Knowledge BaseKnowledge Base

Setting Up The Wazzi Scorecard Connector

Read the compiled scorecard and manage metric definitions, targets, sections, and dimensions from your AI assistant — the write surface behind Scorecard Center. First-party, org-scoped, and requires no credentials.

August 12, 2026
8 min read

Path: Connectors → Wazzi Scorecard → Configuration

What this connector does

Wazzi Scorecard is a first-party MCP connector that exposes your organization's Scorecard Center — dimensions (tabs), metrics, targets, sections, and manual weekly overrides — as MCP tools. It's the same surface the in-app scorecard UI drives, made available to AI assistants so your team can read the compiled scorecard, configure metrics, adjust targets, and log manual values from chat.

Because Wazzi Scorecard is first-party, there's nothing to configure and no external credentials to enter. Every request is org-scoped server-side, and the connector talks directly to your organization's centers.sc_* tables — no third-party API in the loop.

The connector exposes 20 tools grouped by domain:

  • Reads — the compiled scorecard (4 tools) — list_dimensions, list_metrics, get_scorecard (rows + sections + issue links, in one round-trip), get_status (last ETL run + latest week).
  • Reads — catalog + config (4 tools) — list_metric_catalog, list_targets, list_sections, list_team_members (BambooHR-synced employees so you can assign metric owners).
  • Metric library (3 tools) — create_metric (from catalog or custom), update_metric, delete_metric.
  • Targets & values (2 tools) — set_target (with the "Clear" path and range-op support), set_values (manual weekly overrides with current-week lock semantics).
  • Layout — dimensions & sections (6 tools) — create_dimension, update_dimension, delete_dimension (Portfolio protected), create_section, replace_sections (bulk drag/drop path), attach_metric_to_dimension.
  • Issue tracking (1 tool) — report_cell_issue to flag/unflag a single cell independent of the automated threshold logic.

Before you start

For this connector to have anything to read or write, your organization must have Scorecard Center enabled with at least one dimension configured. If the scorecard has never been set up for your org, the first thing to do is create the Portfolio dimension (created automatically for new orgs) and install a couple of metrics from the platform catalog — everything below then has data to operate on.

Beyond that, there's no per-user setup — just enable the connector on the user's group in Wazzi.

What this connector unlocks for your team

Once configured, members with the right MCP permissions can ask Claude / ChatGPT / Cursor things like:

  • "Show me the current scorecard for the Phoenix market — which cells are red?"
  • "What's our latest scorecard status — when did the ETL last complete, and is the current week fully computed?"
  • "Install the ADR, RevPAR, and occupancy metrics from the catalog and attach them to the Portfolio tab."
  • "Set a target of >=$275 ADR on the Portfolio dimension and give it the note 'Q1 2026 goal from board deck.'"
  • "Clear the target on the retention_30d metric for the Sedona dimension — we're deprecating that goal."
  • "Manually set this week's booked_nights to 412 on Phoenix — the ETL missed a source and we've verified the true value."
  • "Flag this cell as an issue — the value is on target but there's a known operational problem behind the number."
  • "Create a new dimension called 'Corporate Housing' scoped to our LTR source keys and attach the LTR metric set to it."
  • "Rename the 'Growth' section in the Portfolio tab to 'Growth & Acquisition' and move it above 'Retention'."
  • "Assign Sarah Chen (bamboo id 4712) as the owner of the guest_nps metric."

The exact set of available actions depends on which MCP toggles are flipped on for the user's group in Wazzi — see Managing Permissions. Write tools (create / update / delete / set) can be restricted independently from reads, so an analyst group can query while an ops-lead group can also mutate.

Steps — enabling Wazzi Scorecard in Wazzi

1. From the Connectors catalog, click Configure on the Wazzi Scorecard tile.

You'll land on Wazzi Scorecard's Configuration tab:

Wazzi Scorecard connector Configuration tab

2. Read the notice — there are no credentials to enter.

The configuration tab shows an information notice reminding you that Scorecard Center must be enabled and at least one dimension configured for the tools to have data to operate on.

3. Click Test Connection.

Wazzi runs a quick count query against your scorecard tables. On success you'll see:

  • "Connected. 24 metrics, 5 dimensions configured." — your scorecard is set up and ready.
  • "Connected. No scorecard configured yet — define your first dimension and metric under Scorecard Center to get started." — the connector is wired up but you haven't built the scorecard yet.

4. Click Save Configuration.

Wazzi Scorecard moves to the Active section of the catalog and the dot turns green.

Troubleshooting

  • list_dimensions returns only 'portfolio' or nothing. Your organization hasn't set up any custom dimensions yet. Create one via create_dimension (or under Scorecard Center in the UI) — the Portfolio dimension is created automatically for every org and can't be deleted.
  • get_scorecard returns rows with all-null values. The ETL hasn't run yet or has been failing. Call get_status — if last_run is stale or errored, hit the Refresh button in the Scorecard tab (this is intentionally kept UI-only). Manual overrides via set_values continue to work regardless.
  • set_values returns "Past-week writes are locked". Only the current (Monday-aligned) week is writable by default. Set force: true to override a past week — the same "Unlock" action the UI exposes.
  • set_target fails with "target_value_high is required". Range operators (in_range, not_in_range) need both bounds; target_value_high must be >= target_value.
  • delete_dimension refuses to delete 'portfolio'. That's by design — every org needs a Portfolio dimension. Delete a custom dimension instead, or rename Portfolio via update_dimension.
  • create_metric with an id returns 409 conflict. A metric with that id already exists for the org. Either pick a different id or call update_metric to patch the existing one. Custom-metric ids must be lowercase snake_case ([a-z0-9_]+).
  • Values I set manually get overwritten by the next ETL. They shouldn't — every cell written by set_values is stamped is_manual=TRUE, and the ETL skips manual rows. If overwrites are happening, contact Wazzi support with the metric_id / dimension_id / week_start so we can inspect the sync path.

Best practices

  • Install from the catalog when possible. Catalog metrics come with the ETL source pre-wired, so values populate automatically. Reserve custom metrics for things the platform doesn't have a source for.
  • Use get_status before consuming get_scorecard. If the latest ETL run failed or the newest week isn't your current week, the scorecard is stale — call it out before making decisions off it.
  • Set targets at the dimension level that matters. A target on the Portfolio dimension applies to the roll-up view; per-market targets on custom dimensions let you set different goals per segment. Don't over-target — every unmet target adds noise.
  • Use attach_metric_to_dimension with section_order. Grouping metrics into sections (Growth / Retention / Ops / etc.) massively improves scorecard readability. Create the section first with create_section, then attach metrics to that section_order.
  • Restrict destructive tools. delete_metric, delete_dimension, and replace_sections are broad-reach operations. Only grant those permissions to analytics leads — see Managing Permissions.
  • Use report_cell_issue to preserve context. When the number itself is on-target but there's an operational problem behind it (a data-source outage, a one-time boost from a promotion), flagging the cell keeps the story visible to the next reviewer.

Frequently asked questions

Do I need to configure anything?
No. This is a first-party connector with no external credentials. Just enable it on the user's group in Wazzi.

Can users from another organization see or edit my scorecard?
No. Every tool call filters by organization_id — dimensions, metrics, targets, and weekly values are all org-scoped. Cross-org access is impossible.

Where does the automated data come from?
Automated metrics have a source field pointing at a specific ETL (Streamline, BambooHR, GoHighLevel, KeyData, etc.). Their weekly values are computed by the platform ETL and refreshed on a schedule. Manual metrics have no source; their values are only written via set_values or the UI editor.

Why can I only write to the current week by default?
Locking past weeks prevents accidental history rewrites — the scorecard's whole value is showing trend over time, and unrestricted past-week writes erode trust in the numbers. Set force: true on set_values when you truly need to fix a past week; the UI's "Unlock" action drives the same path.

What's the difference between a section and a dimension?
A dimension is a top-level tab in the scorecard — Portfolio, Phoenix Market, Sedona Market, Corporate Housing, etc. Each dimension has its own set of metrics, targets, and weekly values. A section is a visual divider inside a dimension — Growth / Retention / Ops — that groups related metrics together. Metrics belong to (dimension × section) pairs.

Can I trigger a scorecard refresh from this connector?
Not directly. The refresh flow requires an internal API secret and HTTP loopback, so it stays UI-only — use the Refresh button in the Scorecard tab. Once we have a cleaner service-layer entry point for it, we'll add a refresh_scorecard tool.

What's next

Was this article helpful?