Skip to main content
Scorecards drive how Attention’s AI evaluates calls. A scorecard defines a set of weighted scoring items (criteria), an optional set of label-based filters (when does this scorecard apply?), and a numeric range (e.g. 1–5). The MCP server exposes a complete CRUD surface — list and inspect scorecards, create new ones, manage individual items, reorder them, and set the global range.

​
Read tools

​
get_scorecards

Scope: mcp:read. No parameters.
List all scorecards used to evaluate calls in your organization, including their criteria and which teams they apply to. Returns: Markdown list of scorecards with title, ID, status, and team assignments.

​
get_scorecard_details

Scope: mcp:read.
Get detailed information about a specific scorecard — criteria, weights, team assignments, scoring scale, and evaluation instructions. Use the scorecard ID from get_scorecards.
​
scorecard_id
string
required
The UUID of the scorecard to retrieve.
Returns: A full Markdown rendering of the scorecard: title, status, mode (standard / expert), prompt, instructions, interaction type, criteria filters, team assignments, and every item with its weight, scale, and criteria descriptions.

​
Scorecard write tools

​
create_scorecard

Scope: mcp:write. Requires admin role.
Create a new scorecard. After creating, add scoring items with create_scorecard_item.
​
title
string
required
The scorecard title.
​
all_teams
boolean
Apply to all teams. If false, use team_ids.
​
team_ids
array
Team IDs this scorecard applies to. Required when all_teams is false.
​
interaction_type
string
Interaction type: conversation (default), chat, or email.
​
criteria
object
Label-based filter that determines which calls this scorecard applies to:
  • operator: AND (all must match) or OR (any must match).
  • conditions: array of { "field": "Call Type", "value": "Discovery" }.
Use list_labels to see available label categories and options.
​
scorecard_prompt
string
AI prompt used to evaluate calls against this scorecard.
​
detailed_instructions
string
Formatting instructions for how the AI should structure its evaluation feedback.
​
expert_mode
boolean
Enable expert mode for per-item custom prompts.

​
update_scorecard

Scope: mcp:write. Requires admin role.
Update an existing scorecard’s settings, criteria filters, or AI prompt. Use get_scorecard_details to see current values. Item-level changes (add/edit/delete/reorder) live in their own tools below.
​
scorecard_id
string
required
The UUID of the scorecard to update.
​
title
string
New title.
​
enabled
boolean
Enable or disable the scorecard.
​
all_teams
boolean
Apply to all teams.
​
team_ids
array
Team IDs this scorecard applies to.
​
interaction_type
string
Interaction type: conversation, chat, or email.
​
criteria
object
Label-based filter conditions. Replaces all existing criteria.
​
scorecard_prompt
string
AI prompt used to evaluate calls.
​
detailed_instructions
string
Evaluation instructions.
​
expert_mode
boolean
Enable expert mode.

​
Scorecard item tools

Scorecard items are the individual scoring criteria within a scorecard.

​
create_scorecard_item

Scope: mcp:write. Requires admin role.
Add a scoring criterion to a scorecard. Each item defines what the AI evaluates on a numeric scale (e.g. 1–5).
​
scorecard_id
string
required
The UUID of the scorecard.
​
title
string
required
The scoring criterion title (e.g. Effective Questioning, Need Discovery).
​
weight
integer
Relative weight of this item in the overall score. Default: 1.
​
min
integer
Minimum score value. Default: 1. Must match the scale of existing items in this scorecard.
​
middle
integer
Middle score value for 3-point anchor scales (e.g. 3 on a 1–5 scale). Must be strictly between min and max.
​
max
integer
Maximum score value. Default: 5.
​
min_criteria
string
Description of what the minimum score means. Required unless the scorecard is in expert mode.
​
middle_criteria
string
Description of what the middle score means.
​
max_criteria
string
Description of what the maximum score means. Required unless the scorecard is in expert mode.
​
expert_prompt
string
Custom AI prompt for this item. Only used when the scorecard’s expert_mode is enabled.

​
update_scorecard_item

Scope: mcp:write. Requires admin role.
Update a scoring criterion. Use get_scorecard_details to find item IDs.
​
item_id
string
required
The UUID of the scorecard item.
​
title
string
New title.
​
weight
integer
New weight.
​
min
integer
New minimum score value.
​
middle
integer
New middle score value.
​
max
integer
New maximum score value.
​
min_criteria
string
New description for the minimum score.
​
middle_criteria
string
New description for the middle score.
​
max_criteria
string
New description for the maximum score.
​
expert_prompt
string
New custom AI prompt for this item.

​
delete_scorecard_item

Scope: mcp:write. Requires admin role. Destructive.
Remove a scoring criterion from a scorecard.
​
item_id
string
required
The UUID of the scorecard item to delete.

​
update_scorecard_item_order

Scope: mcp:write. Requires admin role.
Move a scorecard item to a new position within its scorecard. Items are reordered to accommodate the change.
​
item_id
string
required
UUID of the scorecard item to move.
​
position
integer
required
New position (0-based index).

​
update_scorecard_ranges

Scope: mcp:write. Requires admin role.
Set the score ranges (min, middle, max) for all items in a scorecard at once. Useful when migrating an existing scorecard from one scale to another.
​
scorecard_id
string
required
UUID of the scorecard.
​
min
integer
Minimum score value.
​
middle
integer
Middle score value for 3-point anchor scales.
​
max
integer
Maximum score value.