research_web_fetch
Fetch and read one known page, rather than searching for one. A login-walled, private or loopback URL is refused: putty will not read a page the caller cannot. Asynchronous: returns a `jobId`, and the text arrives on `research_job_status`.
Fetch and read one known page, rather than searching for one. A login-walled, private or loopback URL is refused: putty will not read a page the caller cannot. Asynchronous: returns a jobId, and the text arrives on research_job_status.
Input
The tool takes a single JSON object. Every field, its type, and an example are on the generated reference at GET /mcp/tools, under this tool's name.
Calling it
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": { "name": "research_web_fetch", "arguments": {} }
}Put your arguments in place of the empty object. A call that fails comes back as a normal result carrying isError: true and a message naming what went wrong, not as a JSON-RPC protocol error.
Notes
The category is Research, subcategory Research. The full request and response shape, and a live playground, live on the generated reference at GET /mcp/tools.
research_web_search
Search the open web and return what it finds. Asynchronous: this returns a `jobId` and the answer arrives on `research_job_status`. Charged to the caller's own Apify account, so it refuses with a message telling them to connect one if there is none. A count above the cap is clamped, not refused.
research_crawl
Crawl outward from one page, following links up to `maxPages`. Set `maxPages` deliberately: each page is fetched and summarised, and the run is charged to the caller's own Apify account. A login-walled, private or loopback start URL is refused. Asynchronous: returns a `jobId`, and the collected text arrives on `research_job_status`.