Wincher Mcp
About
Unofficial Wincher SEO MCP server (stdio). Rankings, competitors, SERPs for Cursor and Claude Code. PyPI: wincher-mcp.
Details
- Author
- vmandic
- Downloads
- 216
- Categories
- Developer Tools
Jump to
- Read-only — no writes to your Wincher account
- Stdio transport — local process, no HTTP listener
- Nine focused tools covering common SEO data
- Hardened defaults: input limits, response caps, safe errors
- Optional TOON output to reduce LLM token usage
- Canonical open-source package on PyPI
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
Wincher McpCommand (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
Run as a local stdio MCP process spawned by the client; no HTTP listener. Nine focused tools are available for websites, keywords, rankings, competitors, SERPs, groups, bulk history, and annotations.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"wincher mcp": {
"wincher": {
"command": "wincher-mcp",
"args": [],
"env": {
"WINCHER_API_KEY": "YOUR_KEY_HERE"
}
}
}
}
}McpServers
{
"wincher": {
"command": "wincher-mcp",
"args": [],
"env": {
"WINCHER_API_KEY": "YOUR_KEY_HERE"
}
}
}Read-only Wincher SEO data for AI coding agents.
Connect Cursor, Claude Code, or any MCP client to your tracked websites: keyword rankings, competitors, SERPs, and groups, without leaving the editor.
https://github.com/vmandic/wincher-mcp
Read-only by design — GET-style Wincher API usage only; no writes to your account
Stdio MCP — local process spawned by the client; no HTTP listener
Nine focused tools — websites, keywords, rankings, competitors, SERPs, groups, bulk history, annotations
Hardened defaults — input limits, response caps, safe errors, optional staging host validation
Optional TOON output — compact Token-Oriented Object Notation responses to cut LLM token use on large keyword and ranking lists
Canonical open-source Wincher MCP server: PyPI package wincher-mcp, agent docs, CI, vendored OpenAPI, optional TOON output, and security hardening. Lineage from the early chris-tutt/wincher-mcp-server prototype; this repo is the maintained home for new work.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
