- Explore MCP Servers
- FunMcp
Funmcp
What is Funmcp
FunMcp is a minimalist AI-integrated service that allows users to configure their own MCP Server pool. It enables the association of MCP Servers through Agents, allowing all MCP Servers to be shared among various Agents.
Use cases
Use cases for FunMcp include creating chatbots for customer support, integrating AI capabilities into existing applications, and developing tools that require real-time communication with users.
How to use
To use FunMcp, configure the AccessToken in the appsettings.json file, create an Application to obtain an API key, and create Agents to bind MCP Servers. Use the Chat API by adding the api-key header in the HTTP request.
Key features
Key features of FunMcp include integration with Azure and OpenAI services, support for multiple AI models, and a straightforward API for chat interactions. It also provides management APIs for handling Applications, Agents, and MCP Servers.
Where to use
FunMcp can be used in various fields such as customer service automation, chatbot development, and any application requiring AI-driven interactions.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Overview
What is Funmcp
FunMcp is a minimalist AI-integrated service that allows users to configure their own MCP Server pool. It enables the association of MCP Servers through Agents, allowing all MCP Servers to be shared among various Agents.
Use cases
Use cases for FunMcp include creating chatbots for customer support, integrating AI capabilities into existing applications, and developing tools that require real-time communication with users.
How to use
To use FunMcp, configure the AccessToken in the appsettings.json file, create an Application to obtain an API key, and create Agents to bind MCP Servers. Use the Chat API by adding the api-key header in the HTTP request.
Key features
Key features of FunMcp include integration with Azure and OpenAI services, support for multiple AI models, and a straightforward API for chat interactions. It also provides management APIs for handling Applications, Agents, and MCP Servers.
Where to use
FunMcp can be used in various fields such as customer service automation, chatbot development, and any application requiring AI-driven interactions.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Content
FunMcp
这是一个极简的集成AI的服务,用户可以配置自己的MCP Server池,通过Agent去关联MCP Server,所有MCP Server可以在各个Agent中共用。
配置完成后,可通过Chat API在自己的业务服务中直接调用Agent。
后端服务说明
-
环境:.NET 9、 EF Core
-
配置:
{
"Logging": {
"LogLevel": {
"Default": "Information",
"Microsoft.AspNetCore": "Warning",
"Microsoft.EntityFrameworkCore": "Warning"
}
},
"AllowedHosts": "*",
"AccessToken": "123456", // API 认证的AccessToken
"AIConfig": {
"DefaultAI": "Azure", //默认的AI 服务
"Configs": {
"Azure": { //AI 服务名称
"Type": "AzureOpenAI", // 支持OpenAI和AzureOpenAI两种
"Endpoint": "https://xxxxx.openai.azure.com/", // OpenAI和AzureOpenAI请求地址
"ApiKey": "xxxxxxxxx", //OpenAI和AzureOpenAI的API Key
"DefaultModelId": "gpt-4o-mini", //默认模型
"Models": { //支持的模型列表
"GPT-4o-mini": "gpt-4o-mini",
"GPT-4o": "gpt-4o",
"DeepSeekV3": "DeepSeek-V3"
}
}
}
}
}
Manage API使用说明
-
先配置appsettings.json中的AccessToken。
-
Manage API请求需要在Http Request Headers中添加 Authorization: Bearer {AccessToken}
Chat API使用说明
使用前提
-
创建 Application,获取应用api-key。
-
创建Agent,绑定MCP Server
-
Http Request Headers添加 api-key header.
Chat API 只需要api-key header,不需要Authorization header
API
-
Post /api/chat 对话API
-
Get /api/chat/agent/tools/{agentId} 根据agent获取绑定的MCP Server和tools
-
Get /api/chat/agent/tools/{agentId}/{mcpId} 根据agent和指定mcp server获取该mcp server的tools
-
Get /api/chat/agent/mcp/{agentId} 根据agent获取绑定的MCP Server信息
Road Map
- ✅ Application Manage
- ✅ Agent Manage
- ✅ MCP Server Manage
- ✅ Chat API
- ❌ WEB UI
- ❌ A2A
- ❌ Application/Agent Usage Statistics
推荐几个MCP站点
Dev Tools Supporting MCP
The following are the main code editors that support the Model Context Protocol. Click the link to visit the official website for more information.










