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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.