Productive

Create one or more records of a given resource type. Use describe_resource with include: ["fields"] first to learn required and optional fields. Provide a single-item array to create one record, or multiple items for bulk creation. Use productive_domain to discover all available resource types.

Delete one or more records of a given resource type. Provide a single-item array to delete one record, or multiple items for bulk deletion.

Describe the available fields, groups, filters, and custom fields for a report type. Inline tags on each field convey extra capability: "(formulable)" — usable in formula expressions "(sortable)" — usable as a sort_by value (prefix "-" for descending) "(sortable: <key>)" — sortable but only via the named key (the API sort key differs from the field key) "(list)" on a filter row — that filter accepts a list of values; rows without it accept a single scalar value A date-period group key carries a required bucket suffix, shown inline as "<key>:{day|week|month|quarter|year}" — pick exactly one bucket (e.g. "date:month") for both group_by and sort_by; the bare key is not a valid group/sort value. Call this before query_report to understand what configuration is available. By default, includable relationships are listed compactly (name and type only). To see available attributes for include_fields, pass include_fields_for with relationship keys to expand.

Describe a resource type in the Productive domain — its purpose, available operations, and pointers to every detail area. Call this to learn how a resource works before querying, creating, or updating records. Without options, returns a compact overview that includes a short hint for each detail area that exists (fields, relationship filters, custom fields, actions). Pass include to expand any of those areas: "fields" for the full field schema (types, flags, filter operators, sort, search), "relationship_filters" for the dot-notation filter list, "custom_field_schemas" for org-specific custom field metadata, "action_schemas" for full action input schemas. Use productive_domain to discover all available resource types.

Load the current user's identity (name, email, role) and their organization (currency, timezone, services offered). Call this early to resolve "me"/"I"/"my" — who you're talking to and what kind of organization they work in.

Load a single resource by ID. Returns primary attributes only by default. Use include_fields to request relationship attributes (e.g. "assignee.first_name", "project.name"). Large responses are replaced by a slim handle stub: `items` is a single `{type, id}` pointer (not the full record). The stub envelope carries `output_type: "json"` so query_output knows to route through jq. Call query_output(output_id, jq_expression=<jq>) against the handle to read fields. The store envelope is `{items: [{id, type, fields, url?}], included?}`; `fields` is keyed by the field's `param` from describe_resource (e.g. `.items[0].fields.title`). Relationship values under `fields` are `{type, id}` objects (NOT JSON:API `.relationships.<name>.data`). See query_output for the supported jq subset.

Load full instructions and available actions for one or more skills by id. Skills are specialized domain workflows (e.g. automation-builder), domain guides (e.g. task-creation), or user-authored skills defined by the organization. Call this with every skill id whose description matches what the user needs — up to 5 per call. The response includes each skill's instructions and any actions you can call via perform_action. Prefer one batched call over multiple single-id calls when several skills are relevant.

Execute a registered action by its globally-unique slug (e.g. "send_email", "archive_email_thread", "validate_automation"). describe_resource lists each resource's available actions and their signatures in its default overview; pass include: ["action_schemas"] for full input schemas.

Productive domain reference — all resource types, tool usage patterns, and search strategies. Start here if you are unfamiliar with this server.

Query a report endpoint to fetch aggregated data. Returns raw report data grouped, filtered, and sorted as specified. Always call describe_report first to understand available fields, groups, filters, and sorts. Slicing uses `limit` (default 30, max 200) and `offset` (default 0; must be a multiple of `limit`). Two call shapes (mutually exclusive): - Fresh query: `{report_type, name, group_by?, filters?, formulas?, sort_by?, currency_variant?, include_fields?, display_fields?, report_layout?, chart_type?, limit?, offset?}` — issues a new query and returns a `query_id` you can use to continue it. - Continuation: `{query_id, offset, limit?}` — the full report config (`report_type`, `name`, `group_by`, `filters`, `formulas`, `sort_by`, `currency_variant`, `include_fields`, `display_fields`, `report_layout`, `chart_type`) is pinned from the original call. `offset` is required — pass the `next_offset` from the previous response.