模型上下文协议 (MCP) 服务器，通过 PolyMarket API 提供对预测市场数据的访问。该服务器实现了一个标准化接口，用于检索预测市场的市场信息、价格和历史数据。
实时预测市场数据，包括当前价格和概率
详细的市场信息，包括类别、决议日期和描述
具有可自定义时间范围（1 天、7 天、30 天、全部）的历史价格和数量数据
内置错误处理和速率限制管理
清晰的数据格式，方便使用
Related MCP server: Polymarket MCP Server
要通过Smithery自动为 Claude Desktop 安装 PolyMarket Predictions：
npx -y @smithery/cli install polymarket_mcp --client claude在 MacOS 上： ~/Library/Application\ Support/Claude/claude_desktop_config.json
在 Windows 上： %APPDATA%/Claude/claude_desktop_config.json
"mcpServers": {
"polymarket-mcp": {
"command": "uv",
"args": [
"--directory",
"/Users/{INSERT_USER}/YOUR/PATH/TO/polymarket-mcp",
"run",
"polymarket-mcp" //or src/polymarket_mcp/server.py
],
"env": {
"KEY": "<insert poly market api key>",
"FUNDER": "<insert polymarket wallet address"
}
}
}克隆存储库并安装依赖项：
uv pip install -e .通过 json 文件将 Claude 客户端与 MCP 工具连接并安装软件包后，Claude 应该可以看到服务器的 mcp 工具：
您可以通过以下方式自行运行服务器：在 polymarket-mcp repo 中：
uv run src/polymarket_mcp/server.py*如果您想与服务器一起运行服务器检查器：
npx @modelcontextprotocol/inspector uv --directory C:\\Users\\{INSERT_USER}\\YOUR\\PATH\\TO\\polymarket-mcp run src/polymarket_mcp/server.py使用您的 PolyMarket API 密钥创建一个.env文件：
Key=your_api_key_here
Funder=poly market wallet address通过 json 文件将 Claude 客户端与 MCP 工具连接后，运行服务器：在 alpha-vantage-mcp repo 中： uv run src/polymarket_mcp/server.py
该服务器实现了四个工具：
get-market-info ：获取有关特定预测市场的详细信息
list-markets ：列出可用的预测市场并附带过滤选项
get-market-prices ：获取当前价格和交易信息
get-market-history ：获取历史价格和交易量数据
输入模式：
{
"market_id": {
"type": "string",
"description": "Market ID or slug"
}
}响应示例：
Title: Example Market
Category: Politics
Status: Open
Resolution Date: 2024-12-31
Volume: $1,234,567.89
Liquidity: $98,765.43
Description: This is an example prediction market...
---输入模式：
{
"status": {
"type": "string",
"description": "Filter by market status",
"enum": ["open", "closed", "resolved"]
},
"limit": {
"type": "integer",
"description": "Number of markets to return",
"default": 10,
"minimum": 1,
"maximum": 100
},
"offset": {
"type": "integer",
"description": "Number of markets to skip (for pagination)",
"default": 0,
"minimum": 0
}
}响应示例：
Available Markets:
ID: market-123
Title: US Presidential Election 2024
Status: Open
Volume: $1,234,567.89
---
ID: market-124
Title: Oscar Best Picture 2024
Status: Open
Volume: $234,567.89
---输入模式：
{
"market_id": {
"type": "string",
"description": "Market ID or slug"
}
}响应示例：
Current Market Prices for US Presidential Election 2024
Outcome: Democratic
Price: $0.6500
Probability: 65.0%
---
Outcome: Republican
Price: $0.3500
Probability: 35.0%
---输入模式：
{
"market_id": {
"type": "string",
"description": "Market ID or slug"
},
"timeframe": {
"type": "string",
"description": "Time period for historical data",
"enum": ["1d", "7d", "30d", "all"],
"default": "7d"
}
}响应示例：
Historical Data for US Presidential Election 2024
Time Period: 7d
Time: 2024-01-20T12:00:00Z
Price: $0.6500
Volume: $123,456.78
---
Time: 2024-01-19T12:00:00Z
Price: $0.6300
Volume: $98,765.43
---该服务器包括针对各种场景的全面错误处理：
速率限制（429 个错误）
无效的 API 密钥（403 错误）
无效的市场 ID（404 错误）
网络连接问题
API 超时条件（30 秒超时）
格式错误的响应
错误消息以清晰、人类可读的格式返回。
Python 3.9 或更高版本
httpx>=0.24.0
mcp-核心
python-dotenv>=1.0.0
欢迎贡献代码！欢迎提交 Pull 请求。对于重大变更，请先提交一个 issue 来讨论您想要修改的内容。
Get historical price and volume data for a market
| Name | Required | Description | Default |
|---|---|---|---|
| market_id | Yes | Market ID or slug | |
| timeframe | No | Time period for historical data | 7d |
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. While it indicates this is a read operation ('Get'), it lacks details on permissions, rate limits, data freshness, or error handling. For a tool fetching historical market data, this omission is significant, as users need to understand constraints like data availability or API limits.
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: 'Get historical price and volume data for a market'. It's front-loaded with the core purpose, has zero waste, and is appropriately sized for a simple tool. Every word earns its place without redundancy.
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 complexity (historical data retrieval with parameters) and lack of annotations and output schema, the description is incomplete. It doesn't explain what the return values look like (e.g., data format, fields), potential limitations (e.g., max timeframe), or how it differs from siblings. For a tool without structured output documentation, this leaves gaps in usability.
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%, so the input schema already documents both parameters ('market_id' and 'timeframe') with descriptions and an enum for 'timeframe'. The description adds no additional parameter semantics beyond implying historical data retrieval, which is already covered by the tool's purpose. Baseline 3 is appropriate as the schema handles most documentation.
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: 'Get historical price and volume data for a market'. It specifies the verb ('Get'), resource ('historical price and volume data'), and target ('for a market'). However, it doesn't explicitly distinguish this tool from sibling tools like 'get-market-prices' or 'get-market-info', which might also retrieve market data but with different scopes or timeframes.
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 provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'get-market-prices' or 'get-market-info', nor does it specify scenarios where this tool is preferred (e.g., for historical analysis vs. current data). Without such context, users might struggle to choose between similar tools.
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 prediction market
| Name | Required | Description | Default |
|---|---|---|---|
| market_id | Yes | Market ID or slug |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It states the tool retrieves 'detailed information' but doesn't specify what that includes (e.g., market status, participants, outcomes), whether it's read-only (implied by 'Get'), or any behavioral traits like rate limits, authentication needs, or error handling.
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 directly states the tool's purpose without unnecessary words. It's appropriately sized for a simple tool with one parameter and is front-loaded with the core action.
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 no annotations and no output schema, the description is incomplete. It doesn't explain what 'detailed information' entails, the return format, or how this tool fits with siblings. For a tool that likely returns complex market data, more context is needed to guide effective use.
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 the single parameter 'market_id' documented as 'Market ID or slug'. The description adds no additional parameter semantics beyond what the schema provides, such as format examples or valid slug patterns, so it meets the baseline for high schema coverage.
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 resource ('detailed information about a specific prediction market'), making the purpose unambiguous. However, it doesn't explicitly differentiate from siblings like 'get-market-history' or 'get-market-prices', which likely provide different types of market data.
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 provides no guidance on when to use this tool versus alternatives like 'list-markets' or 'get-market-history'. It doesn't specify prerequisites, such as needing a market ID, or contextual factors like whether this is for real-time data or historical analysis.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get current prices and trading information for a market
| Name | Required | Description | Default |
|---|---|---|---|
| market_id | Yes | Market ID or slug |
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 states the tool retrieves 'current prices and trading information', implying a read-only operation, but doesn't specify aspects like rate limits, authentication needs, data freshness, or error handling. For a tool with zero annotation coverage, this leaves significant gaps in understanding its behavior.
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 directly states the tool's purpose without any wasted words. It is front-loaded with the core functionality, making it easy to parse and understand quickly.
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 parameter, no output schema, no annotations), the description is adequate but has clear gaps. It covers the basic purpose but lacks usage guidelines and behavioral details, making it incomplete for optimal agent decision-making in a context with sibling tools.
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 has 100% description coverage, with the 'market_id' parameter clearly documented as 'Market ID or slug'. The description adds no additional meaning beyond this, such as examples or format details, but since the schema does the heavy lifting, the 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 tool's purpose with a specific verb ('Get') and resource ('current prices and trading information for a market'), making it easy to understand what it does. However, it doesn't explicitly differentiate itself from sibling tools like 'get-market-info' or 'get-market-history', which might also retrieve market-related data, so it doesn't reach the highest score.
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 provides no guidance on when to use this tool versus alternatives like 'get-market-info' or 'get-market-history'. It lacks context about specific use cases, prerequisites, or exclusions, leaving the agent to infer usage based on tool names alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a list of prediction markets with optional filters
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of markets to return (default: 10) | |
| offset | No | Number of markets to skip (for pagination) | |
| status | No | Filter by market status (e.g., open, closed, resolved) |
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 mentions 'optional filters' but fails to describe key behaviors: whether this is a read-only operation, how pagination works with limit/offset, what the default sorting is, or what the response format looks like. For a listing tool with zero annotation coverage, this leaves significant gaps in understanding its operation.
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 front-loads the core purpose ('Get a list of prediction markets') and adds essential qualification ('with optional filters'). There is no wasted language, and every word serves to clarify the tool's function appropriately for its complexity.
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 lack of annotations and output schema, the description is incomplete for a listing tool with 3 parameters. It doesn't explain the return format, pagination behavior, or any error conditions. While the schema covers parameters well, the overall context for agent usage remains underspecified, especially for behavioral aspects.
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 all parameters well-documented in the schema (limit, offset, status with enum values). The description adds minimal value beyond the schema by mentioning 'optional filters,' which aligns with the status parameter but doesn't provide additional context or examples. This meets the baseline for high schema coverage.
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 resource ('list of prediction markets'), making the purpose immediately understandable. It distinguishes this tool from its siblings (get-market-history, get-market-info, get-market-prices) by focusing on listing with filters rather than retrieving specific market details. However, it doesn't explicitly contrast with siblings beyond the general 'list' vs 'get' distinction.
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 through 'with optional filters,' suggesting this tool is for filtered listing operations. However, it provides no explicit guidance on when to use this tool versus its siblings (e.g., use list-markets for overviews vs get-market-info for details) or any prerequisites. The context is clear but lacks specific alternatives or exclusions.
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-market-historyget-market-infoget-market-priceslist-marketsScored across 4 tools
The tools have overlapping purposes that could cause confusion. get-market-history, get-market-info, and get-market-prices all retrieve data about a specific market, making it unclear which to use for different needs. However, the descriptions provide some guidance on the type of data each returns (historical vs. current vs. detailed info), which helps reduce misselection.
All tool names follow a consistent verb_noun pattern with hyphens (e.g., get-market-history, list-markets). The naming is predictable and uniform across all four tools, making it easy for agents to understand the pattern and purpose at a glance.
With only 4 tools, the server feels thin for a prediction market domain, which typically involves actions like creating markets, placing bets, or managing positions. While the tools cover data retrieval well, the lack of operational tools (e.g., trade, create-market) suggests the scope is limited, bordering on under-provisioned for the apparent purpose.
There are significant gaps in the tool surface for a prediction market server. The tools only support read-only operations (get and list), with no ability to interact with markets (e.g., trade, resolve, create). This will cause agent failures when trying to perform common actions in this domain, as the surface is severely incomplete for the stated purpose.
Polymarket in your AI: market rules, real fill costs, who is trading, top traders. Read-only.
Live prediction markets: Polymarket + Kalshi prices, odds, order books. Pay-per-call USDC, no key.
Live Polymarket odds, order books, fee-inclusive quotes and non-custodial prediction trading.
Polymarket MCP — prediction-market data via Gamma + CLOB + Data public APIs.