Space Monkey Mailchimp Dashboard

Resolve which Space Monkey projects this API key can read. Call this first when the user names a company rather than a project ID, and match on companyName — never silently mix projects.

無需輸入參數。

Introspect the API key's own account — effective tier, per-service entitlements, current hour/month quota usage and project count. Use it to check headroom or diagnose a 403/429 before retrying.

無需輸入參數。

Rank the most engaged members of a project by engagement percentile. Use when you need who is paying attention right now, filtered by rep, tag, rating, status or bot/insider rules. engagementScore is a 0-100 percentile here (at-risk tools use a raw score that can go negative), memberRating is Mailchimp's 1-5 rating, and subscriberHash is the MD5 of the member's downcased email, the join key for member-centric tools. Results are paginated with pageSize capped at 100 rows.

Find previously engaged members whose recent activity has collapsed, for building save lists. Note its engagementScore is a raw decayed score that can be negative, unlike the leaders percentile.

Browse or search a project's full member directory. Use when you need people by rating, tag, status or free-text search rather than by engagement rank.

Load one member's full profile — title, company, tags, clicked URLs, engagement percentile, at-risk state and bot detection. Use for pre-call briefs and to enrich a shortlist.

List the individual campaigns one member received, opened or clicked. This email-level drill-down is often empty even for highly engaged members, so always keep a fallback. For the inverse view — the members who responded to one campaign — use sm_list_campaign_responders.

Replay one member's raw activity events in time order. Use to establish when someone last paid attention and what triggered it.

List a project's campaigns with performance metrics. Use to map a member's lastActivityAt onto a real send, or to find the latest house send by send_time.

Load one campaign's full report — delivery, open, click, click-to-open and bounce rates plus campaign metadata. Use after you have identified a campaign of interest. Returns a fixed-size set of campaign-level aggregates in one call regardless of audience size; per-variant, funnel and geography breakdowns are on sm_get_variate, not here.

Analyse a variate (A/B) campaign — per-variant reports, statistical significance, engagement velocity, audience quality and geo split. Only meaningful for multivariate campaigns. All metrics come from synced BigQuery tables rather than a live Mailchimp read, so they are only as current as the project's last sync run, whose cadence is per-project: manual, daily or weekly.

Produce a full post-mortem of one sent campaign: summary metadata, delivery and performance rates, engagement velocity (time-to-first-open and hourly engagement), audience quality, and per-variant breakdown when the campaign is an A/B test. Combines the detail, velocity, audience-quality and variate views into one report. All metrics come from synced BigQuery tables, so they are only as current as the project last sync run.

List the members who registered a tracked response to one campaign — opened, clicked, bounced or unsubscribed — never the full send list; emailsSent is echoed so the unenumerated majority stays visible as a denominator. Narrow with action (clicked-only is usually a fraction of responders), engagementType, variant, rating or score filters; subscriberHash is the MD5 of the downcased email and joins to member-centric tools. For the campaign's own report use sm_get_campaign, for member-to-campaign history use sm_get_member_campaigns (the inverse view), and for the whole directory use sm_list_members. Results are paginated with an opaque keyset cursor valid for 24 hours and pageSize capped at 100 rows.

Get headline campaign and audience performance for a project: per-campaign performance table, single-campaign detail, list overview, engagement and send-volume trends, subscriber-growth series, and period-over-period averages. Start here for "how are we doing". Excludes engagement distribution, tag and segment summaries, growth baseline/churn decomposition and campaign consistency — use sm_get_insights_advanced for those. Excludes campaign fatigue, subject-line keywords, send-time heatmap, monthly trend and audience health — use sm_get_insights_expert. For the member-composition view (status, rating, rep and language counts) use sm_get_member_overview, and for signup cohorts, churn and retention use sm_get_member_growth; the list overview and subscriber-growth series here are Mailchimp-list and audience-trend views, not member-level lifecycle. All three insight tiers also return campaign averages, previous-period averages, audience summary and auto-generated insights.

Get deeper audience analytics for a project: engagement distribution, tag and segment summaries, subscriber-growth baseline with churn decomposition, and campaign consistency. Use when basic insights cannot explain a change. Excludes the per-campaign performance table, single-campaign detail, list overview and the engagement and send-volume trends — use sm_get_insights_basic for those. Excludes campaign fatigue, subject-line keywords, send-time heatmap, monthly trend and audience health — use sm_get_insights_expert. All three insight tiers also return campaign averages, previous-period averages, audience summary and auto-generated insights.

Get expert diagnostics explaining why performance is moving: campaign fatigue, subject-line keywords, timezone-aware send-time heatmap, monthly trend and audience health, plus engagement distribution and campaign consistency (also available from sm_get_insights_advanced). Use only after basic or advanced have established what changed. Excludes the per-campaign performance table, single-campaign detail, list overview and the engagement and send-volume trends — use sm_get_insights_basic. Excludes tag and segment summaries and the subscriber-growth series and baselines — use sm_get_insights_advanced. All three insight tiers also return campaign averages, previous-period averages, audience summary and auto-generated insights.

Get aggregate audience composition for a project — totals plus status, rating, rep and language breakdowns. Use for a quick shape-of-the-list answer. Not paginated: totals and the status and rating breakdowns cover every member, but the language list is truncated to the top 20 and the rep and custom-dimension lists to the top 25, and the rep block is absent unless the project maps an owner merge field. For Mailchimp-list health — per-audience sizes, unsubscribe and cleaned counts, open and click rates — use the list overview in sm_get_insights_basic; this tool is the member-composition view (status, rating, rep, language) instead.

Get signup cohorts, churn timeline and cohort retention. Use for list-growth and attrition questions. A cohortRetention row is the current status breakdown of members who signed up in that month, not retention at month N after signup; signup month falls back to last-changed or sync time when Mailchimp has no opt-in timestamp. For the audience size trend over time — subscriber counts bucketed by status month over month — use the subscriber-growth series in sm_get_insights_basic; this returns signup cohorts, churn and retention rather than a status trend.

Get tags and segments with their engagement and status breakdowns. Use to turn an event or interest tag into a working audience. Every tag and segment is returned in one unpaginated call, but untagged members are excluded from the tag list and surface only as a separate untaggedCount, and tag engagement rates exclude insiders while tag member counts do not.

Get the country and region distribution of a project's members. Use for territory, event and travel-planning questions. Country is inferred from the member's region where possible (US states and Canadian provinces map to US and CA) before falling back to stored country data, with unresolvable values bucketed as Unknown; regions stays null unless countryCode is passed.

List recent data-pipeline sync runs with status and results. Operational tool for checking data freshness before trusting an analysis. Results are paginated with pageSize capped at 100 rows.

Load one sync run's full detail — per-stage results, progress, lookback window and pending batch count. Use after sm_list_sync_runs to explain why data is stale or a run failed. Failure detail lands in one of two places and rarely both: orchestration failures set run.errorMessage with no stage rows, while per-data-type failures leave it null and record the message on results[].errorMessage, so check both and treat status as the failure signal.

Returns Space Monkey's MCP knowledge documents (analyst preamble, metric guardrails, live OpenAPI schema URL) as tool output for clients that cannot read MCP resources — read this before interpreting any Space Monkey metrics.

Get the Enterprise API's OpenAPI-derived schema catalog. Omitting `operation` returns a compact index of every Enterprise API operation; passing a tool name, full path, or path suffix returns that one operation's full parameters and resolved response schemas. Use before calling an unfamiliar tool to confirm its exact fields.

List the Space Monkey prompt workflows: user-invocable recipes that chain sm_ tools into this week's sales actions (build call sheets, strike after a send, save cooling leaders, harvest an event, brief before a call). Each entry lists its arguments and its category. Use sm_get_prompt to render one with concrete argument values, then follow the rendered instructions to run the workflow.

無需輸入參數。

Render one Space Monkey prompt workflow with concrete argument values, returning the complete instruction text ready to follow, plus the effective arguments that were bound (provided values plus defaults for omitted optionals). Prompt names and their arguments come from sm_list_prompts. If the rendered text still contains {{tokens}} such as {{projectId}} or {{company}}, a required argument was not provided; call again with it filled. The rendered text references sm_ tools by name; call them as instructed.