list_monitoring_groupsLABSCO SUMMARY
Your competitive feed becomes something you can ask questions of.
The qualification has already happened inside Watchr, so what reaches the model is filtered signal rather than a scrape. That makes it usable for the thing people actually want — a weekly recap, a battle card update, a positioning comparison across tracked brands — instead of another dashboard to read.
What it is
The official remote server for Watchr, a competitive intelligence and brand monitoring platform. Watchr watches competitors' sites, ads, social posts and news and qualifies each signal against a prompt you define; this server exposes the resulting monitoring groups, tracked brands, insights and sent reports to an MCP client. Read-only.
What you get
- The monitoring groups your workspace runs, and the brands tracked under them
- Validated insights, searchable across your workspace
- A single insight in full, when you want the source behind a line in a summary
- The reports Watchr has sent, and any one of them fetched back
- Everything scoped to your workspace, so the answer is the movement Watchr already qualified as relevant rather than raw feed noise
Requirements
A Watchr workspace. The server is hosted at https://mcp.watchr.ai/mcp — no local install and no Docker. Clients that support Dynamic Client Registration sign in through a browser OAuth flow; everything else uses a personal API key generated in your workspace.
Setup effort
One command — claude mcp add --transport http watchr https://mcp.watchr.ai/mcp
USE CASES
01
Writing this week's competitive recap
Search the workspace for the period you care about and pull the insights behind it, then let the assistant draft the summary from them.
02
Seeing what is actually being watched
List the monitoring groups and the brands under each, so you know the coverage before you trust a gap.
03
Comparing positioning changes across brands
Pull the tracked brands, then search insights across them for the last 30 days and read the shifts side by side.
04
Picking up where the last report left off
List the reports Watchr has already sent and fetch the most recent one, so the new draft continues it instead of repeating it.
6 tools
Listed in project docs. Your client may show a different list.
list_brandssearch_insightsget_insightlist_reportsget_reportBEFORE YOU INSTALL
What to know first
Tools you get
6 tools named in the project's documentation.
Requires
A client that can reach a remote MCP server over HTTP
INSTALLATION
Connect your client
Server setup
claude mcp add
Claude Code — OAuth
TERMINAL
claude mcp add --transport http watchr https://mcp.watchr.ai/mcpHosted endpoint
ENDPOINT URL
https://mcp.watchr.ai/mcpAdd this hosted endpoint to your MCP client.
MCP Clients
ChatGPT — OAuth
Settings → Connectors → Add custom connector; MCP server URL https://mcp.watchr.ai/mcp; Authentication: OAuth
Cursor — OAuth
CURSOR — OAUTH · JSON
{
"mcpServers": {
"watchr": {
"url": "https://mcp.watchr.ai/mcp"
}
}
}Windsurf — API key
WINDSURF — API KEY · JSON
{
"mcpServers": {
"watchr": {
"serverUrl": "https://mcp.watchr.ai/mcp",
"headers": {
"Authorization": "Bearer wat_mcp_<<YOUR_KEY>>"
}
}
}
}VS Code — API key
VS CODE — API KEY · JSON
{
"servers": {
"watchr": {
"type": "http",
"url": "https://mcp.watchr.ai/mcp",
"headers": {
"Authorization": "Bearer wat_mcp_<<YOUR_KEY>>"
}
}
}
}Cursor — API key
CURSOR — API KEY · JSON
{
"mcpServers": {
"watchr": {
"url": "https://mcp.watchr.ai/mcp",
"headers": {
"Authorization": "Bearer wat_mcp_<<YOUR_KEY>>"
}
}
}
}
