Content Intelligence MCP Tools

Content Intelligence tools help agents evaluate a page against market context and return recommendations.

Use one-off tools for immediate answers. Use persisted runs when the result should be saved and pollable.

Tools

Tool	Purpose	Scope
discover_sleepwalker_content_trends	Find relevant content trends for a URL.	content_intelligence:trends:discover
score_sleepwalker_content	Score a URL without saving a run.	content_intelligence:content:score
create_sleepwalker_content_run	Queue a persisted Content Intelligence run.	content_intelligence:runs:create
list_sleepwalker_content_runs	List direct Content Intelligence runs.	runs:read
get_sleepwalker_content_run_status	Poll one Content Intelligence run.	runs:read

discover_sleepwalker_content_trends

Use this when the user wants market context only.

Inputs:

Input	Type	Required	Notes
url	string	Yes	Page URL.
extraction_mode	string	No	Optional extraction profile. Omit unless instructed otherwise.
language	string	No	Defaults to en; use et for Estonian.
country	string	No	Defaults to US; use EE for Estonia.

Output includes compact industry, trend, and citation data.

Credits: 1 when completed successfully.

score_sleepwalker_content

Use this when the user wants a score, gaps, and recommendations without saving a run.

Inputs:

Input	Type	Required	Notes
url	string	Yes	Page URL.
extraction_mode	string	No	Optional extraction profile. Omit unless instructed otherwise.
industry	string	No	Optional industry label.
trends	object[]	No	Optional trend set from trend discovery.
language	string	No	Defaults to en; use et for Estonian.
country	string	No	Defaults to US; use EE for Estonia.

If the agent already called discover_sleepwalker_content_trends, it should pass the returned compact trends into score_sleepwalker_content.

Credits:

Mode	Credits
With supplied trends	2
Without supplied trends	3

create_sleepwalker_content_run

Use this when the result should be persisted and retrievable later.

Inputs:

Input	Type	Required	Notes
url	string	Conditional	New direct-URL run. Send exactly one of url or test_id.
test_id	string	Conditional	Rerun an existing saved Content Intelligence test.
analysis_depth	string	No	score or full. Defaults to full.
language	string	No	Direct-URL run output language. Defaults to en; use et for Estonian.
country	string	No	Direct-URL run market. Defaults to US; use EE for Estonia.
idempotency_key	string	No	Retry-safe key.

Use url when the user wants to analyze a new page.

Use test_id only when the user explicitly asks to rerun an existing saved Content Intelligence test. Saved-test reruns use the language and country stored on that test; direct-URL runs use the language and country supplied to this tool.

The create response includes a next_action field when the run is queued or running. Agents should follow that exact tool and arguments instead of creating a duplicate run. Direct URL runs normally poll get_sleepwalker_content_run_status; saved-test reruns may poll get_sleepwalker_run_result because they reuse the Console result path.

Depth

Depth	Use when	Credits
score	The user needs scoring and recommendations.	3
full	The user needs the complete Content Intelligence run output.	6

Polling

Use:

get_sleepwalker_content_run_status

for direct URL runs. For saved-test reruns, follow the next_action returned by create_sleepwalker_content_run; it can point to get_sleepwalker_run_result.

Inputs:

Input	Type	Required	Notes
run_id	string	Yes	Run returned by create.
include_result	boolean	No	Defaults to false.

Poll every 10 to 30 seconds.

When a compact status response is complete, next_action points back to get_sleepwalker_content_run_status with include_result: true so the client can fetch the full Content Intelligence output only when needed.

Example Prompts

Score https://www.example.com and show the top recommendations.

Discover trends for this page first, then score the page against those trends.

Create a full Content Intelligence run for this URL and poll until the result is ready.