ScrapeGraphAI MCP integration for AI agents.
Connect AI agents to ScrapeGraphAI through 6 structured actions, including get credits, extract, and get history. Review authentication, inputs, workflows, a…
- ACTION CONTRACTS
- 6
- 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 ScrapeGraphAI integration exposes
The ScrapeGraphAI Agent App exposes 6 provider-backed actions for ai, data, and developer tools work. Its current contract lets an authorized agent check scrapegraphai remaining credits, plan, and job quotas, extract structured json from a url, raw html, or markdown with a natural-language prompt, and retrieve one scrapegraphai history entry by request id. 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 ScrapeGraphAI account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real ScrapeGraphAI capabilities.
Showing 6 of 6 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_creditsREADCheck ScrapeGraphAI remaining credits, plan, and job quotas.
extractREVIEWExtract structured JSON from a URL, raw HTML, or markdown with a natural-language prompt.
INPUTS: url / html / markdown / prompt / schema
get_historyREADRetrieve one ScrapeGraphAI history entry by request ID.
INPUTS: id
list_historyREADList recent ScrapeGraphAI request history entries with optional filters.
INPUTS: page / limit / service
scrapeREVIEWFetch a public URL with ScrapeGraphAI and return one or more content formats.
INPUTS: url / formats / contentType / fetchConfig
searchREADRun a web search with ScrapeGraphAI, fetch the top results, and optionally extract JSON from them.
INPUTS: query / numResults / prompt / schema / format
INPUT CONTRACTS
Know what the action needs before it runs.
extract
urlOPTIONAL- The public URL to extract from.
htmlOPTIONAL- Raw HTML content to extract from.
markdownOPTIONAL- Markdown content to extract from.
promptREQUIRED- The natural-language description of what to extract.
schemaOPTIONAL- A loose JSON object.
get_history
idOPTIONAL- The UUID of the ScrapeGraphAI history entry to retrieve.
list_history
pageOPTIONAL- The 1-indexed history page number to fetch.
limitOPTIONAL- The number of history entries to return per page.
serviceOPTIONAL- The ScrapeGraphAI service type to filter by.
scrape
urlREQUIRED- The public URL to fetch.
formatsREQUIRED- The output formats to return from ScrapeGraphAI.
contentTypeOPTIONAL- The content type override, such as text/html or application/pdf.
fetchConfigOPTIONAL- Fetch-time options used when ScrapeGraphAI retrieves a page.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Credits
Check ScrapeGraphAI remaining credits, plan, and job quotas. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_creditsVerify with Get History
Retrieve one ScrapeGraphAI history entry by request ID. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
get_historySAFETY BOUNDARY
Operate ScrapeGraphAI with explicit limits
- Authorize ScrapeGraphAI with API key and grant only the provider access required by the selected actions.
- The current action names appear read-oriented, but returned ScrapeGraphAI 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 ScrapeGraphAI rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the ScrapeGraphAI task completed successfully.
CONNECTION MODEL
API key
ScrapeGraphAI API key sent in the SGAI-APIKEY header.
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
- 4
- WRITE SIGNALS
- 0
- HIGH IMPACT
- 0
- REVIEW SIGNALS
- 2
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 ScrapeGraphAI.