mockoon-mcp
Lets AI assistants create and manage Mockoon mock APIs through natural language.
README
mockoon-mcp
An MCP server that lets AI assistants (Claude, GitHub Copilot, Cursor, etc.) create and manage Mockoon mock APIs through natural language.
Requirements
- Node.js 18+
- Mockoon Desktop — for managing environment files via the UI
- Mockoon CLI (optional) — required only if you want to use the
start_server/stop_servertools to start mock servers programmatically (npm install -g @mockoon/cli)
Configuration
No installation needed. Configure your AI client using npx:
VS Code / GitHub Copilot
Create .vscode/mcp.json in your workspace:
{
"servers": {
"mockoon": {
"type": "stdio",
"command": "npx",
"args": ["-y", "mockoon-mcp@latest"]
}
}
}
Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"mockoon": {
"command": "npx",
"args": ["-y", "mockoon-mcp@latest"]
}
}
}
Cursor
Edit ~/.cursor/mcp.json (global) or .cursor/mcp.json in your project:
{
"mcpServers": {
"mockoon": {
"command": "npx",
"args": ["-y", "mockoon-mcp@latest"]
}
}
}
Environment variables
| Variable | Description |
|---|---|
MOCKOON_STORAGE_DIR |
Override the primary storage directory (default: Mockoon Desktop's storage folder) |
MOCKOON_DATA_DIRS |
Semicolon-separated list of additional directories to search for environment files |
Default storage path:
- Windows:
%APPDATA%\mockoon\storage - macOS/Linux:
~/.config/mockoon/storage
Example:
"env": {
"MOCKOON_DATA_DIRS": "/path/to/dir1;/path/to/dir2"
}
Available Tools
Environments
| Tool | Description |
|---|---|
list_environments |
List all environments with file path and port |
create_environment |
Create a new environment |
delete_environment |
Permanently delete an environment file |
Routes
| Tool | Description |
|---|---|
list_routes |
List all routes in an environment (UUID, method, endpoint, response count) |
get_route |
Inspect a single route with all responses, rules, headers and body |
create_route |
Create a route with a single default response |
create_route_with_responses |
Create a route + N responses (default + conditionals) in one call |
bulk_create_routes |
Create N routes in one call — ideal for scaffolding an entire API |
update_route |
Update method, endpoint, documentation and/or default response fields |
duplicate_route |
Clone a route (all responses included) with new UUIDs |
delete_route |
Delete a route and all its responses |
add_route_response |
Add a conditional/alternative response to an existing route |
set_default_response |
Change which response is marked as default |
get_default_response |
Return the current default response (quick inspect) |
Databuckets (Templates)
| Tool | Description |
|---|---|
list_templates |
List all databuckets in an environment |
create_template |
Create a new databucket |
update_template |
Update the content of a databucket |
delete_template |
Delete a databucket |
Server
| Tool | Description |
|---|---|
start_server |
Start a mock server for an environment |
stop_server |
Stop a running mock server |
list_running_servers |
List all currently running mock servers |
Note:
start_serverandstop_serverrequire Mockoon CLI to be installed globally (npm install -g @mockoon/cli). If you only use Mockoon Desktop, these tools will not work — but all other tools (environments, routes, databuckets) work without CLI.
Example Prompts
Here are some example phrases you can say to your AI assistant to interact with Mockoon via this MCP server:
Exploring environments and routes
- "List all available Mockoon environments."
- "Show me all the routes in the Taccuino environment."
- "Get the full detail of route
GET /users/:id, including all responses and rules."
Creating routes
- "Create a
GET /productsroute in the Demo API environment that returns a JSON array of 3 products with status 200." - "Add a
POST /auth/loginroute with two responses: 200 with a token body and 401 Unauthorized." - "Scaffold a full CRUD API for a
Taskresource under/tasksin the Demo environment."
Updating and managing routes
- "Change the default response of
GET /usersto return status 204 with an empty body." - "Duplicate the
GET /ordersroute." - "Delete the
DELETE /legacy/endpointroute from the environment." - "Add a conditional 403 response to
POST /documentsthat triggers when theX-Roleheader equalsguest."
Databuckets
- "Create a databucket called
UserListin the Demo API with a JSON array of 5 fake users." - "Update the
ProductCatalogdatabucket with a new list of items."
Server management
- "Start the mock server for the Taccuino environment."
- "Stop all running mock servers."
- "Which Mockoon environments are currently running?"
How It Works
The server communicates via stdio (JSON-RPC 2.0). It reads and writes Mockoon's environment JSON files directly, no REST API involved.
Changes made by the MCP server are reflected in Mockoon Desktop automatically if the Environment file watcher is enabled. Go to Application → Settings and set it to Auto for silent reloads.
License
MIT — see LICENSE.
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。
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。
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。
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。