Model Context Protocol
MCP server
Use SuaveHooks from Cursor or Claude Desktop to list endpoints, inspect captures, and replay webhooks — without leaving your editor.
How it works
The MCP server is a small local program that your IDE launches. It speaks MCP over stdio and calls the SuaveHooks REST API on your behalf.
You run locally: Cursor / Claude Desktop → suavehooks-mcp binary
We host: https://suavehooks.com (capture, storage, API)
Nothing extra to deploy — download the binary, create an API key, and point the MCP config at this site.
Download
Self-contained binaries ship with every
GitHub Release
of the public suavehooks-cli repository.
Extract the archive and use the SuaveHooks.Mcp executable inside
(SuaveHooks.Mcp.exe on Windows).
MCP server
The release also includes CLI helper scripts
and an mcp.json.example you can copy into your MCP config.
Setup
-
1. Create an API key
Sign up or sign in, then create a key under API Keys. Keys start with
sh_and are shown once at creation. -
2. Download and extract the MCP binary
Pick your platform above, extract the archive, and note the full path to the executable.
# macOS example tar xzf suavehooks-mcp-osx-arm64.tar.gz chmod +x SuaveHooks.Mcp -
3. Add to Cursor or Claude Desktop
In Cursor: Settings → MCP → Add server (or edit your MCP config JSON directly). Set
SUAVEHOOKS_API_URLto this site and paste your API key.Cursor / Claude MCP config{ "mcpServers": { "suavehooks": { "command": "/path/to/SuaveHooks.Mcp", "env": { "SUAVEHOOKS_API_URL": "https://suavehooks.com", "SUAVEHOOKS_API_KEY": "sh_your_api_key_here" } } } }For local development, use
http://localhost:8080instead. Clone suavehooks-cli to run from source:dotnet run --project src/SuaveHooks.Mcp.
Available tools
list_endpoints
List webhook endpoints for your account.
create_endpoint
Create a new capture endpoint (name, optional targetUrl).
list_requests
List captured requests for an endpoint (endpointId, optional limit).
get_request
Full capture details including body and forward deliveries (requestId).
replay_request
Replay a capture to a target URL (requestId, optional targetUrl).
Ready to connect? Create an API key, download the binary above, and add the MCP server to Cursor. For HTTP integration without MCP, see the REST API docs.