限制跟踪 - 监控 API 使用情况
Related MCP server: Polymarket MCP Server
# Клонировать и установить зависимости
npm install
# Собрать проект
npm run build
# Запустить тесты
npm testget_trending_markets获取高交易量的热门市场。
参数：
limit（数字，默认值：20）- 市场数量
响应示例：
{
"summary": "Найдено 5 трендовых рынков",
"apiUsage": "4/1000 запросов использовано, 996 осталось",
"markets": "1. Will Joe Biden get Coronavirus before the election?\n 💰 Объём: $32,257 | 💧 Ликвидность: $0\n 🏷️ Теги: US-current-affairs\n 📊 Цены: Yes: 0.0% | No: 0.0%",
"rawData": [...]
}get_markets_by_category按类别/标签获取市场。
参数：
tags（字符串数组，必填）- 用于筛选的类别
limit（数字，默认值：50）- 市场数量
示例：
{
"tags": ["Politics", "US Election"],
"limit": 20
}search_markets按文本查询搜索市场。
参数：
query（字符串，必填）- 搜索查询
limit（数字，默认值：30）- 结果数量
get_market_details获取特定市场的详细信息。
参数：
marketId（字符串，必填）- 市场 ID
get_events获取关联市场的事件。
参数：
limit（数字，默认值：20）- 事件数量
active（布尔值，默认值：true）- 仅限活跃事件
orderBy（字符串）- 排序方式：volume、liquidity、endDate、createdAt
get_event_details获取事件的详细信息。
参数：
eventId（字符串，必填）- 事件 ID
get_api_usage获取 API 使用统计信息。
服务器使用以下 Gamma API 端点：
GET /markets - 市场列表
GET /markets/{id} - 市场详情
GET /events - 事件列表
GET /events/{id} - 事件详情
基础 URL： https://gamma-api.polymarket.com
{
id: string;
question: string;
description?: string;
outcomes: string[];
prices: number[];
volume: number;
liquidity: number;
endDate: string;
tags: string[];
active: boolean;
closed: boolean;
resolved: boolean;
negRisk: boolean;
spread?: number;
slug: string;
tokens: Array<{
id: string;
outcome: string;
price: number;
winner?: boolean;
}>;
}{
id: string;
title: string;
description?: string;
slug: string;
tags: string[];
startDate?: string;
endDate?: string;
active: boolean;
closed: boolean;
volume?: number;
liquidity?: number;
marketsCount: number;
topMarkets?: ProcessedMarket[];
}# Основные тесты
npm test
# Отладка API структуры
node test/debug-api.js公共 API - 无需密钥，但有合理限制
只读 - 无法下订单（需要 CLOB API）
简化搜索 - 暂不支持全文搜索
数据有延迟 - 非实时报价
添加到 mcp_config.json：
{
"mcpServers": {
"polymarket-gamma": {
"command": "node",
"args": ["C:/Users/pavelk/Desktop/Projects/my_own/Bet/polymarket/mcp-servers/polymarket-gamma-server/dist/index.js"],
"cwd": "C:/Users/pavelk/Desktop/Projects/my_own/Bet/polymarket/mcp-servers/polymarket-gamma-server"
}
}
}该服务器非常适合：
市场分析 - 研究趋势和交易量
事件监控 - 跟踪新市场
研究 - 收集数据用于分析
机会筛选 - 寻找感兴趣的市场
如需实际交易，请使用单独的 CLOB MCP 服务器。
✅ Gamma API 服务器 - 已完成并测试
🔄 CLOB API 服务器 - 用于交易操作
🔄 WebSocket 服务器 - 用于实时数据
🔄 统一服务器 - 整合所有功能
Get current API usage statistics and rate limits
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It implies a read-only operation via 'Get' but does not explicitly state safety, side effects, or any limits. It is adequate for a simple getter but lacks explicit reassurance beyond the verb.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no redundant words. It front-loads the action and resource, 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.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter tool with no annotations or output schema, the description states the core functionality. However, it does not elaborate on the exact nature of the statistics or the structure of the response, which could be useful. It is mostly complete but leaves some ambiguity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the description does not need to add parameter meaning. Baseline for 0 params is 4, and the description mentions 'statistics and rate limits' which hints at the data returned, not parameters. This is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Get') and clearly names the resource ('API usage statistics and rate limits'). It differentiates from sibling tools focused on market/event data, and the tool name reinforces the purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool relative to alternatives or any context about typical use cases (e.g., checking quota before requests). The description only states what it does, not when it should be invoked.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get detailed information about a specific event by ID
| Name | Required | Description | Default |
|---|---|---|---|
| eventId | Yes | Unique event ID |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must carry the full burden of behavioral disclosure. It only states the action and does not mention that the operation is read-only, what happens if the event ID is invalid or not found, or any error behavior. While the name implies a read operation, the description lacks explicit transparency about side effects (or lack thereof).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence with zero filler. It front-loads the action and resource, making it instantly parseable. There is no wasted text.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (one required parameter, no nested objects, no output schema), the description is sufficient to convey the tool's purpose. It does not explain return format, but the absence of an output schema lowers the expectation. Overall, the description covers what is needed for this simple tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already fully describes the single parameter 'eventId' as 'Unique event ID' (100% coverage). The description does not add any additional meaning or usage details beyond the schema, so 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.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Get') and the resource ('detailed information about a specific event') with the criterion 'by ID'. This distinguishes it from sibling tools like get_events (which lists events) and get_market_details (which focuses on markets).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the appropriate use case: when you have a specific event ID and need detailed information. It does not explicitly name alternatives or state 'use this instead of get_events', but the context is clear enough for an agent to infer when to invoke it. No exclusions are mentioned, but the guidance is adequate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get events with their associated markets
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of events to return (default: 20) | |
| active | No | Filter for active events only (default: true) | |
| orderBy | No | Sort events by field (default: volume) | volume |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. The verb 'Get' implies a read-only operation, but the description does not explicitly state side effects, permissions, or any constraints. It is adequate but not detailed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that effectively communicates the core functionality without unnecessary words or preamble.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description explains that events come with associated markets, which provides some context. However, it does not mention return format, pagination, or any caveats. For a simple retrieval tool, it is moderately complete but could be more informative.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema covers all three parameters with descriptions (limit, active, orderBy), so coverage is 100%. The tool description adds no extra meaning beyond the schema, but the parameter descriptions are sufficient, so 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.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'events', with the additional detail of including 'associated markets', which distinguishes it from sibling tools like get_trending_markets or get_sports_events. It is specific enough to understand the tool's function.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not mention when to use this tool versus alternatives. It lacks guidance on when this is preferred over other event-related tools, so the agent has to infer from the name and parameters.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get detailed information about a specific market by ID
| Name | Required | Description | Default |
|---|---|---|---|
| marketId | Yes | Unique market ID |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavior on its own. It only says 'detailed information' without specifying what fields are returned, whether the operation is read-only, or what happens for invalid IDs. The safety profile of a get operation is somewhat implied, but the burden is not fully met.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single clear sentence with no wasted words. It is front-loaded and immediately communicates the core purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema and no annotations, the description's mention of 'detailed information' is vague. The agent is left without knowledge of the return structure or edge-case behavior, which matters for a tool that is meant to provide details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with 'Unique market ID' documenting the parameter. The description adds no extra meaning beyond echoing 'by ID', so it meets the baseline but does not enhance understanding of the parameter's format or constraints.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
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 (detailed information about a market), and the specific scope (by ID). It distinguishes this tool from sibling tools like get_trending_markets or search_markets by emphasizing the ID-based lookup.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when a specific market ID is known and detailed information is needed, but it does not explicitly mention when not to use it or provide alternatives. No exclusions or comparisons to sibling tools are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get markets filtered by category/tags (Politics, Sports, Crypto, etc.)
| Name | Required | Description | Default |
|---|---|---|---|
| tags | Yes | Category tags to filter by (e.g., ["Politics", "US Election"]) | |
| limit | No | Number of markets to return (default: 50) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It indicates a read operation ('Get') but does not disclose how the filtering works (e.g., match all vs any tags), return format, pagination, or sorting behavior. This leaves significant behavioral ambiguity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that immediately states the purpose. It wastes no words and is appropriately sized for a filtered-list tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
This is a low-complexity tool with full schema coverage for both parameters, so the core functionality is described. However, the lack of behavioral details (like tag matching semantics, return shape, or pagination) and the absence of annotations keep it from being fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already describes both parameters with 100% coverage, so the description adds little beyond example tags. The description's examples of categories (Politics, Sports, Crypto) give a flavor of valid values but do not add deeper meaning beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies a verb ('Get'), a resource ('markets'), and a specific filter dimension ('category/tags'). Examples of categories (Politics, Sports, Crypto) distinguish this tool from siblings like search_markets or get_trending_markets.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool should be used when filtering markets by category/tags, but it does not explicitly state when to prefer this over alternatives or when not to use it. No exclusions or alternative tool names are mentioned, leaving the usage context only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Получить спортивные события с Polymarket (ПРАВИЛЬНЫЕ параметры)
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Количество событий (default: 25) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full responsibility for behavioral disclosure, but it only says 'Get' implying a read operation. It does not mention auth requirements, rate limits, output format, or any side effects. The parenthetical about 'correct parameters' is vague and adds no behavioral clarity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is one short sentence, front-loaded with the core purpose. However, the parenthetical '(CORRECT parameters)' is unclear and adds noise, slightly reducing clarity. Still, it is concise and to the point.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with one parameter and no output schema, but the description is minimal and does not explain what constitutes sports events, how they relate to other market tools, or what the response looks like. The ambiguous parenthetical further detracts from completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the single 'limit' parameter is described in the schema. The description adds no additional meaning beyond the schema, which is acceptable but does not enhance the agent's understanding of how the parameter behaves in context.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves sports events from Polymarket, which is a specific verb+resource. However, it does not distinguish itself from sibling tools like get_events, and the parenthetical '(CORRECT parameters)' adds ambiguity rather than clarity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 get_events or search_markets. The description does not mention any context, prerequisites, or exclusions, leaving the agent without direction on tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get trending/popular markets with highest volume and liquidity
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of markets to return (default: 20, max: 100) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of disclosing behavioral traits. It indicates a read-only operation (getting data) but does not clarify whether it returns potential duplicates, requires authentication, or how it sorts results (e.g., by volume first?). The description is minimal but not contradictory; it adds a sorting hint (volume/liquidity) and a limit parameter context, which is useful but incomplete for a read tool without annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that immediately states the core purpose and key ranking criteria. There is no fluff or redundancy, earning a top score for conciseness and front-loading.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one optional parameter, no output schema), the description is adequate for basic grep-style tools. However, it lacks details on the return format or how the results are ordered (e.g., volume primary, liquidity secondary). For a discovery tool, it could specify whether it includes closed markets or requires authentication, but given the minimal complexity, the description is acceptable but has room for improvement.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema covers 100% of the single parameter (limit) with a clear description and default/max values. The description adds a semantic context by mentioning 'trending' and 'highest volume and liquidity', which helps interpret the limit as affecting the number of top markets. This adds value beyond the schema, even though the schema is already clear.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: to retrieve trending/popular markets based on volume and liquidity. The verb 'get' combined with the resource 'trending_markets' is specific, and the mention of 'highest volume and liquidity' distinguishes it from generic market tools like search_markets, though it does not explicitly name alternatives.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies a use case—when you need popular markets by volume and liquidity—but it does not explicitly state when to use this over siblings or when not to. There are no exclusions or comparisons to alternatives like get_markets_by_category or search_markets, leaving usage context implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search markets by text query in question/description
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of results to return (default: 30) | |
| query | Yes | Search query text |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It adds a useful detail about searching within question/description fields, but it does not disclose any quirks, result ordering, pagination behavior, or whether it's a read-only operation. This is adequate but not thorough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that conveys the essential purpose without any fluff or repetition. It is front-loaded and easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple search tool with only two parameters and no output schema, the description is sufficient. It explains what fields are searched and the schema covers the limit parameter. It does not need to enumerate return values since no output schema exists, and the tool's behavior is straightforward.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema provides 100% coverage for both `query` and `limit` with descriptive text. The description adds extra semantics by specifying that the search applies to 'question/description', which clarifies the scope of the query parameter beyond the schema's generic 'Search query text'.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's action ('Search'), the resource ('markets'), and the specific mechanism ('by text query in question/description'). This distinguishes it from sibling tools like get_markets_by_category or get_trending_markets, which retrieve markets through different criteria.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies this tool is for free-text searching within market questions/descriptions, which provides clear context for when to use it. However, it does not explicitly mention alternatives or when not to use this tool, so it falls short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0get_api_usageget_event_detailsget_eventsget_market_detailsget_markets_by_categoryget_sports_eventsget_trending_marketssearch_marketsScored across 8 tools
Most tools are distinct: trending, category, search, details, events, event details, API usage. However, get_events and get_sports_events overlap somewhat, though the descriptions clarify sports is a subset. Search and category are clearly different. Overall, boundaries are mostly clear.
All tools follow the consistent pattern of 'get_' + noun, with clear nouns like 'trending_markets', 'market_details', 'events', etc. No mixed conventions or unexpected verbs.
8 tools are well-scoped for a read-only market data server. Each covers a distinct query type, and none feel redundant or excessive.
The surface covers market retrieval (trending, by category, search), market details, event listings and details, and API usage. Minor gaps like historical price data or market resolution info exist, but core read-only workflows are complete.
Live prediction markets: Polymarket + Kalshi prices, odds, order books. Pay-per-call USDC, no key.
Polymarket orderbook history, live books, trades and settlements, plus Hyperliquid perp books.
Read-only Polymarket sports and esports data: wallet grades on settled P&L, large trades, markets.
Live Polymarket odds, order books, fee-inclusive quotes and non-custodial prediction trading.