MMetadata /docs
⌘K
Docs/Tools/query_metadata_analytics_account

query_metadata_analytics_account

Query the caller's own account CONTEXT from the Metadata.io knowledge base — a rolled-up summary (firmographic, recent 90-day campaign history, open drafts, per-experiment perfo…

Read analytics

Returns data. Calling it changes nothing, so it is safe in an unattended loop.

What it does

Query the caller's own account CONTEXT from the Metadata.io
knowledge base — a rolled-up summary (firmographic, recent 90-day
campaign history, open drafts, per-experiment performance) refreshed
overnight. Use it to GROUND a recommendation or plan in the account's
own history before you suggest or generate something.

USE FOR: firmographic (industry, size, revenue, country) and
high-level recent-history context to back a decision — e.g. "given our
recent LinkedIn performance, what should we try next quarter?".

NOT FOR the account's CURRENT LIVE STATE. This is a periodic roll-up,
not the live platform — it can miss or misreport granular state (e.g.
answer "nothing runs in Germany" while many live campaigns target
Germany). For "what's running / what's live", "which campaigns target
<country/segment>", "list our campaigns / audiences / offers", or
real-time spend / pacing, use the live platform analytics tools instead
(`account_level_stats`, `performance_metrics`, `demographic_country_stats`,
`search_campaigns_by_names`, etc.). Also NOT FOR industry benchmarks
(use `query_metadata_analytics_benchmarks`) or a different company
(cross-tenant queries are rejected).

The caller's `account_id` is resolved server-side from the caller's own
credentials and reflects any active account switch. It cannot be supplied
or overridden by the caller.

Arguments

ArgumentTypeNotes
question string required Natural-language question about the caller's account.

Request

Request template, not a complete runnable example. Replace placeholders, empty objects, arrays, and zero values with valid account-specific inputs. Read required fields and nested constraints in the full schema. Confirm the account, connected channels, and referenced assets before calling a write tool.

curl
curl -s -X POST https://mcp-server.metadata.io/mcp \
  -H "Authorization: $METADATA_PAT" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "MCP-Protocol-Version: 2025-11-25" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"query_metadata_analytics_account","arguments":{"question":"<question>"}}}'

Response

Recorded with these arguments. Enum values are the first the tool's own schema declares; ids were fetched live from a list_ call immediately before.

arguments used
{
 "question": "What were the top performing channels in the last 30 days?"
}

Real, from the production server, in 36963 ms. Values that identify a customer or disclose money are replaced with typed placeholders; keys, types and nesting are exactly as returned.

recorded response
{
 "status": "refused",
 "tool": "[tool redacted]",
 "refused_reason": "[refused_reason redacted]",
 "row_count": 0,
 "rows": [],
 "columns": [],
 "sql": "[sql redacted]",
 "conversation_id": "[conversation_id redacted]",
 "message": "[message redacted]"
}

Other analytics tools:

Browse the tool catalog · machine-readable index