Devnors Data MCP Server
Enables MCP clients to discover capabilities and call legal, enterprise, content, and express APIs using a Devnors Data API Key.
README
Devnors Data MCP Server
简体中文 | English
Use Devnors Data in MCP clients such as Codex, Claude Desktop, Cursor, WorkBuddy, and other AI assistant tools.
Devnors Data MCP helps your assistant discover available capabilities, inspect required parameters, and call legal / enterprise / content / express APIs with your Devnors Data API Key.
Supported Clients
You can use Devnors Data MCP with any MCP-compatible client that supports remote HTTP or local stdio servers, including:
- Codex
- Claude Desktop
- Cursor
- WorkBuddy
- Other MCP-compatible AI assistants
For Codex, add Devnors Data as a remote MCP server and use the Remote HTTP URL and Authorization header below.
Quick Start
Remote HTTP
Remote HTTP is the recommended way to use Devnors Data MCP. No local Python install is required.
{
"mcpServers": {
"devnors-data": {
"url": "https://data.devnors.com/mcp",
"headers": {
"Authorization": "Bearer devnors_sk_live_xxx"
}
}
}
}
Create an API Key in the developer console.
Local stdio
You can also run the MCP server locally after pip install devnors-mcp.
{
"mcpServers": {
"devnors-data": {
"command": "python",
"args": ["-m", "devnors_mcp.server"],
"env": {
"DEVNORS_API_KEY": "devnors_sk_live_xxx"
}
}
}
}
On Windows, client PATH often cannot find devnors-mcp. Prefer the python -m
form above, or set command to an absolute Python path.
Token
Use your Devnors Data API Key in one of these ways:
Authorization: Bearer devnors_sk_live_xxx
or, for local stdio:
DEVNORS_API_KEY=devnors_sk_live_xxx
Bearer … is the recommended Authorization format.
Optional private / self-hosted base URL for local stdio:
DEVNORS_DATA_BASE_URL=https://data.devnors.com
Things You Can Ask
Ask your MCP client naturally:
List available Devnors Data capabilities and required filters.
More examples:
Search Chinese legal judgment documents for private lending interest disputes.
Look up current PRC law articles about contract termination.
Get company registration details for this credit code.
Check whether this company is on the dishonest judgment debtor list.
Show today's Douyin hot rank.
Track this express parcel with company code and tracking number.
The API returned insufficient_balance. What should I do next?
The API returned rate_limited. Help me retry safely.
The assistant can call list_capabilities first, explain required parameters,
invoke the selected tool after you provide values, and help interpret common
error codes.
Tools
| Tool | Description |
|---|---|
list_capabilities |
Discover live domain/type, filters, fields, examples, errors |
legal_case_search |
Legal judgment documents |
legal_law_search |
Current law articles |
content_keyword_index |
Keyword traffic index |
content_keyword_expand |
Keyword expansion |
content_wechat_index |
WeChat Index |
content_hot_rank |
Weibo / Douyin hot rank |
enterprise_company_detail |
Company registration details |
enterprise_annual_report |
Annual reports |
enterprise_tax_invoice |
Tax invoice information |
enterprise_shixin_check |
Dishonest judgment debtor check |
enterprise_zhixing_check |
Enforcement debtor check |
cloud_express |
Express tracking |
data_query |
Unified entry for any domain + type |
Billing and Errors
Successful calls return units and request_id. Failures return structured
fields so the agent can self-correct:
code |
Meaning | retryable |
|---|---|---|
unauthorized |
Missing / invalid key | no |
insufficient_balance |
Need top-up | no |
rate_limited |
Rate limited | yes |
invalid_capability |
Bad domain/type | no |
not_implemented |
Planned capability | no |
unavailable / upstream_error |
Temporary failure | yes |
Retryable 429 / 5xx errors are retried by the underlying Python SDK with
bounded backoff. The MCP layer does not stack extra retries.
Related
- Python SDK: devnors-data-python
- Docs: https://data.devnors.com/docs
- Product site: https://data.devnors.com
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。