Mockmcp
About
Hosted MCP endpoint that returns realistic fake data for prototyping agents. Paste one URL into Claude Code, Cursor, or Claude Desktop — 12 pre-built tools covering users, products, orders, events, email, and knowledge base search. No signup, no config, no auth. Built for develop
Details
- Author
- K-Cupples
- Downloads
- 329
- Categories
- Developer Tools
Jump to
- 12 pre-built tools for common agent scenarios.
- Deterministic fake data seeded from client inputs.
- Works with Claude Code, Cursor, and Claude Desktop.
- Native Streamable HTTP transport — no proxy required.
- No signup, no config, no API keys.
- Free tier with rate limits (30 req/min, 500 req/day).
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
MockmcpCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Paste the URL https://mockmcp.io/mcp into Claude Code, Cursor, or Claude Desktop. All three clients support Streamable HTTP natively—no proxy needed. Tools are invoked by name (e.g., list_users or create_order) and all data is deterministically seeded from your inputs.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mockmcp": {
"mockmcp": {
"url": "https://mockmcp.io/mcp"
}
}
}
}
McpServers
{
"mockmcp": {
"url": "https://mockmcp.io/mcp"
}
}
What it is
MockMCP is a hosted Model Context Protocol endpoint that returns realistic fake data for prototyping agents. Paste one URL into Claude Code, Cursor, or Claude Desktop — no signup, no config, no API keys. 12 pre-built tools covering the scenarios in most agent tutorials. Built for developers who want to design and test agent workflows before the real backend exists. ## Quickstart Claude Code ```bash claude mcp add --transport http mockmcp https://mockmcp.io/mcp Cursor — add to ~/.cursor/mcp.json: { "mcpServers": { "mockmcp": { "url": "https://mockmcp.io/mcp" } } } Claude Desktop — Settings → Connectors → Add custom connector → paste https://mockmcp.io/mcp. All three clients speak Streamable HTTP natively. No mcp-remote proxy required. Tools ┌───────────────────────┬─────────────────────────────────────────┐ │ Tool │ What it does │ ├───────────────────────┼─────────────────────────────────────────┤ │ list_users │ Paginated list of mock users │ ├───────────────────────┼─────────────────────────────────────────┤ │ get_user │ One mock user by id or seed │ ├───────────────────────┼─────────────────────────────────────────┤ │ create_user │ Create a mock user (no persistence) │ ├───────────────────────┼─────────────────────────────────────────┤ │ list_products │ Paginated list of mock products │ ├───────────────────────┼─────────────────────────────────────────┤ │ get_product │ One mock product │ ├───────────────────────┼─────────────────────────────────────────┤ │ list_orders │ Mock orders with optional status filter │ ├───────────────────────┼─────────────────────────────────────────┤ │ get_order │ One mock order │ ├───────────────────────┼─────────────────────────────────────────┤ │ create_order │ Create a mock order (no persistence) │ ├───────────────────────┼─────────────────────────────────────────┤ │ list_events │ Mock analytics events │ ├───────────────────────┼─────────────────────────────────────────┤ │ create_event │ Record a mock event │ ├───────────────────────┼─────────────────────────────────────────┤ │ send_email │ Returns fake success, nothing delivered │ ├───────────────────────┼─────────────────────────────────────────┤ │ search_knowledge_base │ Mock KB search with ranked results │ └───────────────────────┴─────────────────────────────────────────┘ All data is seeded from your inputs — same input, same output across requests. Free tier limits - 30 requests per minute per hashed fingerprint - 500 requests per day per hashed fingerprint 429 responses include retry_after_seconds and an upgrade_url. Successful responses carry X-RateLimit-* headers. Drop your email at mockmcp.io/waitlist for paid-tier access when it launches. Links - Website: mockmcp.io - Source: github.com/K-Cupples/mockmcp (MIT) - Paid tier waitlist: mockmcp.io/waitlistSign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.





