RequestBin MCP Server
Enables AI coding agents to create webhook bins, inspect and replay HTTP requests, and stand up mock API endpoints directly from the editor.
README
@requestbin/mcp-server
Use RequestBin directly in Claude Code, Cursor, Windsurf, and any MCP-compatible AI coding agent.
Create webhook bins, inspect captured HTTP requests, replay them, and stand up mock API endpoints — all without leaving your editor.
Installation
npm install -g @requestbin/mcp-server
Or run directly with npx:
npx @requestbin/mcp-server
Get an API Key
- Go to requestbin.net/api-keys
- Create a new API key
API keys and MCP access are available on every plan, including FREE (5 keys per account). Per-feature limits (bin count, mock endpoint count, custom mock slug) still apply per plan — see requestbin.net/pricing.
Configuration
Claude Code
Add to your project's .mcp.json or ~/.claude/settings.json:
{
"mcpServers": {
"requestbin": {
"command": "requestbin-mcp",
"env": {
"REQUESTBIN_API_KEY": "rb_your_key_here"
}
}
}
}
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"requestbin": {
"command": "requestbin-mcp",
"env": {
"REQUESTBIN_API_KEY": "rb_your_key_here"
}
}
}
}
Cursor
Add to Cursor Settings > MCP Servers:
{
"requestbin": {
"command": "requestbin-mcp",
"env": {
"REQUESTBIN_API_KEY": "rb_your_key_here"
}
}
}
Windsurf
Add to ~/.windsurf/mcp_config.json:
{
"mcpServers": {
"requestbin": {
"command": "requestbin-mcp",
"env": {
"REQUESTBIN_API_KEY": "rb_your_key_here"
}
}
}
}
Available Tools
Webhook bins & replay:
| Tool | Description |
|---|---|
list_bins |
List all your webhook bins with URLs and stats |
create_bin |
Create a new webhook bin (returns URL for webhook endpoint) |
get_bin |
Get bin details including recent interactions |
delete_bin |
Delete a webhook bin |
list_interactions |
List captured HTTP requests for a bin (method, headers, body) |
replay_request |
Send an HTTP request to any URL (server-side replay) |
get_replay_status |
Check the status of a replay job |
list_servers |
List available servers for bin creation |
Mock APIs (*.rbmock.dev):
| Tool | Description |
|---|---|
list_mock_endpoints |
List your mock endpoints with slug, URL, and rule count |
create_mock_endpoint |
Create a mock endpoint (returns live {slug}.rbmock.dev URL) |
add_mock_rule |
Append a routing rule (match method/path → status + headers + body) |
deploy_mock |
Publish the current rule set so the live mock server picks it up |
list_mock_captures |
List recent requests that hit a mock endpoint — verify your integration is actually calling the mock URL |
Example Workflow
Here is what a typical conversation looks like with an AI agent that has the RequestBin MCP server configured:
You: "Create a webhook bin for testing my Stripe integration"
The agent will:
- Call
list_serversto find available servers - Call
create_binwith name "Stripe Webhooks" - Return the bin URL to configure in your Stripe Dashboard
You: "Show me the last 5 requests to my Stripe webhook bin"
The agent will:
- Call
list_binsto find your bins - Call
list_interactionswith the bin ID and limit of 5 - Display the HTTP method, path, headers, and body of each captured request
You: "Replay the last webhook event to my local server at localhost:3000/webhooks"
The agent will:
- Call
list_interactionsto find the most recent request - Call
replay_requestwith the same method, headers, and body targetinghttp://localhost:3000/webhooks - Call
get_replay_statusto confirm delivery
You: "Stand up a mock Stripe API that returns 200 for POST /v1/charges and 402 for POST /v1/charges/decline"
The agent will:
- Call
create_mock_endpointwith name "Stripe mock" — gets back a live URL likehttps://abc12.rbmock.dev - Call
add_mock_ruletwice (one per path) with the matching status codes and JSON bodies - Call
deploy_mockto publish — the URL is now ready to point your integration at
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
REQUESTBIN_API_KEY |
Yes | -- | Your API key from requestbin.net/api-keys |
REQUESTBIN_BASE_URL |
No | https://requestbin.net |
Custom API base URL (for self-hosted instances) |
REQUESTBIN_MOCK_DOMAIN |
No | rbmock.dev |
Domain that hosts mock endpoints (override for self-hosted) |
Requirements
- Node.js >= 18
- A RequestBin account (FREE tier works — API/MCP is open to every plan)
Development
npm install
npm run dev # runs with tsx (hot reload)
npm run build # compile TypeScript to dist/
License
MIT
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
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.