ScrapingAnt MCP integration for AI agents.
Connect AI agents to ScrapingAnt through 4 structured actions, including get api credits usage, extract content as markdown, and extract data with ai. Review…
- ACTION CONTRACTS
- 4
- AUTHENTICATION
- API key
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the ScrapingAnt integration exposes
The ScrapingAnt Agent App exposes 4 provider-backed actions for ai, data, and developer tools work. Its current contract lets an authorized agent read the current scrapingant subscription status and remaining api credits, convert a page into markdown through scrapingant's markdown transformation endpoint, and extract structured top-level json fields from a page through scrapingant's ai extraction endpoint. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.
For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected ScrapingAnt account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real ScrapingAnt capabilities.
Showing 4 of 4 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_api_credits_usageREADRead the current ScrapingAnt subscription status and remaining API credits.
extract_content_as_markdownREVIEWConvert a page into Markdown through ScrapingAnt's Markdown transformation endpoint.
INPUTS: url / method / browser / timeout / returnPageSource
extract_data_with_aiREVIEWExtract structured top-level JSON fields from a page through ScrapingAnt's AI extraction endpoint.
INPUTS: url / method / browser / timeout / returnPageSource
scrape_with_extended_json_outputREVIEWScrape a page through ScrapingAnt's v2 extended endpoint and return HTML, text, cookies, headers, XHRs, and iframes.
INPUTS: url / method / browser / timeout / returnPageSource
INPUT CONTRACTS
Know what the action needs before it runs.
extract_content_as_markdown
urlREQUIRED- The absolute URL to scrape.
methodOPTIONAL- The HTTP method sent to the target site through ScrapingAnt.
browserOPTIONAL- Whether ScrapingAnt should render the page in a headless browser.
timeoutOPTIONAL- The maximum upstream request time in seconds.
returnPageSourceOPTIONAL- Whether ScrapingAnt should return the raw server page source without JavaScript rendering.
extract_data_with_ai
urlREQUIRED- The absolute URL to scrape.
methodOPTIONAL- The HTTP method sent to the target site through ScrapingAnt.
browserOPTIONAL- Whether ScrapingAnt should render the page in a headless browser.
timeoutOPTIONAL- The maximum upstream request time in seconds.
returnPageSourceOPTIONAL- Whether ScrapingAnt should return the raw server page source without JavaScript rendering.
scrape_with_extended_json_output
urlREQUIRED- The absolute URL to scrape.
methodOPTIONAL- The HTTP method sent to the target site through ScrapingAnt.
browserOPTIONAL- Whether ScrapingAnt should render the page in a headless browser.
timeoutOPTIONAL- The maximum upstream request time in seconds.
returnPageSourceOPTIONAL- Whether ScrapingAnt should return the raw server page source without JavaScript rendering.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Api Credits Usage
Read the current ScrapingAnt subscription status and remaining API credits. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_api_credits_usageVerify with Extract Content As Markdown
Convert a page into Markdown through ScrapingAnt's Markdown transformation endpoint. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
extract_content_as_markdownSAFETY BOUNDARY
Operate ScrapingAnt with explicit limits
- Authorize ScrapingAnt with API key and grant only the provider access required by the selected actions.
- The current action names appear read-oriented, but returned ScrapingAnt data may still be sensitive and should be minimized before it enters model context.
- Do not infer permission from catalog visibility. Workspace policy, connection identity, and upstream authorization still govern execution.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in ScrapingAnt rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the ScrapingAnt task completed successfully.
CONNECTION MODEL
API key
ScrapingAnt API key sent as the x-api-key query parameter.
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 1
- WRITE SIGNALS
- 0
- HIGH IMPACT
- 0
- REVIEW SIGNALS
- 3
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by ScrapingAnt.