WebAPI MCP 服务器
@yinzhouzhi
About WebAPI MCP 服务器
(一键将传统业务系统转换成智能体)支持将传统的WebAPI,转换成MCP工具的mcp服务器
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"webapi-mcp-server": {
"command": "npx",
"args": [
"-y",
"@yinzhouzhi/webapi-mcp-server",
"start"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is WebAPI MCP 服务器?
WebAPI MCP 服务器 converts traditional Web APIs into MCP (Model Context Protocol) tools, enabling direct integration between legacy business systems and large language models without requiring custom interface development. It supports batch registration of API definitions from JSON or Markdown files or directories, and allows setting default request headers globally for all registered APIs.
How to use WebAPI MCP 服务器?
Install via npx or clone the repository and run npm install and npm start. Configure using a JSON/YAML/YML configuration file specifying API directories, individual API files, and global headers, or via environment variables (WEBAPI_CONFIG_FILE, WEBAPI_APIS_DIR, WEBAPI_DEBUG). Define APIs in JSON or Markdown format and use built-in MCP tools to register, unregister, list, and manage them.
Key features of WebAPI MCP 服务器
- Converts any Web API to an MCP tool
- Dynamic runtime registration and removal of APIs
- Centralized global request header management
- Supports multiple parameter types and validation
- Extracts specific data from nested responses via result path
- Batch loads API definitions from files or directories
Use cases of WebAPI MCP 服务器
- Directly connect existing enterprise HTTP APIs to LLM applications without extra code
- Expose internal weather, database, or authentication APIs as MCP tools
- Centralize API permission control by setting default authorization headers
- Rapidly prototype MCP-compatible tools from legacy REST endpoints
FAQ from WebAPI MCP 服务器
How does WebAPI MCP 服务器 differ from RAG-based approaches?
It replaces vector database retrieval with direct API calls, providing more precise and reliable data without data chunking or embedding, and is simpler to deploy.
What API definition formats are supported?
Both JSON and Markdown formats are supported. JSON requires name, description, url, method; Markdown uses headings (name, URL, method, parameters, headers, result path, etc.).
Can I set global headers for all API calls?
Yes. Global headers can be defined in the configuration file via the globalHeaders object or set dynamically using the set_default_headers MCP tool.
What MCP tools are built into the server?
The server provides register_web_api, set_default_headers, list_registered_apis, unregister_api, load_api_from_file, load_apis_from_directory, and load_from_config.
Does WebAPI MCP 服务器 work with Cursor or other MCP clients?
Yes. It can be added as an MCP server in Cursor by using the npx command with the package @yinzhouzhi/webapi-mcp-server start in the MCP client configuration.
More Other MCP servers
Mcp
browsermcpBrowser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
MCP Toolbox for Databases
googleapisMCP Toolbox for Databases is an open source MCP server for databases.
Awesome-MCP-ZH
yzflyMCP 资源精选, MCP指南,Claude MCP,MCP Servers, MCP Clients
Nginx UI
0xJackyYet another WebUI for Nginx
Blender
ahujasidOpen-source MCP to use Blender with any LLM
Comments