Niches · Product analytics & experimentation

Look up one user's events, flags or segment membership

Four or more companies' docs show a full fit.

7companies, full fit
6companies, fit with a limit
23companies carry the tag
6share of the category's work
3first-hand accounts

What counts as done

That user's recent events, flag evaluations or membership returned by exact id or email, with no truncation.

Measured, for our own tests: in one or two calls. No docs we read state these figures, so they don't count against a listing here.

How agents ask for it: what did this customer do before churning, which flags does this customer have on, is this user in the beta segment, show this user's sessions

Does the job 7

The docs show it meets the test above, and nothing we read says otherwise.

ListingWhy
Amplitude BB
Amplitude, Inc.
/api/2/usersearch finds a user by user id or Amplitude id, then /api/2/useractivity returns up to 1,000 events with offset paging; get_amp_user_data covers it over MCP. source
Fullstory B
Fullstory, Inc.
List Sessions returns a user's most recent sessions by uid or email, /api/v1/export/userEvents returns one user's events, and review-open accepts an email or user uid. source
Matomo B
InnoCraft Limited
Live.getLastVisitsDetails with a segment such as userId or visitorId returns one visitor's visits and events in one call. source
OpenPanel B
OpenPanel AB
find_profiles searches by email or name, and get_profile returns a profile with its most recent events; get_profile_sessions orders sessions newest first. source
Pendo E
Pendo.io, Inc.
visitorActivity returns one visitor's chronological product activity with console and network logs, and listVisitors and visitorMetadataSchema read metadata. source
PostHog B
PostHog Inc. (formerly Hiberly Inc.)
persons-retrieve and persons-cohorts-retrieve read one person and their cohorts, and feature-flags-evaluation-reasons-retrieve shows how every flag evaluates for a distinct_id and why. source
Woopra D
Woopra, Inc.
/profile/actions looks up one profile by a unique key such as email, pid or id and returns its visits and action timeline in one call. source

Does the job, with a limit 7

It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.

ListingWhy
Countly E
Countly Ltd
user_profiles_query searches by free text with totals and paging, and user_profiles_get reads one profile, but the users plugin is Enterprise only and exact-email lookup isn't stated. source
Flagsmith B
Bullet Train Ltd
GET /api/v1/identities/ returns one identity's flags and traits by identifier, but it is the SDK API with an environment key, not an MCP tool, and there are no events. source
Harness Feature Management & Experimentation BB
Harness Inc.
Segment keys can be listed with fme_segment_definition list_keys, but there is no tool to evaluate flags for a given key, and identity writes aren't wired in native mode. source
LaunchDarkly BB
Catamorphic, Co. (dba LaunchDarkly)
POST flags/evaluate returns a context's flag values over REST, but the MCP lacks it (open issue 93), and get-segment truncated targets at ten with no exact lookup (open issue 97). source
Mixpanel B
Mixpanel, Inc.
Profile Event Activity returns events for given distinct_ids over inclusive dates, but it is in maintenance mode at 60 queries an hour, and Engage returned 403 for a service account with no email lookup (acc-21). source
Statsig BB
Amplitude, Inc.
Check Feature Gate(s) evaluates gates for a given user object, but results depend on the attributes the caller supplies, and no endpoint returns one user's event history. source
Userpilot B
Userpilot, Inc.
With the profile permission the MCP reads one user's or company's profile and activity, but tool names, lookup keys and truncation aren't documented. source

Doesn't do this job 5

Listings in the category that do something else, with the reason.

ListingWhy
GrowthBook BB
GrowthBook, Inc.
No endpoint returns one user's events or flag evaluations; user data stays in the warehouse and flags evaluate in the SDK. source
Heap D
Content Square, Inc.
Identify and Add User Properties write user data; no endpoint reads one user's events or profile back. source
Mostly Good Metrics E
Mostly Good Metrics
No per-user events or profile tool; query tools are aggregate-only. source
Optimizely Experimentation B
Optimizely North America Inc.
No endpoint or tool looks up one visitor's events or flag decisions. source
RudderStack MCP C
RudderStack, Inc.
Profile tools return profile project models, statistics and history, not one user's events by id or email. source

What stops agents finishing

  • profile API forbidden for the service account role
  • segment targets truncated with no exact lookup
  • no flag evaluation for a given context

Around it

Before: support.read-ticket. After: support.reply-ticket.

Where this comes from

Weight 6 of 100 in Product analytics & experimentation: 3 of 55 account links; Mixpanel, Fullstory and Pendo list user investigation among MCP uses

The same as data: /api/v1/use-cases/product-analytics.user-lookup.json, or the MCP tool get_use_case with id product-analytics.user-lookup. Other jobs in this category: /api/v1/niches?category=product-analytics.

Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person. A mark says what the docs show, not what a run measured.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.