mcp-scraper 0.3.7 → 0.3.9

package/README.md

@@ -214,9 +214,9 @@ env = { MCP_SCRAPER_API_KEY = "sk_live_your_key" }
 - `browser_replay_start` — start an MP4 replay. Returns `replay_id`, `view_url`, and `download_url` when available.
 - `browser_replay_stop` — stop a replay. Returns the final `view_url` and `download_url`.
 - `browser_list_replays` — list replay videos for a session.
-- `browser_replay_download` — download and save the replay MP4 locally under `MCP_SCRAPER_OUTPUT_DIR/browser-replays`.
+- `browser_replay_download` — download and save the replay MP4 under `MCP_SCRAPER_OUTPUT_DIR/browser-replays`.
 - `browser_replay_mark` — while recording, locate a DOM target and return a replay-timed annotation object.
-- `browser_replay_annotate` — download a replay MP4, render timed boxes, circles, underlines, arrows, and labels using annotation objects from `browser_replay_mark` or exact bounds from `browser_locate`, and save a new annotated MP4 locally.
+- `browser_replay_annotate` — download a replay MP4, render timed boxes, circles, underlines, arrows, and labels using annotation objects from `browser_replay_mark` or exact bounds from `browser_locate`, and save a new annotated MP4 under `MCP_SCRAPER_OUTPUT_DIR/browser-replays`.
 - `browser_close`
 - `browser_list_sessions`
 
@@ -246,7 +246,7 @@ The `mcp-scraper` and `mcp-scraper-combined` NPX stdio servers also expose saved
 - `BROWSER_AGENT_PROFILE_NAME` is optional and sets the default saved hosted browser profile for `browser-agent` and `mcp-scraper-combined` stdio sessions. Aliases: `BROWSER_SERVICE_PROFILE_NAME`, `KERNEL_BROWSER_PROFILE_NAME`, `KERNEL_PROFILE_NAME`.
 - `BROWSER_AGENT_PROFILE_SAVE_CHANGES=true` is optional hosted setup behavior. It persists cookies and storage back to the named profile when `browser_close` deletes the hosted browser session. Aliases: `BROWSER_SERVICE_PROFILE_SAVE_CHANGES`, `KERNEL_BROWSER_PROFILE_SAVE_CHANGES`, `KERNEL_PROFILE_SAVE_CHANGES`.
 
-Every web intelligence tool call made through `mcp-scraper` or `mcp-scraper-combined` saves a full Markdown report locally by default and returns the file path in the MCP response. The hosted `/mcp` endpoint returns reports inline only and never writes files. Browser replay downloads are saved by `browser_replay_download` under `MCP_SCRAPER_OUTPUT_DIR/browser-replays`.
+Every web intelligence tool call made through `mcp-scraper` or `mcp-scraper-combined` saves a full Markdown report to disk by default and returns the file path in the MCP response. The hosted `/mcp` endpoint returns reports inline only and never writes files. Browser replay downloads are saved by `browser_replay_download` under `MCP_SCRAPER_OUTPUT_DIR/browser-replays`.
 
 ## Updating Existing Installs
 

package/dist/bin/api-server.cjs

@@ -21921,7 +21921,7 @@ var PACKAGE_VERSION;
 var init_version = __esm({
   "src/version.ts"() {
     "use strict";
-    PACKAGE_VERSION = "0.3.7";
+    PACKAGE_VERSION = "0.3.9";
   }
 });
 
@@ -23073,7 +23073,7 @@ function buildPaaExtractorMcpServer(executor, options = {}) {
 }
 function registerPaaExtractorMcpTools(server, executor, options = {}) {
   const savesReports = options.savesReportsLocally !== false;
-  const reportNote = savesReports ? " Saves a full Markdown report locally." : " Reports are returned inline; no files are saved on this hosted endpoint.";
+  const reportNote = savesReports ? " Saves a full Markdown report to disk." : " Reports are returned inline; no files are saved on this hosted endpoint.";
   const withReportNote = (description) => `${description}${reportNote}`;
   if (savesReports) registerSavedReportResources(server);
   server.registerTool("harvest_paa", {
@@ -24649,12 +24649,14 @@ async function createSession(opts = {}) {
   const resolvedProfileName = opts.profileName ?? browserServiceProfileName();
   const resolvedSaveProfileChanges = opts.saveProfileChanges ?? browserServiceProfileSaveChanges();
   const disableDefaultProxy = opts.disableDefaultProxy ?? !resolvedProxyId;
+  const startUrl = opts.startUrl?.trim();
   if (resolvedProfileName && resolvedSaveProfileChanges === true) {
     await ensureProfile(k, resolvedProfileName);
   }
-  const browser = await k.browsers.create({
+  const createPayload = {
     stealth: opts.stealth ?? true,
     timeout_seconds: opts.timeoutSeconds ?? DEFAULT_TIMEOUT_SECONDS,
+    ...startUrl ? { start_url: startUrl } : {},
     ...resolvedProxyId ? { proxy_id: resolvedProxyId } : {},
     ...resolvedProfileName ? {
       profile: {
@@ -24662,7 +24664,8 @@ async function createSession(opts = {}) {
         ...typeof resolvedSaveProfileChanges === "boolean" ? { save_changes: resolvedSaveProfileChanges } : {}
       }
     } : {}
-  });
+  };
+  const browser = await k.browsers.create(createPayload);
   const runtimeSessionId = browser.session_id;
   if (disableDefaultProxy) {
     try {
@@ -25049,6 +25052,7 @@ function buildBrowserAgentRoutes() {
     }
     const body = await c.req.json().catch(() => ({}));
     const timeoutSeconds = typeof body.timeout_seconds === "number" ? body.timeout_seconds : void 0;
+    const startUrl = typeof body.url === "string" ? body.url : void 0;
     const gate = await acquireConcurrencyGate(user, "browser_agent_session", {
       ttlSeconds: browserSessionLockTtlSeconds(timeoutSeconds),
       metadata: { label: typeof body.label === "string" ? body.label : null }
@@ -25061,6 +25065,7 @@ function buildBrowserAgentRoutes() {
         proxyId: typeof body.proxy_id === "string" ? body.proxy_id : void 0,
         profileName: typeof body.profile === "string" ? body.profile : void 0,
         saveProfileChanges: typeof body.save_profile_changes === "boolean" ? body.save_profile_changes : void 0,
+        startUrl,
         disableDefaultProxy: typeof body.disable_default_proxy === "boolean" ? body.disable_default_proxy : void 0,
         viewport: body.viewport && typeof body.viewport === "object" ? body.viewport : void 0
       });