Capabilities - Profound

Profound MCP gives AI assistants read-only access to Profound’s Answer Engine Optimization (AEO), brand visibility, citation, sentiment, and agent analytics data. Use this page to understand what the hosted MCP server can do before connecting it to an MCP client. To set up the server, see Connecting to Profound MCP.

https://mcp.tryprofound.com/mcp

Profound MCP uses OAuth 2.1. Each tool runs as the authenticated Profound user and returns only the data that user can access.

How the tools work together

Most workflows start with discovery, then move into reports. Here’s what that typically looks like:

Confirm access

Use whoami to confirm the signed-in user, available organizations, regions, and entitlements.

Find the right scope

Use list_organizations, then list_categories for visibility reports or list_domains for traffic reports.

Add optional filters

Use list_regions, list_models, list_tags, list_topics, and list_prompts to narrow a report to the relevant market, AI engine, prompt set, topic, or tag.

Run a report

Use the visibility, sentiment, citations, prompt answers, referrals, or bot crawl tools to retrieve analytics for a date range.

Behavior and safety

All tools are read-only. They retrieve analytics and reference data, but don’t create, update, or delete anything in Profound.

Behavior	What it means
Non-destructive	No tool performs destructive updates
Live data	Tools read from the Profound API, so results reflect the caller’s current access and data

The following MCP hints are set on all report tools:

Hint	Value	What it means
`readOnlyHint`	`true`	The tool only reads data
`idempotentHint`	`true`	The tool is safe to retry with the same arguments

Dates are ISO 8601 strings in YYYY-MM-DD format. Reports validate start_date and end_date and return an actionable error if the date window is invalid.

Discovery tools

Use discovery tools to resolve human-readable context into IDs that report tools can use.

Tool	Use it for
`whoami`	Confirm the authenticated principal, organizations, regions, and entitlements
`list_organizations`	List organizations the user can access
`list_regions`	List geographic regions, optionally scoped to an organization
`list_models`	List tracked AI models such as ChatGPT, Perplexity, Google AI Overviews, and Gemini
`list_categories`	List tracked categories for an organization
`list_domains`	List tracked domains for an organization
`list_tags`	List tags in a category
`list_topics`	List topics in a category
`list_prompts`	List configured prompts in a category, with optional status, tag, and topic filters

whoami

Confirm the authenticated user, organizations, regions, and entitlements available to this MCP session.Inputs: none.

list_organizations

List the organizations the authenticated user can access. Returned IDs feed category, domain, and report tools.Inputs: none.

list_regions

List geographic regions configured for an organization. Omit org_id to see regions across all accessible organizations.

Input	Required	Default	Description
`org_id`	No	`null`	Organization to scope to

Example:

{
  "org_id": "org_123"
}

list_models

List the AI models Profound tracks. Use returned model IDs to filter reports to a single engine.Inputs: none.

list_categories

List tracked categories, markets, or segments in an organization. Most brand visibility reports are scoped to a category.

Input	Required	Default	Description
`org_id`	Yes	-	Organization whose categories to list

Example:

{
  "org_id": "org_123"
}

list_domains

List tracked domains for an organization. Domains are exact hostnames, so www.example.com and example.com are distinct.

Input	Required	Default	Description
`org_id`	Yes	-	Organization whose tracked domains to list

Example:

{
  "org_id": "org_123"
}

list_tags

Input	Required	Default	Description
`category_id`	Yes	-	Category whose tags to list

list_topics

List topics available within a category for filtering prompts and reports.

Input	Required	Default	Description
`category_id`	Yes	-	Category to list topics for

Example:

{
  "category_id": "cat_123"
}

list_prompts

List prompts configured in a category. Prompts are the questions Profound runs against AI engines to measure brand visibility.

Input	Required	Default	Description
`category_id`	Yes	-	Category to list prompts for
`status`	No	`all`	One of `active`, `disabled`, or `all`
`tag_ids`	No	`null`	Include only prompts carrying these tags
`topic_ids`	No	`null`	Include only prompts under these topics
`exclude_tag_ids`	No	`null`	Exclude prompts carrying these tags
`exclude_topic_ids`	No	`null`	Exclude prompts under these topics
`combine`	No	`AND`	How include filters combine: `AND` or `OR`
`limit`	No	`100`	Maximum prompts to return
`cursor`	No	`null`	Pagination token from a previous response’s `next_cursor`

Example:

{
  "category_id": "cat_123",
  "status": "active"
}

Brand visibility reports

These tools are scoped to a category_id and a date range. Use them to understand how brands appear in AI answers, how those answers feel, and which sources AI engines cite.

Tool	Description
`get_visibility_report`	How visible a brand is in AI answers and how that varies by model, topic, region, prompt, tag, or persona
`get_sentiment_report`	What sentiment AI answers express about a brand or competitor and which themes are positive or negative
`get_citations_report`	Which domains, pages, or URLs are AI engines citing for this category
`get_prompt_answers`	What raw AI answers were observed behind the metrics

get_visibility_report

Measure how often and how prominently a brand appears in AI answers for a category over a date range.Default metric: visibility_score.Other useful metrics include share_of_voice, mentions_count, executions, and average_position. Useful dimensions include date, region, topic, model, prompt, tag, and persona.

Input	Required	Default	Description
`category_id`	Yes	-	Category to report on
`start_date`	Yes	-	Window start (inclusive) in `YYYY-MM-DD` format
`end_date`	Yes	-	Window end (inclusive) in `YYYY-MM-DD` format
`metrics`	No	`visibility_score`	Metrics to return
`dimensions`	No	`null`	Group-by fields
`filters`	No	`null`	Advanced `{ "field", "operator", "value" }` predicates
`limit`	No	`null`	Top-N row cap. When set, `next_cursor` is always `null`
`topic_filter`	No	`null`	Narrow to one or more topics
`tag_filter`	No	`null`	Narrow to one or more tags
`region_filter`	No	`null`	Narrow to one or more regions
`model_filter`	No	`null`	Narrow to one or more AI models
`persona_filter`	No	`null`	Narrow to one or more personas
`asset_filter`	No	`null`	Narrow to one or more brand or competitor assets
`cursor`	No	`null`	Pagination token from a previous response
`page_size`	No	`500`	First-page size, up to 10,000

Example:

{
  "category_id": "cat_123",
  "start_date": "2026-04-01",
  "end_date": "2026-05-01",
  "dimensions": ["model"]
}

get_sentiment_report

Measure sentiment in AI answers for a category over a date range.Default metrics: positive, negative, and occurrences. positive and negative are weighted aggregates; occurrences is a raw count.

Input	Required	Default	Description
`category_id`	Yes	-	Category to report on
`start_date`	Yes	-	Window start (inclusive) in `YYYY-MM-DD` format
`end_date`	Yes	-	Window end (inclusive) in `YYYY-MM-DD` format
`metrics`	No	`positive`, `negative`, `occurrences`	Metrics to return
`filters`	No	`null`	Advanced `{ "field", "operator", "value" }` predicates
`limit`	No	`null`	Top-N row cap. When set, `next_cursor` is always `null`
`topic_filter`	No	`null`	Narrow to one or more topics
`tag_filter`	No	`null`	Narrow to one or more tags
`region_filter`	No	`null`	Narrow to one or more regions
`model_filter`	No	`null`	Narrow to one or more AI models
`persona_filter`	No	`null`	Narrow to one or more personas
`asset_filter`	No	`null`	Narrow to one or more brand or competitor assets
`theme_filter`	No	`null`	Narrow to one or more sentiment themes, such as pricing
`cursor`	No	`null`	Pagination token from a previous response
`page_size`	No	`500`	First-page size, up to 10,000

Example:

{
  "category_id": "cat_123",
  "start_date": "2026-04-01",
  "end_date": "2026-05-01",
  "theme_filter": "pricing"
}

get_citations_report

See which sources AI engines cite for a category, and how often, over a date range.Default metrics: count and citation_share. Useful dimensions include hostname, path, root_domain, url, model, topic, prompt, tag, and persona.

root_domain_filter must be paired with dimensions: ["root_domain"].

Input	Required	Default	Description
`category_id`	Yes	-	Category to report on
`start_date`	Yes	-	Window start (inclusive) in `YYYY-MM-DD` format
`end_date`	Yes	-	Window end (inclusive) in `YYYY-MM-DD` format
`metrics`	No	`count`, `citation_share`	Metrics to return
`dimensions`	No	`null`	Group-by fields
`filters`	No	`null`	Advanced `{ "field", "operator", "value" }` predicates
`limit`	No	`null`	Top-N row cap. When set, `next_cursor` is always `null`
`topic_filter`	No	`null`	Narrow to one or more topics
`tag_filter`	No	`null`	Narrow to one or more tags
`region_filter`	No	`null`	Narrow to one or more regions
`model_filter`	No	`null`	Narrow to one or more AI models
`persona_filter`	No	`null`	Narrow to one or more personas
`root_domain_filter`	No	`null`	Narrow to one or more root domains. Requires `root_domain` in `dimensions`
`hostname_filter`	No	`null`	Narrow to one or more hostnames
`citation_category_filter`	No	`null`	Narrow to one or more citation categories
`cursor`	No	`null`	Pagination token from a previous response
`page_size`	No	`500`	First-page size, up to 10,000

Example:

{
  "category_id": "cat_123",
  "start_date": "2026-04-01",
  "end_date": "2026-05-01",
  "dimensions": ["root_domain"]
}

get_prompt_answers

Retrieve the actual answers AI engines gave for a category’s prompts over a date range.

Input	Required	Default	Description
`category_id`	Yes	-	Category to retrieve prompt answers for
`start_date`	Yes	-	Window start (inclusive) in `YYYY-MM-DD` format
`end_date`	Yes	-	Window end (inclusive) in `YYYY-MM-DD` format
`limit`	No	`100`	Rows per page
`offset`	No	`0`	Row offset for pagination

Example:

{
  "category_id": "cat_123",
  "start_date": "2026-04-01",
  "end_date": "2026-05-01"
}

Traffic reports

These tools are scoped to a tracked domain, not a category. Use list_domains first and pass the exact hostname returned by Profound.

Tool	Description
`get_referrals_report`	How many visits did a domain receive from AI engines, and which referrers drove them
`get_bots_report`	Which AI crawlers are visiting a domain, and how often

get_referrals_report

Measure visits a domain received from AI engines, such as ChatGPT and Perplexity, over a date range.Default metric: visits. Useful dimensions include referral_type, referral_source, and date.

Input	Required	Default	Description
`domain`	Yes	-	Tracked domain, using the exact hostname from `list_domains`
`start_date`	Yes	-	Window start (inclusive) in `YYYY-MM-DD` format
`end_date`	Yes	-	Window end (inclusive) in `YYYY-MM-DD` format
`metrics`	No	`visits`	Metrics to return
`dimensions`	No	`null`	Group-by fields, such as `referral_type`, `referral_source`, or `date`
`organization_id`	No	`null`	Disambiguates the domain when the caller belongs to multiple organizations
`filters`	No	`null`	Advanced `{ "field", "operator", "value" }` predicates
`limit`	No	`null`	Top-N row cap. When set, makes `next_cursor` always `null`
`referral_source_filter`	No	`null`	Narrow to one or more referrer vendors, such as `openai`
`referral_type_filter`	No	`null`	Narrow to one or more referral categories: `internal`, `referer`, `utm`, or `none`
`cursor`	No	`null`	Pagination token from a previous response
`page_size`	No	`500`	First-page size, up to 10,000

Example:

{
  "domain": "example.com",
  "start_date": "2026-04-01",
  "end_date": "2026-05-01",
  "dimensions": ["referral_source"]
}

get_bots_report

Measure AI crawler activity against a domain over a date range, including bots such as GPTBot and PerplexityBot.Default metrics: count and citations. Useful dimensions include bot_provider, bot_name, bot_type, and date.

Input	Required	Default	Description
`domain`	Yes	-	Tracked domain, using the exact hostname from `list_domains`
`start_date`	Yes	-	Window start (inclusive) in `YYYY-MM-DD` format
`end_date`	Yes	-	Window end (inclusive) in `YYYY-MM-DD` format
`metrics`	No	`count`, `citations`	Metrics to return
`dimensions`	No	`null`	Group-by fields, such as `bot_provider`, `bot_name`, `bot_type`, or `date`
`organization_id`	No	`null`	Disambiguates the domain when the caller belongs to multiple organizations
`filters`	No	`null`	Advanced `{ "field", "operator", "value" }` predicates
`limit`	No	`null`	Top-N row cap. When set, makes `next_cursor` always `null`
`bot_provider_filter`	No	`null`	Narrow to one or more providers, such as `openai` or `anthropic`
`bot_name_filter`	No	`null`	Narrow to one or more individual bots, such as `GPTBot`
`bot_type_filter`	No	`null`	Narrow to one or more bot categories: `ai_assistant`, `ai_training`, `index`, or `ai_agent`
`cursor`	No	`null`	Pagination token from a previous response
`page_size`	No	`500`	First-page size, up to 10,000

Example:

{
  "domain": "example.com",
  "start_date": "2026-04-01",
  "end_date": "2026-05-01",
  "dimensions": ["bot_provider"]
}

Resources

Profound MCP also exposes read-only MCP resources: static reference material that an MCP client can load into context.

Resource URI	Audience	Use it for
`file:///profound/glossary`	Assistant	Compact index of Profound-specific terms to load once per session
`file:///profound/glossary/full`	User	Full glossary with definitions and examples, larger than the index
`file:///profound/glossary/{term}`	Assistant	Full definition of one glossary term, addressed by slug

Glossary lookup flow

The glossary defines recurring Profound terms such as visibility score, share of voice, citations, prompts, and AI engines.A client typically loads file:///profound/glossary once, then fetches a specific term with file:///profound/glossary/{term} when it needs a precise definition. For example, use file:///profound/glossary/visibility-score for the visibility score definition.

Glossary structure

The glossary includes 38 terms across seven categories: Identity, Taxonomy, AI Engines, Prompts, Reports, Metrics, and Agents.Each term has a stable lowercase hyphenated slug, short summary, full description, examples, and see-also references to related terms.

​How the tools work together

​Behavior and safety

​Discovery tools

​Brand visibility reports

​Traffic reports

​Resources

How the tools work together

Behavior and safety

Discovery tools

Brand visibility reports

Traffic reports

Resources