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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.