Watchr

Watchr MCP Server

Bring competitive intelligence and brand monitoring into your AI assistant. Ask Claude, Cursor, or any MCP-compatible client what your competitors did this week. Answers come straight from your Watchr workspace.

Watchr is a competitive intelligence and brand monitoring platform. It watches your competitors' websites, ads, social posts, news, and other sources, then qualifies each signal against a prompt you define, so what you see is relevant movement, not noise.

This repository documents the official Model Context Protocol (MCP) server for Watchr. It exposes account-scoped data and controlled account workflows. API keys provide read access; authorized OAuth administrators can also configure watchlists, manage members, record feedback and manage account tags.

The server is hosted by Watchr. No local install, no Docker. Just point your client at https://mcp.watchr.ai/mcp and authenticate. There are two paths, depending on your client:

• One-click OAuth for Claude (Desktop / Code), ChatGPT, Cursor and any other client supporting Dynamic Client Registration. Browser opens, you approve, done.
• Personal API key (generated in your Watchr workspace) for agentic frameworks and custom integrations where you embed the MCP into your own automation stack.

Table of contents

• What you can do with it
• Showcase
• Available tools
• Insight response contract
• Getting started with Watchr
• Authentication
  • Option A. One-click OAuth
  • Option B. Personal API key
• Configuration
  • OAuth clients
  • API key clients
• Improving your results
• Support

What you can do with it

Once connected, you can ask your AI assistant things like:

• "What did our competitors launch this week?"
• "Draft a Slack message summarizing the top 5 competitive insights from this month."
• "Compare positioning changes across our tracked brands over the last 30 days."
• "Build me a one-page competitive briefing on HubSpot from the last month, make it visual."
• "Automatically update my Notion battle cards and competitor recap pages with this week's Watchr insights."

The MCP server provides the data; your assistant handles the reasoning, drafting, and integration with the rest of your workflow.

Showcase

A short conversation with Claude pulling the latest HubSpot signals through Watchr:

Same data, one follow-up prompt later. Claude generates a designed competitive briefing artifact directly from the validated Watchr insights:

This is the core loop. Watchr collects and qualifies. Your AI client reasons and outputs. The MCP server is the glue.

Available tools

The default endpoint exposes 37 tools, including reads and writes. The dedicated ChatGPT profile exposes 62 tools, with individually named configuration preview/apply actions. Runtime tools/list is the source of truth for arguments, schemas and permissions.

Collections support their documented pagination and filters. Configuration uses a persistent preview followed by explicit approval before application. Reads require mcp:read; configuration and tag writes additionally require mcp:configure; member administration requires mcp:members:manage. Current roles and permissions are checked server-side. API keys remain read-only.

Previewing does not start collection, send emails or apply a change. Some apply actions launch external discovery or collection. Tag definitions do not reclassify history: classification jobs are explicit, bounded and budgeted, and preserve manual corrections by default. Recorded relevance feedback does not change qualification or perform replay.

New MCP-created watchlists have report preparation and email delivery disabled by default. Those two effects share one setting; disabling it does not stop collection. Existing report preferences are preserved.

Insight response contract

search_insights returns a compact discovery payload. Every item includes an id, a title, a factual summary, source and brand metadata, and an effective_date. The accompanying date_type says whether that effective date is the source publication date (published) or Watchr's detection date (detected). Website changes therefore remain safely dateable even when they have no publication date.

The search response intentionally omits the original description, qualification_analysis, raw dates, and related_items. This keeps result pages small enough for an AI client to rank and shortlist without spending its context window on source text it may never use.

When an item's title or summary is not clear enough, call get_insight with the returned id as insight_id before answering. get_insight provides the source description, qualification reasoning, published and detected dates, and any related validated insights. Consumers should not infer missing detail from the compact summary alone.

search_signals and get_signal expose watchlist-scoped topics, source relations and recorded report appearances. competitive_signal_id is a legacy shared grouping hint, not the authoritative topic identity. Historical report appearances may be unavailable when no structure was recorded. A stored snapshot timestamp is not proof of the actual screenshot capture time.

Getting started with Watchr

You need a configured Watchr workspace before the MCP server has anything interesting to return. The full path:

1. Create an account at watchr.ai/signup. A free tier is available.
2. Finalize your settings at watchr.ai/app/settings:
   • Add the brands and competitors you want to track
   • Specify the market you are monitoring (used to qualify relevance)
   • Subscribe to the newsletters and press feeds you want pulled in
   • Add the pages you want Watchr to monitor for changes (pricing, changelog, careers, etc.)
   • Add social media profiles to scrape (LinkedIn, Facebook, Instagram)
3. Wait for the first collected insights. Report preparation and delivery depend on watchlist settings; requesting a chat recap does not enable scheduled reports.
4. Connect the MCP server (see Authentication and Configuration) and start querying your insights from any AI client.

Authentication

The default endpoint is https://mcp.watchr.ai/mcp. The dedicated ChatGPT profile uses https://mcp.watchr.ai/mcp/chatgpt. There are two authentication methods, depending on the client.

Option A. One-click OAuth

Standard OAuth 2.1 with Dynamic Client Registration (RFC 7591) and PKCE. Your client self-registers, opens a browser window, you authorize Watchr access, and tokens are stored transparently by the client. No copy/paste, no manual rotation.

OAuth clients can use the authorization flow above:

• Claude Desktop
• Claude Code
• ChatGPT, using its dedicated endpoint and the connector/plugin setup available to the account
• Cursor (recent versions)

If your client is in this list, jump straight to OAuth clients. No key generation needed.

Option B. Personal API key

For agentic frameworks, custom integrations, scripts, Windsurf, VS Code extensions, or any client that doesn't support OAuth, Watchr issues long-lived API keys prefixed with wat_mcp_.

To generate a key:

1. Sign in at watchr.ai
2. Go to Integrations → MCP in your workspace
3. Click Create API key
4. Give it a descriptive name (e.g. "My LangGraph agent", "Windsurf, work laptop"), optionally set an expiry date
5. Copy the key immediately. Watchr only displays the full key once. The dashboard stores a prefix and a hash, so a lost key cannot be recovered (revoke and regenerate).

Pass the key as a Bearer token on every request:

Authorization: Bearer wat_mcp_<your-key>

Most MCP clients let you declare this via a headers field in their config. Examples in API key clients.

A few notes on security:

• Treat the key like a password. Read-only doesn't mean low-risk: it can see all your competitive intelligence.
• One key per device or integration, named clearly. Revoke and re-issue from Integrations → MCP if a laptop is lost.
• Set an expiry date on keys for CI or shared environments.
• Keys inherit your account's access. They cover every active monitoring group in the account.

Don't have a Watchr account yet? Create one for free.

Configuration

OAuth clients

For all clients below, the server URL is https://mcp.watchr.ai/mcp and authentication is triggered automatically on first connection.

Claude Desktop

Edit claude_desktop_config.json (Settings → Developer → Edit Config):

{
  "mcpServers": {
    "watchr": { "url": "https://mcp.watchr.ai/mcp" }
  }
}

Restart Claude Desktop. Watchr appears in the connectors panel. Click it to complete OAuth.

Claude Code

claude mcp add --transport http watchr https://mcp.watchr.ai/mcp

Then run /mcp inside Claude Code and click Authenticate next to Watchr.

ChatGPT

Settings → Connectors → Add custom connector:

• MCP server URL: https://mcp.watchr.ai/mcp
• Authentication: OAuth

ChatGPT triggers the OAuth flow on first use.

Cursor

Settings → MCP → Add new MCP server:

{
  "watchr": { "url": "https://mcp.watchr.ai/mcp" }
}

API key clients

First generate an API key, then pass it as a Bearer token in the client config.

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "watchr": {
      "serverUrl": "https://mcp.watchr.ai/mcp",
      "headers": { "Authorization": "Bearer wat_mcp_<your-key>" }
    }
  }
}

VS Code

Add to .vscode/mcp.json (or user settings):

{
  "servers": {
    "watchr": {
      "type": "http",
      "url": "https://mcp.watchr.ai/mcp",
      "headers": { "Authorization": "Bearer wat_mcp_<your-key>" }
    }
  }
}

Cursor (without OAuth)

Same JSON shape as the OAuth version with an added headers block:

{
  "watchr": {
    "url": "https://mcp.watchr.ai/mcp",
    "headers": { "Authorization": "Bearer wat_mcp_<your-key>" }
  }
}

Custom agentic frameworks

LangGraph, CrewAI, Mastra, n8n, custom Python or TypeScript agents, etc. Connect to https://mcp.watchr.ai/mcp over streamable HTTP and attach the header Authorization: Bearer wat_mcp_<your-key> to every request. Any MCP-compatible SDK works.

Improving your results

If your assistant says it has "no relevant insights" or returns thin results, the data lives upstream in your Watchr workspace. Make Watchr smarter and the MCP gets smarter:

• Add monitored pages (competitor pricing, changelog, careers, product pages)
• Complete social profiles by adding LinkedIn, Facebook, Instagram handles for each tracked brand
• Refine the qualifying prompt at the monitoring-group level. It decides what counts as "relevant". Tighten it (more specific themes you care about) or broaden it (catch more) based on what's getting through.
• Add more news and press sources. The more sources, the higher the signal density.

Everything is configurable at watchr.ai/app/settings.

Support

• Bug reports and feature requests: open an issue in this repo
• General questions and feedback: contact@watchr.ai
• Status and uptime: the MCP endpoint shares status with the main Watchr platform

Built by the Watchr team. MIT licensed.