Bluebarry

@bluebarry list the last 50 shopper identities that haven't been merged into another record, so I can see our active user base.

Bluebarry returned 50 identity records with mergedIntoId set to null. Each entry includes an identity ID, creation timestamp, and associated profile count. For example, identity `ident_a1b2c3` was created on 2024-01-15 and links to 3 profiles. The response includes a next_cursor token you can use to fetch the next page if you need more than 50 records. This snapshot represents distinct shoppers who have not been consolidated into other identities.

This example uses the List Identities tool with a mergedIntoId filter to surface only surviving shopper records. Bluebarry requires an API key with read access to identity data. If your account has thousands of identities, you'll need to paginate using the offset or cursor pattern—this example shows a single page of 50.

@bluebarry show me the raw profile rows for shopper identity ident_x9y8z7, including session-level details, so I can debug why this user appears twice in our analytics.

Bluebarry returned 2 profile records linked to identity ident_x9y8z7. Profile 1 was created on 2024-02-10 from session sess_abc123 with user-agent Mozilla/5.0 (iPhone). Profile 2 was created on 2024-02-12 from session sess_def456 with user-agent Chrome/120. Both profiles share the same email but originated from different devices. This explains the duplicate appearance—Bluebarry tracks each session separately before merging them into a single shopper identity.

This example uses the List Profiles tool to drill into per-session data for a single identity. It's useful when you need to understand how a shopper's activity was captured across multiple visits or devices. Be aware that profile data can be verbose if a shopper has many sessions—filter by identity ID to keep the response manageable.

@bluebarry pull all profiles created in the last 7 days and summarize the top 3 traffic sources by profile count, so I can see where our new shoppers are coming from.

Bluebarry returned 342 profiles created between 2024-03-01 and 2024-03-08. Analyzing the referrer and UTM fields, the top 3 traffic sources are: (1) Google Ads—118 profiles, (2) Organic search—97 profiles, (3) Instagram—64 profiles. The remaining 63 profiles came from direct traffic or other sources. This breakdown shows paid search is currently your largest acquisition channel, followed closely by organic discovery. You may want to investigate the Instagram cohort's conversion rate separately.

This example combines Bluebarry's List Profiles tool with AI reasoning to aggregate and rank traffic sources. The MCP returns raw profile rows; the AI parses referrer metadata and counts occurrences. Bluebarry does not natively compute these summaries, so the analysis depends on the AI's ability to process the returned data. Large date ranges may hit API rate limits or return thousands of profiles—narrow the window if performance becomes an issue.

When Bluebarry helps support teams trace suspicious orders

A 6-person customer support team at a Shopify store sees a spike in chargebacks from accounts that look legitimate at first glance. Bluebarry's identity merge gives them a way to pull all profiles tied to a single shopper—across sessions, devices, and email variants—so they can spot patterns like multiple failed payment attempts or address mismatches before approving high-value orders. The two-tool setup (list identities, list profiles) is narrow enough that non-technical support leads can run queries without waiting on engineering. This works when your fraud volume is under 50 cases a week; beyond that, you need a dedicated fraud platform with real-time scoring, not a manual lookup MCP. If you're triaging chargebacks in Slack and want to pull shopper history without opening your analytics dashboard, Bluebarry closes that gap.

Why this MCP falls short for campaign performance analysis

A 3-person growth team wants to understand which acquisition channels drive repeat purchases, so they consider using Bluebarry to merge anonymous sessions into known buyer profiles. The problem: Bluebarry only exposes identity and profile listing—it doesn't surface campaign UTMs, referral sources, or conversion events. You can see that shopper ID 12345 has three profiles, but you can't tie those profiles back to the Facebook ad or email campaign that brought them in. For attribution work, you need an MCP that integrates with your analytics warehouse (like Snowflake or BigQuery) or your marketing stack (like Segment). Bluebarry is built for identity resolution, not funnel analysis. If your question is 'who is this person across sessions,' it works; if your question is 'which campaign converted them,' look elsewhere.

When Bluebarry helps CS teams spot at-risk accounts early

A 4-person customer success team at a B2B SaaS company uses Bluebarry to track how many distinct users from a single organization are logging in each month. By listing profiles filtered to a customer's domain, they can see if engagement is concentrated in one person (a churn risk) or spreading across the team (a healthy sign). The API key auth and two-tool scope make this safe to run from a shared Switchy workspace without exposing sensitive customer data beyond identity records. This works for accounts with 5 to 500 users; smaller accounts don't generate enough profile volume to matter, and enterprise accounts need a proper product analytics tool with cohort tracking. If you're doing quarterly business reviews and want a quick pulse on account activity without building a dashboard, Bluebarry gives you that in two queries.