Skip to main content

Profound

How often do AI answers mention your brand? Profound tracks it prompt by prompt.

Tools

61 available tools

Search the tool definitions captured from the MCP server. The live list can vary with version, deployment, and credentials.

61 tools found.

  • Add knowledge base document

    Tool name: add_knowledge_base_document

    Add ONE new document (inline markdown text) to a knowledge base.

  • Archive project

    Tool name: archive_project

    Preview or archive (retire) a project — set it aside without deleting it.

  • Create agent definition

    Tool name: create_agent_definition

    Create a draft agent definition — preview first, then apply on confirmation.

  • Create doc

    Tool name: create_doc

    Create a new document in the Profound platform from content you have written.

  • Create project task

    Tool name: create_project_task

    Preview or add a task ("play") to a project.

  • Create prompts

    Tool name: create_prompts

    Create one or more prompts in a category.

  • Get agent

    Tool name: get_agent

    Get details of an agent, including its input_schema.

  • Get agent definition

    Tool name: get_agent_definition

    Read back an agent's full workflow graph so you can copy and edit it.

  • Get agent node schema

    Tool name: get_agent_node_schema

    Get the configuration schema for one node type.

  • Get agent run

    Tool name: get_agent_run

    Get the status (and outputs if terminal) of a previously triggered run.

  • Get bots report

    Tool name: get_bots_report

    Bot-traffic report for a domain over a date window.

  • Get citations report

    Tool name: get_citations_report

    Citations report for a category over a date window.

  • Get citations report v1

    Tool name: get_citations_report_v1

    Citations report for a category over a date window.

  • Get doc

    Tool name: get_doc

    Read one Profound document.

  • Get factcheck claims

    Tool name: get_factcheck_claims

    FactCheck inaccurate-claims report for one category.

  • Get factcheck report

    Tool name: get_factcheck_report

    FactCheck score report for one category.

  • Get project

    Tool name: get_project

    Get one project: its goal, why it matters, and its full task list.

  • Get project status

    Tool name: get_project_status

    Get one project's lifecycle and live-generation status.

  • Get prompt answers

    Tool name: get_prompt_answers

    Observed AI-engine responses for prompts in a category over a window.

  • Get prompt volume

    Tool name: get_prompt_volume

    Projected demand for ONE keyword — how often people prompt about it.

  • Get prompt volume intents

    Tool name: get_prompt_volume_intents

    Intent mix for ONE keyword — WHY people ask about it.

  • Get referrals report

    Tool name: get_referrals_report

    Referral-traffic report for a domain over a date window.

  • Get sentiment report

    Tool name: get_sentiment_report

    Sentiment report for one brand/asset, from AI responses or cited pages.

  • Get shopping brands report

    Tool name: get_shopping_brands_report

    Brand visibility inside AI shopping results for a category.

  • Get shopping merchants report

    Tool name: get_shopping_merchants_report

    Which retailers AI engines surface for a category's shopping results.

  • Get shopping products report

    Tool name: get_shopping_products_report

    Individual product visibility inside AI shopping results for a category.

  • Get shopping trigger rate report

    Tool name: get_shopping_trigger_rate_report

    How often prompts make an AI engine return a shopping surface at all.

  • Get visibility report

    Tool name: get_visibility_report

    Visibility report for a category over a date window.

  • Get visibility report v1

    Tool name: get_visibility_report_v1

    Visibility report for a category over a date window.

  • List agent definition templates

    Tool name: list_agent_definition_templates

    Browse proven starting points before building an agent from scratch.

  • List agent node types

    Tool name: list_agent_node_types

    List the node types you may use to build an agent graph.

  • List agents

    Tool name: list_agents

    List agents defined for the authenticated organization.

  • List categories

    Tool name: list_categories

    Tracked categories for an org (e.g. "Banking — Canada").

  • List docs

    Tool name: list_docs

    List documents in the Profound workspace (metadata only, no content).

  • List domains

    Tool name: list_domains

    Domains tracked for an org.

  • List integrations

    Tool name: list_integrations

    List the integrations your org has connected, to fill a node's integration_id.

  • List knowledge bases

    Tool name: list_knowledge_bases

    Knowledge bases accessible to the caller (resolver for search).

  • List models

    Tool name: list_models

    AI engines (ChatGPT, Gemini, Perplexity, etc.) the caller has visibility into.

  • List organizations

    Tool name: list_organizations

    List organizations available to the authenticated principal.

  • List projects

    Tool name: list_projects

    List a category's projects as thin triage rows (in backend order).

  • List prompts

    Tool name: list_prompts

    Prompts configured in a category, optionally filtered by status/tags/topics.

  • List regions

    Tool name: list_regions

    Regions (US, UK, CA, etc.) available to the caller.

  • List resources

    Tool name: list_resources

    List all available resources and resource templates.

  • List tags

    Tool name: list_tags

    Tags defined in a category.

  • List topics

    Tool name: list_topics

    Topics defined in a category.

  • New project

    Tool name: new_project

    Preview or kick off a fire-and-forget project generation run in a category.

  • Publish agent definition

    Tool name: publish_agent_definition

    Publish a draft agent definition so the agent goes live — preview first, then apply.

  • Read resource

    Tool name: read_resource

    Read a resource by its URI.

  • Replace doc content

    Tool name: replace_doc_content

    Replace a Profound document's ENTIRE content with new text.

  • Run agent

    Tool name: run_agent

    Start an agent run.

  • Search knowledge base

    Tool name: search_knowledge_base

    Semantic / full-text search inside a single knowledge base.

  • Set project task status

    Tool name: set_project_task_status

    Preview or transition a task's status.

  • Share feedback

    Tool name: share_feedback

    Report that Profound's MCP tools could not fully satisfy the user's request.

  • Start agent build session

    Tool name: start_agent_build_session

    Open a build session — the FIRST step of building or revising an agent.

  • Update agent definition

    Tool name: update_agent_definition

    Update a draft agent definition's graph — preview first, then apply on confirmation.

  • Update doc

    Tool name: update_doc

    Rename a Profound document, change who can see it, or both in one call.

  • Update project task

    Tool name: update_project_task

    Preview or update fields on an existing task (send only what changes).

  • Update prompts

    Tool name: update_prompts

    Update one or more existing prompts.

  • Update prompts status

    Tool name: update_prompts_status

    Bulk activate, disable, or DELETE prompts.

  • Validate agent definition

    Tool name: validate_agent_definition

    Check whether a saved draft agent definition is well-formed and publishable.

  • Whoami

    Tool name: whoami

    Return information about the authenticated principal — user ID, granted scopes, and the Profound entitlements visible to this session.

Compatibility

Connect Profound to the clients your teams already use

27 AI clients can connect to Profound through Runlayer. Pick one for its setup steps and controls.

Why Runlayer

Why connect Profound through Runlayer?

One approved path

Approve Profound once and everyone gets it in the AI clients they already use. Runlayer holds the credentials, so nothing sits in client configuration.

Fine-grained policy

Control who can use each server, tool, and resource, and under which runtime conditions.

Runtime security

Scan tool inputs and outputs for prompt injection, credential exposure, PII, and data exfiltration, then alert, mask, or block.

Audit and observability

Trace every request across users, clients, tools, policies, scanner decisions, and downstream systems.

Frequently asked questions