API: tools/extract

tools/extract#

Interfaces#

ExtractResponse#

The spec-shaped per-URL extraction response.

Properties#

Property	Type	Description	Defined in
`api_endpoints`	`unknown`	-	src/tools/extract.ts:49
`content`	`string`	-	src/tools/extract.ts:42
`extraction`	{ `confidence`: `number`; `method`: `string`; `rendered`: `boolean`; }	-	src/tools/extract.ts:43
`extraction.confidence`	`number`	-	src/tools/extract.ts:45
`extraction.method`	`string`	-	src/tools/extract.ts:44
`extraction.rendered`	`boolean`	-	src/tools/extract.ts:46
`metadata`	`PageMetadata`	-	src/tools/extract.ts:50
`security`	`SecurityReport`	Provenance for the content above. Page text is attacker-controlled, so it is always marked untrusted and screened for text addressing the agent.	src/tools/extract.ts:55
`structured_data`	`unknown`	-	src/tools/extract.ts:48
`title`	`string`	-	src/tools/extract.ts:41
`url`	`string`	-	src/tools/extract.ts:40

Variables#

BROWSER_URL_TIMEOUT_MS#

const BROWSER_URL_TIMEOUT_MS: 35000 = 35_000

Defined in: src/tools/extract.ts:62

Per-URL timeout when a browser render may run, in milliseconds.

extractInputSchema#

const extractInputSchema: { browser_fallback: ZodDefault<ZodBoolean>; include_api_data: ZodDefault<ZodBoolean>; include_structured_data: ZodDefault<ZodBoolean>; mode: ZodDefault<ZodEnum<["auto", "fast", "browser"]>>; urls: ZodArray<ZodString, "many">; }

Defined in: src/tools/extract.ts:30

Input schema for web_extract.

Type Declaration#

Name	Type	Defined in
`browser_fallback`	`ZodDefault`<`ZodBoolean`>	src/tools/extract.ts:35
`include_api_data`	`ZodDefault`<`ZodBoolean`>	src/tools/extract.ts:33
`include_structured_data`	`ZodDefault`<`ZodBoolean`>	src/tools/extract.ts:34
`mode`	`ZodDefault`<`ZodEnum`<[`"auto"`, `"fast"`, `"browser"`]>>	src/tools/extract.ts:32
`urls`	`ZodArray`<`ZodString`, `"many"`>	src/tools/extract.ts:31

URL_TIMEOUT_MS#

const URL_TIMEOUT_MS: 8000 = 8_000

Defined in: src/tools/extract.ts:59

Per-URL timeout when the browser tier cannot run, in milliseconds.

Functions#

registerExtract()#

registerExtract(server, cache?): void

Defined in: src/tools/extract.ts:205

Parameters#

Parameter	Type
`server`	`McpServer`
`cache?`	`Cache`

Returns#

void

runExtract()#

runExtract(args): Promise<ExtractResponse[]>

Defined in: src/tools/extract.ts:166

Run a bounded-concurrency extraction over the given URLs.

Exported separately so tests and the smoke harness can call the handler logic directly.

Parameters#

Parameter	Type
`args`	{ `browser_fallback?`: `boolean`; `cache?`: `Cache`; `include_api_data?`: `boolean`; `include_structured_data?`: `boolean`; `mode?`: `"auto"` \| `"browser"` \| `"fast"`; `urls`: `string`[]; }
`args.browser_fallback?`	`boolean`
`args.cache?`	`Cache`
`args.include_api_data?`	`boolean`
`args.include_structured_data?`	`boolean`
`args.mode?`	`"auto"` \| `"browser"` \| `"fast"`
`args.urls`	`string`[]

Returns#

Promise<ExtractResponse[]>

timeoutForMode()#

timeoutForMode(mode, browserFallback): number

Defined in: src/tools/extract.ts:65

The per-URL budget for a given mode / fallback combination.

Parameters#

Parameter	Type
`mode`	`"auto"` \| `"browser"` \| `"fast"`
`browserFallback`	`boolean`

Returns#

number