> **Building with AI coding agents?** Install the authstack plugin with one command. This equips your agent with accurate Scalekit implementation patterns. > > **Recommended** (the `-y` flags skip prompts, so the command runs without an interactive terminal): > ```bash > npx -y @scalekit-inc/cli setup -y > ``` > > Global: > ```bash > npm install -g @scalekit-inc/cli > scalekit setup -y > ``` > > Supports Claude Code, Cursor, GitHub Copilot, Codex + skills for other Agent Skills-compatible agents in `~/.agents/skills`. > Skills: integrate-agentkit, implement-saaskit, add-mcp-oauth, implement-sso, implement-scim. > [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/) --- # Connect AI agents to the Profound MCP server The Profound MCP connector routes your AI agent's tool calls to Profound's own MCP server through Scalekit. Each user signs in to Profound once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 15 tools. **Authentication:** OAuth 2.1/DCR **Categories:** Marketing, Analytics, AI **Tools:** 15: 15 read, 0 write, 0 destructive **Users sign in with:** OAuth **OAuth app:** Scalekit's or your own **Built by:** Vendor MCP **Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=PROFOUNDMCP) ## Setup 1. ### Install the SDK **Node.js** ```bash npm install @scalekit-sdk/node dotenv ``` **Python** ```bash pip install scalekit-sdk-python python-dotenv ``` 2. ### Set your credentials Add your Scalekit credentials to your `.env` file. Find values in **[app.scalekit.com](https://app.scalekit.com)** > **Developers** > **API Credentials**. ```sh title=".env" SCALEKIT_ENVIRONMENT_URL= SCALEKIT_CLIENT_ID= SCALEKIT_CLIENT_SECRET= ``` 3. ### Create the Profound MCP connection In **AgentKit > Connections**, create a Profound MCP connection. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/). Scalekit credentials are available for Profound MCP server, so you don't need to register an OAuth app. 4. ### Authorize a user and make your first call **Node.js** (`quickstart.mts`) ```typescript import { ScalekitClient } from '@scalekit-sdk/node' import 'dotenv/config' import { createInterface } from 'node:readline/promises' const scalekit = new ScalekitClient( process.env.SCALEKIT_ENVIRONMENT_URL, process.env.SCALEKIT_CLIENT_ID, process.env.SCALEKIT_CLIENT_SECRET, ) const actions = scalekit.actions const connector = 'profoundmcp' const identifier = 'user_123' // Generate an authorization link for the user const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier }) console.log('Authorize Profound MCP:', link) const rl = createInterface({ input: process.stdin, output: process.stdout }) await rl.question('Press Enter after authorizing...') rl.close() // Make your first call const result = await actions.executeTool({ connector, identifier, toolName: 'profoundmcp_list_models', toolInput: { rationale: 'YOUR_RATIONALE' }, }) console.log(result) ``` ```bash npx tsx quickstart.mts ``` **Python** (`quickstart.py`) ```python import os from scalekit import ScalekitClient from dotenv import load_dotenv load_dotenv() scalekit_client = ScalekitClient( env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"), client_id=os.getenv("SCALEKIT_CLIENT_ID"), client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"), ) actions = scalekit_client.actions connection_name = "profoundmcp" identifier = "user_123" # Generate an authorization link for the user link_response = actions.get_authorization_link( connection_name=connection_name, identifier=identifier, ) print("Authorize Profound MCP:", link_response.link) input("Press Enter after authorizing...") # Make your first call result = actions.execute_tool( tool_input={"rationale":"YOUR_RATIONALE"}, tool_name="profoundmcp_list_models", connection_name=connection_name, identifier=identifier, ) print(result) ``` ```bash python quickstart.py ``` Each user signs in once. See [Authorize a user](/agentkit/tools/authorize/) for the full flow and statuses. ## Tools Pass the exact name to `execute_tool`, with an input like each tool's example. To ask for a tool that's missing, use the [request form](https://scalekitsupport.portal.usepylon.com/forms/request-a-connector-tool). **Node.js** ```typescript const result = await actions.executeTool({ toolName: 'profoundmcp_get_bots_report', toolInput: { domain: '', end_date: '', rationale: '', start_date: '', }, connector: 'profoundmcp', identifier: 'user_123', }) ``` **Python** ```python result = actions.execute_tool( tool_name="profoundmcp_get_bots_report", tool_input={ "domain": "", "end_date": "", "rationale": "", "start_date": "", }, connection_name="profoundmcp", identifier="user_123", ) ``` `result.data` is the app's response as JSON, and `result.execution_id` (`executionId` in Node.js) is the ID of the call. ### `profoundmcp_get_bots_report` Get Bots Report · Read-only Measure AI crawler activity against a domain over a date range, including bots such as GPTBot and PerplexityBot. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `domain` (`string`, required): Tracked domain using exact hostname from list_domains - `end_date` (`string`, required): Window end in YYYY-MM-DD format (exclusive) - `rationale` (`string`, required): Always provide a brief explanation of why you are calling this tool - `start_date` (`string`, required): Window start in YYYY-MM-DD format (inclusive) - `bot_name_filter` (`array`, optional): Narrow to specific bots - `bot_provider_filter` (`array`, optional): Narrow to specific bot providers - `bot_type_filter` (`array`, optional): Narrow to bot categories - `cursor` (`string`, optional): Pagination token - `dimensions` (`array`, optional): Group-by fields - `filters` (`array`, optional): Advanced predicates - `limit` (`integer`, optional): Top-N row cap - `metrics` (`array`, optional): Metrics to return - `organization_id` (`string`, optional): Disambiguate domain across organizations - `page_size` (`integer`, optional): First-page size, up to 10,000 Example input: `{"domain":"","end_date":"","rationale":"","start_date":""}` ### `profoundmcp_get_citations_report` Get Citations Report · Read-only See which sources AI engines cite for a category, and how often, over a date range. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `category_id` (`string`, required): Category to report on - `end_date` (`string`, required): Window end in YYYY-MM-DD format (exclusive) - `rationale` (`string`, required): Always provide a brief explanation of why you are calling this tool - `start_date` (`string`, required): Window start in YYYY-MM-DD format (inclusive) - `citation_category_filter` (`array`, optional): Narrow to specific citation categories - `cursor` (`string`, optional): Pagination token - `dimensions` (`array`, optional): Group-by fields - `filters` (`array`, optional): Advanced predicates - `hostname_filter` (`array`, optional): Narrow to specific hostnames - `limit` (`integer`, optional): Top-N row cap - `metrics` (`array`, optional): Metrics to return - `model_filter` (`array`, optional): Narrow to specific AI models - `page_size` (`integer`, optional): First-page size, up to 10,000 - `persona_filter` (`array`, optional): Narrow to specific personas - `region_filter` (`array`, optional): Narrow to specific regions - `root_domain_filter` (`array`, optional): Narrow to specific root domains - `tag_filter` (`array`, optional): Narrow to specific tags - `topic_filter` (`array`, optional): Narrow to specific topics Example input: `{"category_id":"","end_date":"","rationale":"","start_date":""}` ### `profoundmcp_get_prompt_answers` Get Prompt Answers · Read-only Retrieve the actual answers AI engines gave for a category's prompts over a date range. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `category_id` (`string`, required): Category to retrieve answers for - `end_date` (`string`, required): Window end in YYYY-MM-DD format (exclusive) - `rationale` (`string`, required): Always provide a brief explanation of why you are calling this tool - `start_date` (`string`, required): Window start in YYYY-MM-DD format (inclusive) - `limit` (`integer`, optional): Rows per page - `offset` (`integer`, optional): Row offset for pagination Example input: `{"category_id":"","end_date":"","rationale":"","start_date":""}` ### `profoundmcp_get_referrals_report` Get Referrals Report · Read-only Measure visits a domain received from AI engines, such as ChatGPT and Perplexity, over a date range. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `domain` (`string`, required): Tracked domain using exact hostname from list_domains - `end_date` (`string`, required): Window end in YYYY-MM-DD format (exclusive) - `rationale` (`string`, required): Always provide a brief explanation of why you are calling this tool - `start_date` (`string`, required): Window start in YYYY-MM-DD format (inclusive) - `cursor` (`string`, optional): Pagination token - `dimensions` (`array`, optional): Group-by fields - `filters` (`array`, optional): Advanced predicates - `limit` (`integer`, optional): Top-N row cap - `metrics` (`array`, optional): Metrics to return - `organization_id` (`string`, optional): Disambiguate domain across organizations - `page_size` (`integer`, optional): First-page size, up to 10,000 - `referral_source_filter` (`array`, optional): Narrow to specific referrer vendors - `referral_type_filter` (`array`, optional): Narrow to referral categories Example input: `{"domain":"","end_date":"","rationale":"","start_date":""}` ### `profoundmcp_get_sentiment_report` Get Sentiment Report · Read-only Measure sentiment in AI answers for a category over a date range. Default metrics: positive, negative, and occurrences. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `category_id` (`string`, required): Category to report on - `end_date` (`string`, required): Window end in YYYY-MM-DD format (exclusive) - `rationale` (`string`, required): Always provide a brief explanation of why you are calling this tool - `start_date` (`string`, required): Window start in YYYY-MM-DD format (inclusive) - `asset_filter` (`array`, optional): Narrow to brand/competitor assets - `cursor` (`string`, optional): Pagination token - `filters` (`array`, optional): Advanced predicates - `limit` (`integer`, optional): Top-N row cap - `metrics` (`array`, optional): Metrics to return - `model_filter` (`array`, optional): Narrow to specific AI models - `page_size` (`integer`, optional): First-page size, up to 10,000 - `persona_filter` (`array`, optional): Narrow to specific personas - `region_filter` (`array`, optional): Narrow to specific regions - `tag_filter` (`array`, optional): Narrow to specific tags - `theme_filter` (`array`, optional): Narrow to specific sentiment themes - `topic_filter` (`array`, optional): Narrow to specific topics Example input: `{"category_id":"","end_date":"","rationale":"","start_date":""}` ### `profoundmcp_get_visibility_report` Get Visibility Report · Read-only Measure how often and how prominently a brand appears in AI answers for a category over a date range. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `category_id` (`string`, required): Category to report on - `end_date` (`string`, required): Window end in YYYY-MM-DD format (exclusive) - `rationale` (`string`, required): Always provide a brief explanation of why you are calling this tool - `start_date` (`string`, required): Window start in YYYY-MM-DD format (inclusive) - `asset_filter` (`array`, optional): Narrow to brand/competitor assets - `cursor` (`string`, optional): Pagination token - `dimensions` (`array`, optional): Group-by fields - `filters` (`array`, optional): Advanced predicates with field, operator, value - `limit` (`integer`, optional): Top-N row cap - `metrics` (`array`, optional): Metrics to return - `model_filter` (`array`, optional): Narrow to specific AI models - `page_size` (`integer`, optional): First-page size, up to 10,000 - `persona_filter` (`array`, optional): Narrow to specific personas - `region_filter` (`array`, optional): Narrow to specific regions - `tag_filter` (`array`, optional): Narrow to specific tags - `topic_filter` (`array`, optional): Narrow to specific topics Example input: `{"category_id":"","end_date":"","rationale":"","start_date":""}` ### `profoundmcp_list_categories` List Categories · Read-only List tracked categories, markets, or segments in an organization. Most brand visibility reports are scoped to a category. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `org_id` (`string`, required): Organization whose categories to list - `rationale` (`string`, required): Always provide a brief explanation of why you are calling this tool Example input: `{"org_id":"","rationale":""}` ### `profoundmcp_list_domains` List Domains · Read-only List tracked domains for an organization. Domains are exact hostnames, so www.example.com and example.com are distinct. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `org_id` (`string`, required): Organization whose tracked domains to list - `rationale` (`string`, required): Always provide a brief explanation of why you are calling this tool Example input: `{"org_id":"","rationale":""}` ### `profoundmcp_list_models` List Models · Read-only List the AI models Profound tracks. Use returned model IDs to filter reports to a single engine. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `rationale` (`string`, required): Always provide a brief explanation of why you are calling this tool Example input: `{"rationale":""}` ### `profoundmcp_list_organizations` List Organizations · Read-only List the organizations the authenticated user can access. Returned IDs feed category, domain, and report tools. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `rationale` (`string`, required): Always provide a brief explanation of why you are calling this tool Example input: `{"rationale":""}` ### `profoundmcp_list_prompts` List Prompts · Read-only List prompts configured in a category. Prompts are the questions Profound runs against AI engines to measure brand visibility. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `category_id` (`string`, required): Category to list prompts for - `rationale` (`string`, required): Always provide a brief explanation of why you are calling this tool - `combine` (`string`, optional): How include filters combine. One of: `AND`, `OR`. - `cursor` (`string`, optional): Pagination token from previous response - `exclude_tag_ids` (`array`, optional): Exclude prompts carrying these tags - `exclude_topic_ids` (`array`, optional): Exclude prompts under these topics - `limit` (`integer`, optional): Maximum prompts to return - `status` (`string`, optional): Filter by prompt status. One of: `active`, `disabled`, `all`. - `tag_ids` (`array`, optional): Include only prompts carrying these tags - `topic_ids` (`array`, optional): Include only prompts under these topics Example input: `{"category_id":"","rationale":""}` ### `profoundmcp_list_regions` List Regions · Read-only List geographic regions configured for an organization. Omit org_id to see regions across all accessible organizations. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `rationale` (`string`, required): Always provide a brief explanation of why you are calling this tool - `org_id` (`string`, optional): Organization identifier Example input: `{"rationale":""}` ### `profoundmcp_list_tags` List Tags · Read-only List tags available within a category for filtering prompts and reports. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `category_id` (`string`, required): Category whose tags to list - `rationale` (`string`, required): Always provide a brief explanation of why you are calling this tool Example input: `{"category_id":"","rationale":""}` ### `profoundmcp_list_topics` List Topics · Read-only List topics available within a category for filtering prompts and reports. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `category_id` (`string`, required): Category to list topics for - `rationale` (`string`, required): Always provide a brief explanation of why you are calling this tool Example input: `{"category_id":"","rationale":""}` ### `profoundmcp_whoami` Whoami · Read-only Confirm the authenticated user, organizations, regions, and entitlements available to this MCP session. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `rationale` (`string`, required): Always provide a brief explanation of why you are calling this tool Example input: `{"rationale":""}` ## Related Other Marketing connectors ([all 59](/agentkit/connectors/?category=marketing)): - [HubSpot](/agentkit/connectors/hubspot/): Scalekit connector, OAuth, 457 tools - [Mailchimp](/agentkit/connectors/mailchimp/): Scalekit connector, OAuth, 73 tools - [Twitter / X](/agentkit/connectors/twitteroauth/): Scalekit connector, OAuth, 92 tools --- ## More Scalekit documentation | Resource | What it contains | When to use it | |----------|-----------------|----------------| | [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content | | [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas | | [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |