Create or update a content source

curl --request PATCH \
  --url https://api.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "configId": "6683f1c2a4b19e0012ab34cd",
  "enabled": true,
  "startUrl": "https://ajuda.acme.com",
  "cron": "0 0 3 * * *",
  "allowedDomains": "ajuda.acme.com",
  "pathFilter": "/artigos",
  "excludePathFilter": "/artigos/rascunhos",
  "defaultScraperTag": "ajuda",
  "defaultScraperTopic": "Autoatendimento",
  "maxAgeMs": 86400000,
  "locales": [
    "pt-BR"
  ]
}
'

import requests

url = "https://api.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config"

payload = {
    "configId": "6683f1c2a4b19e0012ab34cd",
    "enabled": True,
    "startUrl": "https://ajuda.acme.com",
    "cron": "0 0 3 * * *",
    "allowedDomains": "ajuda.acme.com",
    "pathFilter": "/artigos",
    "excludePathFilter": "/artigos/rascunhos",
    "defaultScraperTag": "ajuda",
    "defaultScraperTopic": "Autoatendimento",
    "maxAgeMs": 86400000,
    "locales": ["pt-BR"]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.patch(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'PATCH',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    configId: '6683f1c2a4b19e0012ab34cd',
    enabled: true,
    startUrl: 'https://ajuda.acme.com',
    cron: '0 0 3 * * *',
    allowedDomains: 'ajuda.acme.com',
    pathFilter: '/artigos',
    excludePathFilter: '/artigos/rascunhos',
    defaultScraperTag: 'ajuda',
    defaultScraperTopic: 'Autoatendimento',
    maxAgeMs: 86400000,
    locales: ['pt-BR']
  })
};

fetch('https://api.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "PATCH",
  CURLOPT_POSTFIELDS => json_encode([
    'configId' => '6683f1c2a4b19e0012ab34cd',
    'enabled' => true,
    'startUrl' => 'https://ajuda.acme.com',
    'cron' => '0 0 3 * * *',
    'allowedDomains' => 'ajuda.acme.com',
    'pathFilter' => '/artigos',
    'excludePathFilter' => '/artigos/rascunhos',
    'defaultScraperTag' => 'ajuda',
    'defaultScraperTopic' => 'Autoatendimento',
    'maxAgeMs' => 86400000,
    'locales' => [
        'pt-BR'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config"

	payload := strings.NewReader("{\n  \"configId\": \"6683f1c2a4b19e0012ab34cd\",\n  \"enabled\": true,\n  \"startUrl\": \"https://ajuda.acme.com\",\n  \"cron\": \"0 0 3 * * *\",\n  \"allowedDomains\": \"ajuda.acme.com\",\n  \"pathFilter\": \"/artigos\",\n  \"excludePathFilter\": \"/artigos/rascunhos\",\n  \"defaultScraperTag\": \"ajuda\",\n  \"defaultScraperTopic\": \"Autoatendimento\",\n  \"maxAgeMs\": 86400000,\n  \"locales\": [\n    \"pt-BR\"\n  ]\n}")

	req, _ := http.NewRequest("PATCH", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.patch("https://api.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"configId\": \"6683f1c2a4b19e0012ab34cd\",\n  \"enabled\": true,\n  \"startUrl\": \"https://ajuda.acme.com\",\n  \"cron\": \"0 0 3 * * *\",\n  \"allowedDomains\": \"ajuda.acme.com\",\n  \"pathFilter\": \"/artigos\",\n  \"excludePathFilter\": \"/artigos/rascunhos\",\n  \"defaultScraperTag\": \"ajuda\",\n  \"defaultScraperTopic\": \"Autoatendimento\",\n  \"maxAgeMs\": 86400000,\n  \"locales\": [\n    \"pt-BR\"\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Patch.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"configId\": \"6683f1c2a4b19e0012ab34cd\",\n  \"enabled\": true,\n  \"startUrl\": \"https://ajuda.acme.com\",\n  \"cron\": \"0 0 3 * * *\",\n  \"allowedDomains\": \"ajuda.acme.com\",\n  \"pathFilter\": \"/artigos\",\n  \"excludePathFilter\": \"/artigos/rascunhos\",\n  \"defaultScraperTag\": \"ajuda\",\n  \"defaultScraperTopic\": \"Autoatendimento\",\n  \"maxAgeMs\": 86400000,\n  \"locales\": [\n    \"pt-BR\"\n  ]\n}"

response = http.request(request)
puts response.read_body

[
  {
    "startUrl": "https://ajuda.acme.com",
    "cron": "0 0 3 * * *",
    "allowedDomains": "ajuda.acme.com",
    "pathFilter": "/artigos",
    "excludePathFilter": "/artigos/rascunhos",
    "defaultScraperTag": "ajuda",
    "createdAt": "2026-08-10T14:32:05",
    "configId": "6683f1c2a4b19e0012ab34cd",
    "enabled": true,
    "defaultScraperTopic": "Autoatendimento",
    "maxAgeMs": 86400000,
    "locales": [
      "pt-BR"
    ],
    "updatedAt": "2026-08-10T18:20:41"
  }
]

{
  "error": "Forbidden: token holds no claim for the requested account"
}

{
  "error": "Forbidden: token holds no claim for the requested account"
}

{
  "error": "Forbidden: token holds no claim for the requested account"
}

Content Sources

Create or update a content source

Send configId to change an existing source, or omit it to create one — a configId that matches no source of this knowledge base is refused, never created under the id you sent. Every field is optional and an omitted one keeps what is stored. maxAgeMs is the exception worth reading: omit it to keep the current freshness window, send null to restore the crawler’s default, send a number of milliseconds to apply it — 0 forces a full re-crawl on the next run.

PATCH

knowledge-bases

{kbId}

scraper-config

Create or update a content source

curl --request PATCH \
  --url https://api.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "configId": "6683f1c2a4b19e0012ab34cd",
  "enabled": true,
  "startUrl": "https://ajuda.acme.com",
  "cron": "0 0 3 * * *",
  "allowedDomains": "ajuda.acme.com",
  "pathFilter": "/artigos",
  "excludePathFilter": "/artigos/rascunhos",
  "defaultScraperTag": "ajuda",
  "defaultScraperTopic": "Autoatendimento",
  "maxAgeMs": 86400000,
  "locales": [
    "pt-BR"
  ]
}
'

import requests

url = "https://api.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config"

payload = {
    "configId": "6683f1c2a4b19e0012ab34cd",
    "enabled": True,
    "startUrl": "https://ajuda.acme.com",
    "cron": "0 0 3 * * *",
    "allowedDomains": "ajuda.acme.com",
    "pathFilter": "/artigos",
    "excludePathFilter": "/artigos/rascunhos",
    "defaultScraperTag": "ajuda",
    "defaultScraperTopic": "Autoatendimento",
    "maxAgeMs": 86400000,
    "locales": ["pt-BR"]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.patch(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'PATCH',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    configId: '6683f1c2a4b19e0012ab34cd',
    enabled: true,
    startUrl: 'https://ajuda.acme.com',
    cron: '0 0 3 * * *',
    allowedDomains: 'ajuda.acme.com',
    pathFilter: '/artigos',
    excludePathFilter: '/artigos/rascunhos',
    defaultScraperTag: 'ajuda',
    defaultScraperTopic: 'Autoatendimento',
    maxAgeMs: 86400000,
    locales: ['pt-BR']
  })
};

fetch('https://api.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "PATCH",
  CURLOPT_POSTFIELDS => json_encode([
    'configId' => '6683f1c2a4b19e0012ab34cd',
    'enabled' => true,
    'startUrl' => 'https://ajuda.acme.com',
    'cron' => '0 0 3 * * *',
    'allowedDomains' => 'ajuda.acme.com',
    'pathFilter' => '/artigos',
    'excludePathFilter' => '/artigos/rascunhos',
    'defaultScraperTag' => 'ajuda',
    'defaultScraperTopic' => 'Autoatendimento',
    'maxAgeMs' => 86400000,
    'locales' => [
        'pt-BR'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config"

	payload := strings.NewReader("{\n  \"configId\": \"6683f1c2a4b19e0012ab34cd\",\n  \"enabled\": true,\n  \"startUrl\": \"https://ajuda.acme.com\",\n  \"cron\": \"0 0 3 * * *\",\n  \"allowedDomains\": \"ajuda.acme.com\",\n  \"pathFilter\": \"/artigos\",\n  \"excludePathFilter\": \"/artigos/rascunhos\",\n  \"defaultScraperTag\": \"ajuda\",\n  \"defaultScraperTopic\": \"Autoatendimento\",\n  \"maxAgeMs\": 86400000,\n  \"locales\": [\n    \"pt-BR\"\n  ]\n}")

	req, _ := http.NewRequest("PATCH", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.patch("https://api.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"configId\": \"6683f1c2a4b19e0012ab34cd\",\n  \"enabled\": true,\n  \"startUrl\": \"https://ajuda.acme.com\",\n  \"cron\": \"0 0 3 * * *\",\n  \"allowedDomains\": \"ajuda.acme.com\",\n  \"pathFilter\": \"/artigos\",\n  \"excludePathFilter\": \"/artigos/rascunhos\",\n  \"defaultScraperTag\": \"ajuda\",\n  \"defaultScraperTopic\": \"Autoatendimento\",\n  \"maxAgeMs\": 86400000,\n  \"locales\": [\n    \"pt-BR\"\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Patch.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"configId\": \"6683f1c2a4b19e0012ab34cd\",\n  \"enabled\": true,\n  \"startUrl\": \"https://ajuda.acme.com\",\n  \"cron\": \"0 0 3 * * *\",\n  \"allowedDomains\": \"ajuda.acme.com\",\n  \"pathFilter\": \"/artigos\",\n  \"excludePathFilter\": \"/artigos/rascunhos\",\n  \"defaultScraperTag\": \"ajuda\",\n  \"defaultScraperTopic\": \"Autoatendimento\",\n  \"maxAgeMs\": 86400000,\n  \"locales\": [\n    \"pt-BR\"\n  ]\n}"

response = http.request(request)
puts response.read_body

[
  {
    "startUrl": "https://ajuda.acme.com",
    "cron": "0 0 3 * * *",
    "allowedDomains": "ajuda.acme.com",
    "pathFilter": "/artigos",
    "excludePathFilter": "/artigos/rascunhos",
    "defaultScraperTag": "ajuda",
    "createdAt": "2026-08-10T14:32:05",
    "configId": "6683f1c2a4b19e0012ab34cd",
    "enabled": true,
    "defaultScraperTopic": "Autoatendimento",
    "maxAgeMs": 86400000,
    "locales": [
      "pt-BR"
    ],
    "updatedAt": "2026-08-10T18:20:41"
  }
]

{
  "error": "Forbidden: token holds no claim for the requested account"
}

{
  "error": "Forbidden: token holds no claim for the requested account"
}

{
  "error": "Forbidden: token holds no claim for the requested account"
}

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

kbId

string

required

Knowledge base to operate on. Get the ids from listMyKnowledgeBases.

Body

application/json

What to change on a content source, or the source to create.

configId

string

Source to change, as returned by listContentSources. Omit to create a new one — the id is assigned then and comes back in the response.

Example:

"6683f1c2a4b19e0012ab34cd"

enabled

boolean

A disabled source stays configured but is not crawled. Defaults to true on a new source.

Example:

true

startUrl

string

Where the crawl starts.

Example:

"https://ajuda.acme.com"

cron

string

When the crawl runs, as a cron expression. Leave empty to run it only on demand.

Example:

"0 0 3 * * *"

allowedDomains

string

Hosts the crawl may follow links into. Comma-separated.

Example:

"ajuda.acme.com"

pathFilter

string

Only crawl paths matching this. Leave empty for the whole site.

Example:

"/artigos"

excludePathFilter

string

Paths to never crawl, even when they match pathFilter.

Example:

"/artigos/rascunhos"

defaultScraperTag

string

Tag to apply to every entry this source imports.

Example:

"ajuda"

defaultScraperTopic

string

Topic to group every entry this source imports under.

Example:

"Autoatendimento"

type

enum<string>

Crawler to run this source on. Defaults to FIRECRAWL on a new source.

Available options:

SCRAPY,

FIRECRAWL,

CLOUDCHAT

maxAgeMs

integer<int64> | null

How old a previously fetched page may be before it is fetched again, in milliseconds. Omit to keep the current setting, send null to restore the crawler's default, send 0 to force a full re-crawl.

Example:

86400000

locales

string[]

Languages to keep when the site publishes several.

Example:

["pt-BR"]

Response

Every source of this knowledge base, as stored after the change.

startUrl

string

required

Where the crawl starts.

Example:

"https://ajuda.acme.com"

cron

string

required

When the crawl runs, as a cron expression. Empty means it only runs on demand.

Example:

"0 0 3 * * *"

allowedDomains

string

required

Hosts the crawl may follow links into. Comma-separated.

Example:

"ajuda.acme.com"

pathFilter

string

required

Only paths matching this are crawled. Empty means the whole site.

Example:

"/artigos"

excludePathFilter

string

required

Paths never crawled, even when they match pathFilter.

Example:

"/artigos/rascunhos"

defaultScraperTag

string

required

Tag applied to every entry this source imports.

Example:

"ajuda"

type

enum<string>

required

Crawler this source runs on.

Available options:

SCRAPY,

FIRECRAWL,

CLOUDCHAT

createdAt

string

required

When the source was configured (ISO-8601).

Example:

"2026-08-10T14:32:05"

configId

string

Use this id to update or delete this source.

Example:

"6683f1c2a4b19e0012ab34cd"

enabled

boolean

A disabled source stays configured but is not crawled.

Example:

true

defaultScraperTopic

string

Topic every entry this source imports is grouped under.

Example:

"Autoatendimento"

maxAgeMs

integer<int64>

How old a previously fetched page may be before it is fetched again, in milliseconds. Absent means the crawler's own default.

Example:

86400000

locales

string[]

Languages to keep when the site publishes several.

Example:

["pt-BR"]

updatedAt

string

When it last changed (ISO-8601). Absent until the first change.

Example:

"2026-08-10T18:20:41"

Getting Started

Authentication

Knowledge Bases

Knowledge Base Content

Content Quality

Content Improvements

Content Sources

MCP Servers

Playground

Project Settings

Create or update a content source

Authorizations

Path Parameters

Body

Response