`experiment_performance_stats`

Experiment-level performance statistics from Metadata.io Experiments API.

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

What it does

Experiment-level performance statistics from Metadata.io Experiments API.

USE FOR:
- Experiment-level metrics (spent, leads, impressions, clicks, cpl, ctr, mql)
- Campaign comparisons (A vs B, time periods)
- Triggered/influenced opportunities analysis
- Pipeline opportunity analysis from campaigns
- Campaign ingredients (audience size, channel, audience/ad/offer used)
- ROI analysis, trend analysis, top performers
- Creative usage by experiments
- Filtering by experiment/campaign names
- Filtering by launch status via launchedExperimentStatuses (FAILED / DISCONNECTED experiments are excluded by default — see that parameter)

NOT FOR:
- Experiment pacing status ("which experiments are underpacing")
- Ad-level triggered opportunities
- Ingredient-level analysis (use performance_metrics)

RETURNED DATA: spent, clicks, impressions, leads, mqls, cpl, cpc, cpm, ctr | opens, sends, actionClicks, costPerOpen, costPerSend (CONVO/MESSAGE ads) | adTypes (list of ad types in this experiment) | triggeredAmount, oppsAmount, cpMql, mqlRate, conversionRate | experimentName, campaignName, audienceName, offerName, adName | audienceTypes, audienceSize, channel, goal | imageLibraryName | startDate, endDate, pacing, quarterIndex

CONVO/MESSAGE AD CAVEAT: when adTypes contains CONVO or MESSAGE, success is measured by opens, sends, and actionClicks (and costPerOpen / costPerSend), NOT clicks/ctr/cpc. An experiment with $100K+ spend and 0 clicks where adTypes includes CONVO can be a top performer — assess on the right metric. To rank conversational performance explicitly, use sort='actionClicks,desc' or sort='opens,desc' instead of the lead-gen defaults.

LINK FORMAT: /hub/advertise/experiments?name={wizExperimentName}

RULES:
- 'cpl2Score,desc' for Lead Gen/unspecified, 'cpc2Score,desc' for Brand Awareness
- 'triggeredAmount,desc' for ROI/pipeline, 'oppsAmount,desc' for influenced pipeline
- size=1 for 'top' singular, size=requested for 'top X', size=50 for plural, size=15 default
- failed/non-launched experiments are excluded by default; pass launchedExperimentStatuses=['Failed'] ONLY when the user explicitly asks about failures

Arguments

Argument	Type	Notes
`metrics`	array	List of metrics for secondary ordering when question involves multiple metrics (e.g., ['cpl', 'ctr', 'leads']). Only include when analyzing more than one metric simultaneously. Do NOT include for single metric questions.
`minSpend`	number	Minimum spend threshold. REQUIRED for all campaigns except Brand Awareness. Use for Lead Generation and when campaign type is unspecified.
`minLeads`	integer	Minimum leads threshold. REQUIRED for Lead Generation campaigns. Do NOT use for Brand Awareness campaigns.
`minCpl`	integer	Minimum cost per lead threshold (whole dollars). REQUIRED for Lead Generation campaigns. Do NOT use for Brand Awareness campaigns.
`minAudienceSize`	integer	Minimum audience size to filter experiments
`minClicks`	integer	Minimum clicks threshold. REQUIRED for Brand Awareness campaigns only. Do NOT use for Lead Generation campaigns.
`minCpc`	integer	Minimum cost per click threshold (whole dollars). Do NOT use for Lead Generation or unspecified campaign types.
`size`	integer	Number of results to return. RULES: size=1 for 'top' singular questions, size=requested number for 'top X' questions, size=50 for plural questions (e.g. 'campaigns'), size=30+ for multiple metrics analysis, size=15 as default when not specified. Raise it freely for full-dataset analytics — there is
`sort`	string	Sorting parameter. CRITICAL RULES: 'cpl2Score,desc' for Lead Generation or unspecified campaigns, 'cpc2Score,desc' for Brand Awareness, 'triggeredAmount,desc' for ROI/pipeline questions, 'oppsAmount,desc' for influenced pipeline, 'conversionRate,desc' for conversion rate, 'internalStatus,desc' for a
`goals`	string	Campaign goal type. RULES: 'CPL' for Lead Generation campaigns, 'CTR' for Brand Awareness campaigns. Do NOT include for unspecified campaign types. When multiple metrics involved, use only the first metric's corresponding goal. one of: `CPL`, `CTR`
`name`	object	Experiment name filter, matched as ONE substring per request. Use 'name' field (NOT experimentName) for specific experiment questions. Can be a single string or an array of strings for multiple experiments; an array is queried one name per request and the results are merged. Do NOT add additional pa
`campaignName`	object	Campaign name filter. Use when question is about specific campaign(s). Can be single string or array ['campaign1', 'campaign2'] for multiple campaigns. Do NOT include additional parameters when filtering by specific campaign name.
`audienceName`	string	Filter by target audience name (e.g., 'WTS EMEA Jan25_EMEAPitchbook')
`offerName`	string	Filter by specific offer name (e.g., 'AMER_ZO_EN_HBR Reimagining Work'). Use this field when question mentions specific offers.
`adName`	string	Filter by specific ad name (e.g., 'Sifted_WorkShift_Ad5_Beige'). Use 'adName' field when question asks about specific ad names.
`audienceTypes`	string	Comma-separated list of audience types (e.g., 'Spotlight Retargeting Contacts (Dynamic),Technographic (Aberdeen)')
`imageLibraryName`	string	Filter by creative/image name (e.g., 'JP - Square-Ad15.png'). Use 'imageLibraryName' field when question asks about specific creative names.
`offerTypes`	array	Offer types filter. RULES: ['LP'] for lead gen forms/landing pages questions, ['LP', 'LG'] as default when offer types mentioned. LP=Landing Pages, LG=Lead Gen forms. Should NOT be empty when included.
`channels`	array	Marketing channels to include
`visibilities`	array	Visibility status filter
`launchedExperimentStatuses`	array	Filter experiments by launch status. DEFAULT when omitted: successfully-launched experiments only (Active, WithoutSpend, Paused, Completed) — Failed and Disconnected are EXCLUDED, because a failed/non-launched experiment has 0 leads and is a non-starter, not a 'bottom performer'. Pass values explici
`timeFrame`	string	Timeframe aggregation. CRITICAL RULES: Use ONLY for WEEK or QUARTER questions. NEVER use 'YEAR' - use startDate/endDate instead. If timeFrame is included, DO NOT add startDate or endDate parameters under any circumstances. one of: `WEEK`, `QUARTER`
`startDate`	string	Start date in ISO 8601 format (e.g., '2024-10-18T00:00:00.000Z'). CRITICAL: Do NOT include if timeFrame parameter is used. Use last year of data if period cannot be inferred from question. For specific campaigns/experiments without timeframe, omit this parameter.
`endDate`	string	End date in ISO 8601 format. Must end on last hour of date (e.g., '2024-11-21T23:59:59.999Z'). CRITICAL: Do NOT include if timeFrame parameter is used. For specific campaigns/experiments without timeframe, omit this parameter.

Request

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":"experiment_performance_stats","arguments":{}}}'

Response

Real, from the production server, in 1262 ms. Values that identify a customer or disclose money are replaced with typed placeholders; keys, types and nesting are exactly as returned.

recorded response

"[value redacted]"

Other analytics tools:

All 160 tools · machine-readable index

experiment_performance_stats

What it does

Arguments

Request

Response

Related

`experiment_performance_stats`