Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@China-Central-Policy-MCP search for policies about artificial intelligence from June 2025"
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.
面向 gov.cn 的国务院政策检索与解析 MCP 服务器，提供“政策列表检索 + 政策正文抓取”两类工具，直接返回结构化数据。
政策检索：基于 gov.cn 官方检索接口/页面，支持关键词与日期范围过滤
正文获取：从政策 URL 抓取并解析正文，统一输出结构化字段
真实数据：对接真实政府站点，非模拟数据
简单稳定：仅请求首页（p=1），每页固定 100 条（n=100），不翻页，性能稳定
Related MCP server: ChinaRxiv MCP Server
get_latest_policies按关键词与日期范围检索政策列表（来自 sousuo.www.gov.cn 官方检索接口）。
参数
startdate（可选）：开始日期，格式 YYYY-MM-DD
enddate（可选）：结束日期，格式 YYYY-MM-DD
limit（可选）：返回条数上限，默认 100，最大 100
keyword（可选）：检索关键词（标题/正文/摘要范围）
行为说明
仅请求首页：p=1, n=100，不自动翻页（一般不超过 100 条）
解析官方返回中的 catMap.*.listVO（并兼容旧式 results）
清洗标题与摘要中的 HTML 标签（如 <em>、<br/>）
统一日期格式：优先时间戳字段（如 ptime），否则解析 YYYY.MM.DD/中文日期
返回 debug.requested_urls 与 debug.catmap_list_lengths 便于排查
返回字段（items 中的每条记录）
policy_id、title、level、category、date、url
summary、issuing_agency、document_number、file_type
catalog：来源分类（如 gongwen、bumenfile、gongbao）
调用示例
{
"name": "get_latest_policies",
"arguments": {
"keyword": "人工智能",
"startdate": "2025-06-19",
"enddate": "2025-08-19",
"limit": 100
}
}get_policy_fulltext从政策 URL 抓取并解析正文为结构化 JSON，优化适配 gov.cn 页面。
参数
url（必填）：政策详情页 URL
policy_id（可选）：内部 ID（可忽略）
返回字段
policy_id、title、date、doc_no、issuer、url、body
调用示例
{
"name": "get_policy_fulltext",
"arguments": {
"url": "https://www.gov.cn/zhengce/zhengceku/202507/content_7031216.htm"
}
}npm install
npm run buildnode build/index.jsnpm install -g supergateway
npx supergateway --stdio "node build/index.js" --port 3100{
"mcpServers": {
"china-policy": {
"command": "node",
"args": ["path/to/build/index.js"]
}
}
}{
"mcpServers": {
"china-policy": {
"type": "sse",
"url": "http://localhost:3100/sse",
"timeout": 600
}
}
}官网“政策/最新”入口：gov.cn 最新政策
内容：国务院政策、部门文件、公告等
作者声明：本项目仅供学习、教学与学术研究使用。开源的目的在于帮助有需要的分析师与研究者更高效地开展政策信息分析与复现工作。
使用边界：本项目不面向生产环境或商业化部署，作者不对任何此类用途进行背书或提供保证。如需用于生产/商业场景，请自行完成充分的合规审查与测试，并自行承担全部风险与责任。
禁止性用途：不得将本项目用于任何违法、侵权、违规或不道德的用途，包括但不限于：
绕过网站服务条款、访问控制或反爬机制；
大规模抓取、存储、传播受版权保护或包含个人信息的数据；
制造或传播虚假/误导性内容，或用于舆论操纵；
任何违反适用法律法规、数据合规与隐私保护要求的行为。
数据来源与合规：本项目对接公开的政府网站入口。使用者应自行确认目标站点的使用条款、robots 协议、访问频率限制与版权要求，合理控制请求频率，避免对对方服务造成不当负载。
免责声明：项目按“现状”提供，不作任何明示或默示担保（包括但不限于适销性、特定用途适用性与非侵权）。在法律允许的最大范围内，作者不对因使用本项目而导致的任何直接或间接损失承担责任。
版权与许可：本项目采用 Apache-2.0 许可证发布。许可证条款是约束使用的唯一法律文本；本节“法律声明与使用限制”表述的是作者的使用态度与合规提示，不构成对许可证的修改。如对许可证与本声明存在理解冲突，以许可证条款为准。
合规与移除：如您认为本项目中的说明或工具可能引发合规风险，或出于正当权利主张提出移除/更正请求，请通过下述联系方式与作者取得联系。
Apache-2.0
LinkedIn：Xingyu Chen
GitHub：guangxiangdebizi
NPM：xingyuchen
Search State Council policies using gov.cn official search API with keyword search and date filtering.
| Name | Required | Description | Default |
|---|---|---|---|
| startdate | No | Start date in YYYY-MM-DD format | |
| enddate | No | End date in YYYY-MM-DD format | |
| limit | No | Max number of items to return (default: 100, max: 100) | |
| keyword | No | Keyword to search in policy content, titles and summaries |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description only mentions the API source and features. It fails to disclose behaviors such as rate limits, pagination, sorting, or response format, leaving significant gaps for an AI agent.
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 with 17 words, efficiently conveying the core purpose 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?
For a search tool with no output schema, the description lacks details on return format, pagination, or effective usage. However, the schema fully documents parameters, and the sibling tool provides some context.
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 description adds minimal value beyond the schema. It reiterates 'keyword search and date filtering' which aligns with the schema, but does not provide additional contextual meaning.
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 searches State Council policies via gov.cn API with keyword and date filtering, distinguishing it from the sibling tool 'get_policy_fulltext'.
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 searching policies, while 'get_policy_fulltext' is for retrieving full texts, but it does not explicitly state when to use this tool or provide alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch policy full text and normalize into structured JSON (title, date, doc_no, body, issuer). Optimized for gov.cn pages.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Policy page URL | |
| policy_id | No | Optional internal policy id |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It states that the tool fetches and normalizes content, indicating a read operation. However, it does not disclose potential failure modes, permissions needed, or rate limits. The optimization note adds some context but not full transparency.
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 sentence that immediately conveys the action and result. It includes essential detail (the output fields) and a relevant optimization note. No redundant words; it is efficiently front-loaded.
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 complexity of fetching and parsing web pages, the description provides moderate completeness. It explains the output format but omits error handling, timeouts, or limitations (e.g., only works on gov.cn). With no output schema, more detail on potential failures would improve 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%, so the schema already describes parameters. The description adds value by specifying the output structure (title, date, doc_no, body, issuer), which is not in the schema. This helps the agent understand what the tool returns, beyond what the input 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 states what the tool does: fetch policy full text and normalize into structured JSON with specific fields (title, date, doc_no, body, issuer). It also specifies the optimization for gov.cn pages, which distinguishes it from the sibling tool get_latest_policies that lists policies rather than fetching full text.
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 provide explicit guidance on when to use this tool versus alternatives. It implies that it is for fetching full text of a specific policy, and the sibling is for listing, but it lacks explicit when-not or alternative usage notes.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The two tools have clearly distinct purposes: get_latest_policies searches and filters policies, while get_policy_fulltext retrieves the full text and normalizes it. There is no overlap.
Both tools follow a consistent verb_noun pattern (get_latest_policies, get_policy_fulltext), using 'get' as the verb and descriptive nouns.
With only 2 tools, the server is minimal but well-scoped for a focused domain (search and retrieve policy full texts). It could benefit from additional tools like browsing by category, but the current count is reasonable.
The core workflow of searching for policies and retrieving their full text is covered. Minor gaps exist, such as the absence of a tool to list policies without keyword search or direct ID lookup, but overall it is sufficiently complete for its stated purpose.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Official EUR-Lex, UK, US, and gazette search, metadata fetch, and change-only watches.
Judged, citation-checked policy corpus over MCP. Keyless public reads; API key for AI tools.
Search US grants + federal contracts (Grants.gov + SAM.gov) from any LLM.
Resolve, search and verify legal citations against the official sources, with provenance.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/guangxiangdebizi/China-Central-Policy-MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
