What can you do with this server?

This MCP server lets you query Chinese ICP filing records and violation blacklists for websites, apps, mini programs, and quick apps, plus check runtime environment and view configuration. * Query ICP filing information (icp_query) by keyword (name), with optional type (web / app / mapp / kapp), pagination (page, page_size), and per-call proxy. * Query illegal/violating blacklists (icp_blacklist) by keyword (name), with optional type (bweb / bapp / bmapp / bkapp) and per-call proxy. * Check the Python runtime environment, dependencies, and supported query types (check_environment). * View the current ICPQuery-MCP service configuration (config_show).

How do I use ICPQuery-MCP?

1. Click on "Deploy 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., "@ICPQuery-MCP query icp filing for baidu.com" 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.

ICPQuery-MCP

by helGayhub233

Overview Schema Source Related Servers Discussions Admin

Python

Remote

支持类型

类型	能力
网站备案	域名、主体名称、备案号等关键词查询
App 备案	App 名称、主体名称等关键词查询，可选补充详情
小程序备案	小程序名称、主体名称等关键词查询，可选补充详情
快应用备案	快应用名称、主体名称等关键词查询，可选补充详情
违法违规黑名单	网站、App、小程序、快应用黑名单查询

Related MCP server: Metaso Search MCP Server

快速开始

源码要求 Python >=3.10，MCP Python SDK mcp[cli]>=2.3.0,<3；锁文件和当前回归验证使用 SDK 2.3.0。

1. 安装 uv

uvx（uv 自带）是 Python 生态中 npx 的等价物——在临时隔离环境中下载并运行包，无需全局安装。

# Linux / macOS（官方安装脚本）
curl -LsSf https://astral.sh/uv/install.sh | sh

# macOS（Homebrew）
brew install uv

2. 配置 MCP 客户端

将以下配置加入支持 MCP 的客户端（Claude Desktop、Cursor 等），无需预先安装 ICPQuery-MCP：

{
  "mcpServers": {
    "icp-query": {
      "command": "uvx",
      "args": ["icpquery-mcp"],
      "env": {
        "ICP_PROXY_TUNNEL": "http://127.0.0.1:7890"
      }
    }
  }
}

目标接口有创宇盾防护，高频访问或特定 IP 可能触发拦截。触发拦截时通过 ICP_PROXY_TUNNEL 走代理访问；不需要代理时移除 env 或将值留空。代理地址须带协议前缀（http://、https:// 或 socks5://）。

版本锁定（生产环境推荐）：将 args 替换为 ["--from", "icpquery-mcp==0.5.0", "icpquery-mcp"]，避免随发布版本浮动。

频率限制已内置默认值（query 5 次/分钟、blacklist 3 次/分钟），无需额外配置。完整配置示例见 mcp.json.example 和 config.example.yml。

其他安装方式

pip：

python -m pip install -U icpquery-mcp
icpquery-mcp

此时将客户端配置中的 command 改为 icpquery-mcp，args 设为 []。

pipx：

pipx install icpquery-mcp
icpquery-mcp

从源码：

git clone https://github.com/helGayhub233/ICPQuery-MCP.git
cd ICPQuery-MCP
uv sync
uv run icpquery-mcp

从源码运行时，推荐在客户端配置中固定项目目录：

{
  "mcpServers": {
    "icp-query": {
      "command": "uv",
      "args": ["--directory", "/absolute/path/to/ICPQuery-MCP", "run", "icpquery-mcp"]
    }
  }
}

配置

环境变量

环境变量统一使用 ICP_ 前缀。config_show 和 check_environment 会将已配置的代理地址显示为 <configured>，避免凭据泄漏到 MCP 对话上下文。

环境变量	说明	默认值
`ICP_TIMEOUT`	HTTP 请求超时秒数	`30`
`ICP_CONCURRENCY`	详情补全并发数（固定为串行，不可调）	`1`
`ICP_RATE_LIMIT_ENABLED`	是否启用 MCP 工具频率限制	`true`
`ICP_RATE_LIMIT_QUERY_PER_MIN`	`icp_query` 每分钟允许次数	`5`
`ICP_RATE_LIMIT_BLACKLIST_PER_MIN`	`icp_blacklist` 每分钟允许次数	`3`
`ICP_RATE_LIMIT_MAX_CONCURRENT`	查询工具最大并发数（固定为串行，不可调）	`1`
`ICP_PROXY_TUNNEL`	固定代理地址，例如 `socks5://127.0.0.1:1080`	—
`ICP_PROXY_POOL_URL`	代理池 API 地址（当前保留）	—
`ICP_PROXY_POOL_SIZE`	代理池大小（当前保留）	—
`ICP_PROXY_POOL_IPV6`	本地 IPv6 出口轮换开关（当前保留）	—

工具列表

工具	说明	参数
`icp_query`	查询 ICP 备案信息	`name`（关键词）、`type`（`web`/`app`/`mapp`/`kapp`，默认 `web`）、`page`（默认 `1`）、`page_size`（最大 `26`）、`proxy`（单次代理）、`include_details`（默认 `false`）、`max_detail_enrichment`（默认及最大 `10`）
`icp_blacklist`	查询违法违规黑名单	`name`（关键词）、`type`（`bweb`/`bapp`/`bmapp`/`bkapp`，默认 `bweb`）、`proxy`（单次代理）
`config_show`	查看当前运行配置	—
`check_environment`	检查运行环境、依赖和支持类型	—

proxy 参数优先级高于 ICP_PROXY_TUNNEL 环境变量。

实际工具目录、参数与输出 Schema 以连接后 tools/list 为准。全部工具拒绝多余参数；空白关键词、无效类型和超出范围的分页参数会在外呼之前返回 validation_error。

查询结果保留 MIIT 的 code、success、message、params / data 字段。业务失败、参数校验失败和执行异常都返回 success=false、error.type、isError=true，并提供与文本 JSON 相等的 structuredContent。稳定错误类别包括 provider_error、validation_error、tool_not_found、timeout、network_error、http_error、invalid_response、captcha_error、provider_blocked、internal_error 和 output_too_large；参数错误不回显被拒绝的值，网络错误不回显代理 URL。工信部 code=500 保留既有客户端码 122，原始码在 error.details.provider_code 中。协议错误及取消继续交由 SDK 处理。

config_show 和 check_environment 保留各自原有的成功结果结构，输出 Schema 增加共同的失败分支。失败响应的完整性固定为 unknown，next_action=stop；分页信号冲突时返回 pagination_conflict 警告，不会据此宣称结果完整。可选详情请求失败会保留对应摘要并返回 detail_enrichment_failed 警告。

公开工具负载按 UTF-8 JSON 限制为 64 KiB，结构化结果和兼容文本副本分别受限；该值不代表两份内容的传输合计或 token 数。长字段保留前 4096 字符并附截断标记；记录按原始顺序保留可容纳的前缀，output 记录省略条数和裁剪字段数，returned_count 与实际返回条数一致。next_action=refine_query 表示本地裁剪，应缩小查询、关闭详情或减少 page_size 后再继续，直接翻页会跳过本页被省略的记录。记录标识不被改写；无法容纳的元数据返回 output_too_large。

本地 CLI

除 MCP 工具外，项目还提供独立的 CLI 入口 icpquery：

icpquery check-env              # 检查运行环境
icpquery config-show            # 查看当前配置
icpquery query baidu.com        # 查询网站备案
icpquery query 微信 -t app      # 查询 App 备案
icpquery query baidu.com -t bweb  # 查询网站黑名单

请求限制

项目在单个 MCP server 实例内做本地保护，避免客户端并发请求直接打到目标接口。

工具	控制方式
`icp_query`	同一 server 实例共享队列执行，默认每分钟 `5` 次
`icp_blacklist`	同一 server 实例共享队列执行，默认每分钟 `3` 次
App/小程序/快应用详情补全	串行执行

Qoder 等 MCP 客户端可能默认并发触发 5-10 个 tool call；同一 server（同一 ToolLimiter）实例会强制串行化，前一个查询完整结束后，下一个查询才会访问目标接口。多 server/worker 部署如需跨实例保持同样约束，须提供外部协调机制。

MCP 协议兼容性

服务使用官方 MCPServer API，同时兼容 2026-07-28 新协议和 2025-11-25 旧协议。SDK 会根据客户端自动选择 server/discover 或传统 initialize 流程，无需启动两套服务。

2026-07-28 的静态目录和发现结果提供 5 分钟 public 缓存提示，配置示例资源提供 1 小时 public 提示；客户端可据此复用，变更通知可提前使缓存失效。查询结果、config_show 和 check_environment 属于动态工具调用，不设置缓存提示。旧协议由 SDK 省略不适用的缓存字段。

项目结构

src/icpquery_mcp/
  server.py              # MCP 入口
  mcp_server.py          # 参数、异常契约与缓存提示
  responses.py           # 业务状态、分页与输出预算
  models.py              # 结构化结果与错误模型
  cli.py                 # 本地 CLI
  core/
    client.py            # 工信部接口调用、token、验证码和详情补全
    captcha.py           # 滑块验证码偏移识别
    config.py            # YAML 和环境变量配置
    ratelimit.py         # 频率控制和单例队列保护
  tools/
    local_tools.py       # MCP 工具与 CLI 复用封装

开发

# 编译检查
python -m compileall src

# 检查运行环境
icpquery check-env

# 单元测试
python -m unittest discover -s tests -v

# 构建
uv build

版本记录见 CHANGELOG.md。

注意事项

本项目仅供学习和技术研究使用，严禁用于任何商业或非法用途。

请只在合法授权范围内使用，并自行承担接口变化、验证码策略变化、目标风控或网络环境导致的失败风险。

许可证

MIT License，见 LICENSE。

Available Tools

4 tools

check_environmentA

检查 ICPQuery-MCP 的 Python 运行环境、依赖和支持的查询类型。

Name	Required	Description	Default
No parameters

Output Schema

Name	Required	Description
No output parameters

TDQS

A3.9/5.0

Behavior3/5

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

With no annotations, the description carries full burden. It mentions checking environment, dependencies, and supported query types, which implies a read-only operation. However, it does not detail any potential side effects or access requirements. The output schema covers return values, mitigating some lack of detail.

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 in Chinese that immediately conveys the tool's purpose. No unnecessary words.

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

Completeness5/5

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

Given zero parameters, an output schema, and sibling tools, the description provides sufficient information to understand the tool's function. No gaps are evident.

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

Parameters4/5

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

There are zero parameters, so the baseline is 4. The description does not need to add parameter info, and it appropriately leaves it out.

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 checks the Python runtime environment, dependencies, and supported query types for ICPQuery-MCP. It distinguishes itself from siblings like icp_query (querying) and icp_blacklist (blacklist management).

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 on when to use this tool versus alternatives. The description does not provide context about prerequisites or scenarios where this tool is appropriate.

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

config_showA

查看当前 ICP 查询服务配置。

Name	Required	Description	Default
No parameters

Output Schema

Name	Required	Description
No output parameters

TDQS

A3.9/5.0

Behavior2/5

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

No annotations are provided, and the description does not explicitly state that the tool is read-only or non-destructive. It only describes the basic operation, leaving the agent to infer behavioral traits.

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 sentence that is front-loaded with the verb and resource, containing no extraneous words. Every word earns its place.

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

Completeness5/5

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

Given the tool's simplicity (0 parameters) and the presence of an output schema (though not shown here), the description is complete. It effectively states the tool's function without needing to explain return values.

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

Parameters4/5

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

The tool has 0 parameters, so the schema coverage is trivially 100%. Per guidelines, baseline is 4. The description adds no parameter info, but none is needed.

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 ('view') and the resource ('ICP query service configuration'), and the sibling tools (check_environment, icp_blacklist, icp_query) are distinct in function, making the purpose unambiguous.

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 for viewing configuration but provides no explicit guidance on when to use this tool versus siblings or when not to use it. A minimal viable score is appropriate given simplicity.

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

icp_blacklistC

查询工信部违法违规黑名单，支持 bweb/bapp/bmapp/bkapp。

Name	Required	Default
`name`	Yes
`type`	No	bweb
`proxy`	No

Output Schema

Name	Required	Description
No output parameters

TDQS

C2.6/5.0

Behavior2/5

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

With no annotations, the description carries full burden but only mentions supported types. It does not disclose authentication needs, rate limits, whether it's a search or match, or behavioral traits like pagination or data recency.

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 concise (one line) and front-loaded with purpose, but it sacrifices necessary detail, making it under-specified rather than efficiently concise.

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 queries a sensitive blacklist, the description lacks context about usage, return format (though output schema exists), and how parameters affect results. It fails to compensate for the 0% schema coverage.

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 coverage is 0%, yet the description adds no meaning to parameters beyond the supported types hint for the 'type' parameter. 'name' and 'proxy' remain unexplained.

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 queries the MIIT illegal blacklist, specifying supported types (bweb/bapp/bmapp/bkapp). However, it does not differentiate from sibling icp_query, which likely serves a similar purpose for ICP records.

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 on when to use this tool versus alternatives like icp_query. The description mentions supported types but provides no exclusions or prerequisites.

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

icp_queryC

查询工信部 ICP 备案信息，支持 web/app/mapp/kapp。

Name	Required	Default
`name`	Yes
`page`	No
`type`	No	web
`proxy`	No
`page_size`	No

Output Schema

Name	Required	Description
No output parameters

TDQS

C2.7/5.0

Behavior2/5

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

With no annotations, the description should disclose key behaviors. It only mentions supported types but lacks information on authentication, rate limits, error handling, or result structure. This is insufficient for an agent to understand the tool's side effects or constraints.

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, concise and front-loaded with the verb 'query'. However, it is under-specified for the tool's complexity; while not verbose, it could be more informative without being lengthy.

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 5 parameters, no schema descriptions, and an output schema, the description is very incomplete. It does not explain pagination, default values, or output format, leaving significant gaps for an agent to use it correctly.

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?

The input schema has 5 parameters with 0% description coverage. The description only adds context for the 'type' parameter (web/app/mapp/kapp). It fails to explain 'name', 'page', 'proxy', or 'page_size', leaving the agent guessing their purpose.

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 queries ICP filing information from the Ministry of Industry and Information Technology, and lists supported types (web/app/mapp/kapp). It is specific about the resource and actions, but does not explicitly differentiate from sibling tools like icp_blacklist.

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?

The description implies usage by mentioning supported types, but provides no explicit guidance on when to use this tool versus alternatives (e.g., icp_blacklist). No context about prerequisites or when not to use it.

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.

4 tool updatesv0.1.0Jul 10, 2026
- First observedcheck_environment
- First observedconfig_show
- First observedicp_blacklist
- First observedicp_query

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.5/5.0

Scored 2026-07-10 09:15 across 4 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: environment check, config display, blacklist query, and ICP query. No overlap or ambiguity.

Naming Consistency5/5

All tools follow the same verb_noun snake_case pattern (check_environment, config_show, icp_blacklist, icp_query), providing consistent and predictable naming.

Tool Count5/5

With 4 tools, the set is well-scoped for its purpose: two core query tools plus two auxiliary tools for environment and configuration. Not too many or too few.

Completeness4/5

The core ICP query and blacklist functionalities are covered with support for multiple record types. Minor gaps exist (e.g., no tool to update configuration), but the surface is largely complete for its stated purpose.

Maintenance

ActivityMaintained

ResponsivenessNo issues

Resources

Related MCP Connectors

IP Location MCP A
cn.pianam.mcp
MCP server for IPv4 geolocation with Chinese output: country/region/city, ISP and ASN.
Location Services Networking & Infrastructure
1
https://mcp.pianam.cn/ip-mcp/mcp
broker-safety A
com.brokerchooser
MCP server offering regulator-sourced legitimacy checks on investment entities by name or URL.
Finance Search Government Data
12
https://mcp.brokerchooser.com/servers/mcp
sentrysurface
io.github.sentrysurface
Cybersecurity MCP server for URL scanning, threat intelligence, and domain reputation.
Security Penetration Testing
2
https://api.sentrysurface.io/mcp/mcp
China Hot Trending MCP A
cn.pianam.mcp
MCP server aggregating hot-search boards from 8 Chinese platforms (Weibo, Zhihu, Bilibili, Douyin).
Social Media Web Scraping
1
https://mcp.pianam.cn/hot-mcp/mcp

Related MCP Servers

crawl-mcp
Browser Automation Web Scraping Search
gqy20
A
license
A
quality
C
maintenance
MCP server for web crawling, searching, and AI-powered content extraction, supporting single-page, batch, and full-site crawling along with text, news, image, book, and video search.
Updated 5 months ago (2026-06-12 02:27 UTC)
8
33 PyPI
1
MIT
Metaso Search MCP Server
Search Web Scraping
SecretRichGarden
A
license
A
quality
D
maintenance
MCP server for Metaso Search API, providing multi-scope search and webpage reading tools.
Updated 8 months ago (2026-03-05 12:49 UTC)
2
29 npm
2
Apache 2.0
WebToolsHub
konkomaji
A
license
Not graded
quality
D
maintenance
MCP server providing domain name checking and other web tools, accessible via MCP, REST API, and CLI for AI assistants.
Updated 2 months ago (2026-09-04 20:15 UTC)
MIT
MAScope MCP Server
Search Research & Data
bbb-build
A
license
A
quality
D
maintenance
MCP server for MAScope: search and analyze World MiniApps, get verified reviews and analytics data.
Updated 6 months ago (2026-05-03 13:44 UTC)
6
18 npm
MIT