MCP Server Reference

MCP Server Reference

MCP Server Reference

This is the technical reference for the Watching That MCP Server. For setup instructions specific to your AI platform, see the AI & LLM Platforms section:


What is the MCP Server?

The Watching That MCP server lets you interact with your platform data through AI assistants. Instead of building queries manually in the Analysis module, you can ask questions in plain English and get answers drawn from your live operational data.

"Show me fill rate by distribution partner for the last 7 days"


Available Tools

The MCP server exposes 7 tools:

Tool

What It Does

Read / Write

Tool

What It Does

Read / Write

current_user

Get your authenticated user info (ID, name, organisation)

Read

list_accessible_orgs

Discover all organisations your account can access

Read

list_available_metrics

Get all metrics for an organisation (code, name, description, scope, applicable databases)

Read

list_available_dimensions

Get all dimensions for an organisation (field, name, description, applicable databases)

Read

allowed_long_term_dim_combinations

Get valid rollup dimension combinations — prevents query failures on historical data

Read

search

Execute data queries — the core workhorse

Read

save_search

Save the last search query server-side for reuse

Write

The search tool

Accepts a full query structure: organisation selection, date ranges (ISO 8601 or relative like today-7d), metric columns (including formulas), groupBy configurations (time intervals, Top N, specific segments), and filters with 16+ comparison operators.


What's Not Covered

The following are only available through the web application: column-level metric filters, conditional formatting, visualisation configuration, saved explorations, Reports module, Monitoring module, and user/org administration.


Connection URL

https://mcp.<instance>.watchingthat.<tld>/mcp?api_key=<your_api_key>

Your Customer Success representative will provide the complete URL. See the platform-specific guides above for how to use it.


Example Use Cases

  • Daily briefing: "Create a daily briefing report for yesterday"

  • Revenue analysis: "Show October revenue by channel with eCPM"

  • Fill rate monitoring: "Show fill rate by distribution partner for the last 7 days"

  • Top advertisers: "Top 50 advertisers by revenue for programmatic, last month"

  • Troubleshooting: "Why is eCPM for one of my channels significantly below the portfolio average?"

  • Week-over-week: "Compare this week vs last week revenue by channel"

  • Save for reuse: "Save that query so I can run it again tomorrow"


Tips for Best Results

  • Be specific about date ranges — "last 7 days", "October 2025", or "yesterday" all work

  • Name your metrics and dimensions — use the names from the Watching That platform. Ask the AI to list what's available if unsure

  • Start broad, then drill down — high-level question first, then follow-up

  • Specify the organisation — if your account has multiple orgs

  • Use formulas — ask for calculated metrics like fill rate, eCPM, or completion rate


Limitations

  • Read-only analytics — cannot create or modify reports, monitors, or configurations

  • No UI features — conditional formatting, visualisations, and widget layouts are web-only

  • Query scope — scoped to your account's organisations and data sources

  • Rate limits — standard API rate limits apply


FAQ

Q: Do I need a separate licence for the MCP server?
A: Contact your Customer Success representative to discuss MCP server access.

Q: Can I use it with AI clients other than those listed?
A: Yes. The server uses standard MCP over SSE, supported by any MCP-compatible client.

Q: Is my data secure?
A: Yes. API key authentication, same organisation-level permissions as the web app. The AI client does not store your data.

Q: Can multiple team members use it simultaneously?
A: Yes. Each user connects with their own API key.

Q: Error about invalid dimension combinations?
A: Not all dimension combinations are available on historical (rollup) data. Ask the AI to check allowed combinations, then adjust.


Still Need Help?