Connect AI agents to the Profound MCP server

Vendor MCP

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.

Tools: 15
What they doRead · write · destructive: 15 · 0 · 015 read0 write0 destructive
Users sign in with: OAuth
OAuth app: Scalekit's or your own

Setup

Install the SDK
- Node.js
- Python
Terminal window
npm install @scalekit-sdk/node dotenv
Terminal window
pip install scalekit-sdk-python python-dotenv
Set your credentials
Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.
.env
```
SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
SCALEKIT_CLIENT_ID=<your-client-id>
SCALEKIT_CLIENT_SECRET=<your-client-secret>
```
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.
Scalekit credentials are available for Profound MCP server, so you don't need to register an OAuth app.

Authorize a user and make your first call

Node.js
Python

1
import { ScalekitClient } from '@scalekit-sdk/node'
2
import 'dotenv/config'
3
import { createInterface } from 'node:readline/promises'
4

5
const scalekit = new ScalekitClient(
6
  process.env.SCALEKIT_ENVIRONMENT_URL,
7
  process.env.SCALEKIT_CLIENT_ID,
8
  process.env.SCALEKIT_CLIENT_SECRET,
9
)
10
const actions = scalekit.actions
11

12
const connector = 'profoundmcp'
13
const identifier = 'user_123'
14

15
// Generate an authorization link for the user
16
const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
17
console.log('Authorize Profound MCP:', link)
18
const rl = createInterface({ input: process.stdin, output: process.stdout })
19
await rl.question('Press Enter after authorizing...')
20
rl.close()
21

22
// Make your first call
23
const result = await actions.executeTool({
24
  connector,
25
  identifier,
26
  toolName: 'profoundmcp_list_models',
27
  toolInput: { rationale: 'YOUR_RATIONALE' },
28
})
29
console.log(result)

npx tsx quickstart.mts

1
import os
2
from scalekit import ScalekitClient
3
from dotenv import load_dotenv
4
load_dotenv()
5

6
scalekit_client = ScalekitClient(
7
    env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),
8
    client_id=os.getenv("SCALEKIT_CLIENT_ID"),
9
    client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
10
)
11
actions = scalekit_client.actions
12

13
connection_name = "profoundmcp"
14
identifier = "user_123"
15

16
# Generate an authorization link for the user
17
link_response = actions.get_authorization_link(
18
    connection_name=connection_name,
19
    identifier=identifier,
20
)
21
print("Authorize Profound MCP:", link_response.link)
22
input("Press Enter after authorizing...")
23

24
# Make your first call
25
result = actions.execute_tool(
26
    tool_input={"rationale":"YOUR_RATIONALE"},
27
    tool_name="profoundmcp_list_models",
28
    connection_name=connection_name,
29
    identifier=identifier,
30
)
31
print(result)

python quickstart.py

Each user signs in once. See Authorize a user for the full flow and statuses.

Tools

Pass the exact name to execute_tool

Try in Playground Request a tool

profoundmcp_get_bots_reportMeasure AI crawler activity against a domain over a date range, including bots such as GPTBot and PerplexityBot.Read-only
Get Bots Report
Measure AI crawler activity against a domain over a date range, including bots such as GPTBot and PerplexityBot.
Inputs
domainstringrequired
Tracked domain using exact hostname from list_domains
end_datestringrequired
Window end in YYYY-MM-DD format (exclusive)
rationalestringrequired
Always provide a brief explanation of why you are calling this tool
start_datestringrequired
Window start in YYYY-MM-DD format (inclusive)
bot_name_filterarray
Narrow to specific bots
bot_provider_filterarray
Narrow to specific bot providers
bot_type_filterarray
Narrow to bot categories
cursorstring
Pagination token
dimensionsarray
Group-by fields
filtersarray
Advanced predicates
limitinteger
Top-N row cap
metricsarray
Metrics to return
organization_idstring
Disambiguate domain across organizations
page_sizeinteger
First-page size, up to 10,000
profoundmcp_get_citations_reportSee which sources AI engines cite for a category, and how often, over a date range.Read-only
Get Citations Report
See which sources AI engines cite for a category, and how often, over a date range.
Inputs
category_idstringrequired
Category to report on
end_datestringrequired
Window end in YYYY-MM-DD format (exclusive)
rationalestringrequired
Always provide a brief explanation of why you are calling this tool
start_datestringrequired
Window start in YYYY-MM-DD format (inclusive)
citation_category_filterarray
Narrow to specific citation categories
cursorstring
Pagination token
dimensionsarray
Group-by fields
filtersarray
Advanced predicates
hostname_filterarray
Narrow to specific hostnames
limitinteger
Top-N row cap
metricsarray
Metrics to return
model_filterarray
Narrow to specific AI models
page_sizeinteger
First-page size, up to 10,000
persona_filterarray
Narrow to specific personas
region_filterarray
Narrow to specific regions
root_domain_filterarray
Narrow to specific root domains
tag_filterarray
Narrow to specific tags
topic_filterarray
Narrow to specific topics
profoundmcp_get_prompt_answersRetrieve the actual answers AI engines gave for a category's prompts over a date range.Read-only
Get Prompt Answers
Retrieve the actual answers AI engines gave for a category's prompts over a date range.
Inputs
category_idstringrequired
Category to retrieve answers for
end_datestringrequired
Window end in YYYY-MM-DD format (exclusive)
rationalestringrequired
Always provide a brief explanation of why you are calling this tool
start_datestringrequired
Window start in YYYY-MM-DD format (inclusive)
limitinteger
Rows per page
offsetinteger
Row offset for pagination
profoundmcp_get_referrals_reportMeasure visits a domain received from AI engines, such as ChatGPT and Perplexity, over a date range.Read-only
Get Referrals Report
Measure visits a domain received from AI engines, such as ChatGPT and Perplexity, over a date range.
Inputs
domainstringrequired
Tracked domain using exact hostname from list_domains
end_datestringrequired
Window end in YYYY-MM-DD format (exclusive)
rationalestringrequired
Always provide a brief explanation of why you are calling this tool
start_datestringrequired
Window start in YYYY-MM-DD format (inclusive)
cursorstring
Pagination token
dimensionsarray
Group-by fields
filtersarray
Advanced predicates
limitinteger
Top-N row cap
metricsarray
Metrics to return
organization_idstring
Disambiguate domain across organizations
page_sizeinteger
First-page size, up to 10,000
referral_source_filterarray
Narrow to specific referrer vendors
referral_type_filterarray
Narrow to referral categories
profoundmcp_get_sentiment_reportMeasure sentiment in AI answers for a category over a date range.Read-only
Get Sentiment Report
Measure sentiment in AI answers for a category over a date range. Default metrics: positive, negative, and occurrences.
Inputs
category_idstringrequired
Category to report on
end_datestringrequired
Window end in YYYY-MM-DD format (exclusive)
rationalestringrequired
Always provide a brief explanation of why you are calling this tool
start_datestringrequired
Window start in YYYY-MM-DD format (inclusive)
asset_filterarray
Narrow to brand/competitor assets
cursorstring
Pagination token
filtersarray
Advanced predicates
limitinteger
Top-N row cap
metricsarray
Metrics to return
model_filterarray
Narrow to specific AI models
page_sizeinteger
First-page size, up to 10,000
persona_filterarray
Narrow to specific personas
region_filterarray
Narrow to specific regions
tag_filterarray
Narrow to specific tags
theme_filterarray
Narrow to specific sentiment themes
topic_filterarray
Narrow to specific topics
profoundmcp_get_visibility_reportMeasure how often and how prominently a brand appears in AI answers for a category over a date range.Read-only
Get Visibility Report
Measure how often and how prominently a brand appears in AI answers for a category over a date range.
Inputs
category_idstringrequired
Category to report on
end_datestringrequired
Window end in YYYY-MM-DD format (exclusive)
rationalestringrequired
Always provide a brief explanation of why you are calling this tool
start_datestringrequired
Window start in YYYY-MM-DD format (inclusive)
asset_filterarray
Narrow to brand/competitor assets
cursorstring
Pagination token
dimensionsarray
Group-by fields
filtersarray
Advanced predicates with field, operator, value
limitinteger
Top-N row cap
metricsarray
Metrics to return
model_filterarray
Narrow to specific AI models
page_sizeinteger
First-page size, up to 10,000
persona_filterarray
Narrow to specific personas
region_filterarray
Narrow to specific regions
tag_filterarray
Narrow to specific tags
topic_filterarray
Narrow to specific topics
profoundmcp_list_categoriesList tracked categories, markets, or segments in an organization.Read-only
List Categories
List tracked categories, markets, or segments in an organization. Most brand visibility reports are scoped to a category.
Inputs
org_idstringrequired
Organization whose categories to list
rationalestringrequired
Always provide a brief explanation of why you are calling this tool
profoundmcp_list_domainsList tracked domains for an organization.Read-only
List Domains
List tracked domains for an organization. Domains are exact hostnames, so www.example.com and example.com are distinct.
Inputs
org_idstringrequired
Organization whose tracked domains to list
rationalestringrequired
Always provide a brief explanation of why you are calling this tool
profoundmcp_list_modelsList the AI models Profound tracks.Read-only
List Models
List the AI models Profound tracks. Use returned model IDs to filter reports to a single engine.
Inputs
rationalestringrequired
Always provide a brief explanation of why you are calling this tool
profoundmcp_list_organizationsList the organizations the authenticated user can access.Read-only
List Organizations
List the organizations the authenticated user can access. Returned IDs feed category, domain, and report tools.
Inputs
rationalestringrequired
Always provide a brief explanation of why you are calling this tool
profoundmcp_list_promptsList prompts configured in a category.Read-only
List Prompts
List prompts configured in a category. Prompts are the questions Profound runs against AI engines to measure brand visibility.
Inputs
category_idstringrequired
Category to list prompts for
rationalestringrequired
Always provide a brief explanation of why you are calling this tool
combinestring
How include filters combineone of ANDOR
cursorstring
Pagination token from previous response
exclude_tag_idsarray
Exclude prompts carrying these tags
exclude_topic_idsarray
Exclude prompts under these topics
limitinteger
Maximum prompts to return
statusstring
Filter by prompt statusone of activedisabledall
tag_idsarray
Include only prompts carrying these tags
topic_idsarray
Include only prompts under these topics
profoundmcp_list_regionsList geographic regions configured for an organization.Read-only
List Regions
List geographic regions configured for an organization. Omit org_id to see regions across all accessible organizations.
Inputs
rationalestringrequired
Always provide a brief explanation of why you are calling this tool
org_idstring
Organization identifier
profoundmcp_list_tagsList tags available within a category for filtering prompts and reports.Read-only
List Tags
List tags available within a category for filtering prompts and reports.
Inputs
category_idstringrequired
Category whose tags to list
rationalestringrequired
Always provide a brief explanation of why you are calling this tool
profoundmcp_list_topicsList topics available within a category for filtering prompts and reports.Read-only
List Topics
List topics available within a category for filtering prompts and reports.
Inputs
category_idstringrequired
Category to list topics for
rationalestringrequired
Always provide a brief explanation of why you are calling this tool
profoundmcp_whoamiConfirm the authenticated user, organizations, regions, and entitlements available to this MCP session.Read-only
Whoami
Confirm the authenticated user, organizations, regions, and entitlements available to this MCP session.
Inputs
rationalestringrequired
Always provide a brief explanation of why you are calling this tool

Connect AI agents to the Profound MCP server

Setup

Install the SDK

Set your credentials

Create the Profound MCP connection

Authorize a user and make your first call

Tools

Call it

Returns

Get Bots Report

Inputs

Get Citations Report

Inputs

Get Prompt Answers

Inputs

Get Referrals Report

Inputs

Get Sentiment Report

Inputs

Get Visibility Report

Inputs

List Categories

Inputs

List Domains

Inputs

List Models

Inputs

List Organizations

Inputs

List Prompts

Inputs

List Regions

Inputs

List Tags

Inputs

List Topics

Inputs

Whoami

Inputs

Setup

Install the SDK

Set your credentials

Create the Profound MCP connection

Authorize a user and make your first call

Tools

Call it

Returns

Get Bots Report

Inputs

Get Citations Report

Inputs

Get Prompt Answers

Inputs

Get Referrals Report

Inputs

Get Sentiment Report

Inputs

Get Visibility Report

Inputs

List Categories

Inputs

List Domains

Inputs

List Models

Inputs

List Organizations

Inputs

List Prompts

Inputs

List Regions

Inputs

List Tags

Inputs

List Topics

Inputs

Whoami

Inputs

Related: other Marketing connectors