@opencraw/mcp 0.1.1 → 0.1.3

package/README.md

@@ -27,14 +27,19 @@ can write files passes their `paths`; one that can't (a chat-only host) passes t
 `probe`/`run` call's `browserPath`/`insecureTls`, so a sandbox without Playwright's own bundled browser
 does not need every tool call to repeat them.
 
-`OPENCRAW_HOOKS` points at a JavaScript module whose default export is `{ name: function }`: the hooks the
-recipes call (`hook` steps and transforms). Only the server's environment names it, never a tool call, so an
-agent can run recipes that use your hooks but can't make the server load a module of its choosing.
+`OPENCRAW_PLUGINS` (or `OPENCRAW_HOOKS`) points at a plugins module: named exports `hooks` (the recipes'
+`hook` steps and transforms), `accessPlugins` (for `{ kind: "plugin" }` access profiles) and `captchaSolvers`;
+a module whose default export is `{ name: function }` is read as hooks alone. Only the server's environment
+names it, never a tool call, so an agent can run recipes that use your plugins but can't make the server load
+a module of its choosing.
 
 `OPENCRAW_ACCESS` points at an access config ([access.md](../../docs/recipes/access.md)): proxy profiles, with
 credentials as `{{env.NAME}}` read from the server's environment. The `probe` and `run` tools then take an
 `access` argument naming a profile. The file and the credentials never pass through a tool call.
 
+`OPENCRAW_PROFILES` is the directory of the persistent browser profiles recipes name in
+`session.browserProfile` (default `.opencraw/profiles` in the server's working directory).
+
 ## Tools
 
 ### `probe`
@@ -53,7 +58,13 @@ endpoints only a script fetches after load.
 
 Returns `{ url, status, findings: { jsonLd, inlineJson, jsonUrls, scriptHosts, apiLinks }, observed }`. For a
 PDF (served as `application/pdf`, or a local path) it adds `pdf: { pages, rows, headers }`: the first rows and
-every likely table header with the `selector` a `table` extract needs.
+every likely table header with the `selector` a `table` extract needs. For a spreadsheet or a CSV (served as a
+spreadsheet type or `text/csv`, or a local `.xlsx`, `.csv` or `.tsv` path) it adds
+`workbook: { csv?: { encoding, delimiter }, sheets, rows, headers }`. For a presentation it adds
+`deck: { width, height, slides, headers, charts, grids }`, and for JSON, JSON Lines or YAML
+`json: { format, type, tree, lists }`: the structure, and every list of records with its path. An HTML page
+adds `html: { tables, outline?, frontMatter? }`: its tables' header rows, and for Markdown its sections and
+front matter keys.
 
 ### `validate`
 
@@ -82,6 +93,7 @@ Crawls the recipes at the given paths, or passed inline.
 | `dryRun?` | One record per input recipe instead of a full crawl — for checking a recipe under construction. |
 | `headed?`, `browserPath?`, `insecureTls?`, `userAgent?` | As in the cli. |
 | `access?` | The access profile for recipes that name none, from the server's `OPENCRAW_ACCESS` config. |
+| `parallel?` | How many input recipes run at once (1 to 16, default 1). |
 
 Returns `{ report: CrawlReport, records?, truncated? }`. `records`/`truncated` are present only when `out`
 was not given, and `records` is capped at 50 even then.

package/dist/index.esm.js

@@ -1,6 +1,6 @@
 import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
 import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js';
-import { readRecipeFiles, probeUrl, loadForRun, resolveAccess, loadHooks } from '@opencraw/cli';
+import { readRecipeFiles, probeUrl, loadForRun, loadPlugins, resolveAccess } from '@opencraw/cli';
 import { z } from 'zod';
 import { memorySink, jsonLinesSink, createCrawler, RecipeSet, RecipeValidationError, RecipeBindingError, parseOutputRecipe, parseInputRecipe, bindRecipeSet } from '@opencraw/core';
 
@@ -72,7 +72,8 @@ async function probeTool(args) {
       insecureTls: args.insecureTls === true || process.env.OPENCRAW_INSECURE_TLS === '1',
       userAgent: args.userAgent,
       access: process.env.OPENCRAW_ACCESS === '' ? undefined : process.env.OPENCRAW_ACCESS,
-      accessProfile: args.access
+      accessProfile: args.access,
+      plugins: nonEmpty(process.env.OPENCRAW_PLUGINS) ?? nonEmpty(process.env.OPENCRAW_HOOKS)
     });
     return {
       content: [{
@@ -91,6 +92,9 @@ async function probeTool(args) {
     };
   }
 }
+function nonEmpty(value) {
+  return value === '' ? undefined : value;
+}
 
 const recipeObject = z.record(z.string(), z.unknown());
 const recipeObjects = z.array(recipeObject).min(1);
@@ -126,7 +130,8 @@ const runInputShape = {
   browserPath: z.string().optional().describe('A browser binary other than the one Playwright installed. Defaults to OPENCRAW_CHROMIUM in the server\'s environment.'),
   insecureTls: z.boolean().optional().describe("Accept an intercepting proxy's certificate. Defaults to OPENCRAW_INSECURE_TLS=1 in the server's environment."),
   userAgent: z.string().optional().describe('The user agent to send.'),
-  access: z.string().optional().describe('An access profile (a proxy) from the server\'s access config file, OPENCRAW_ACCESS, used by every recipe that names none. The error for an unknown name lists the profiles.')
+  access: z.string().optional().describe('An access profile (a proxy) from the server\'s access config file, OPENCRAW_ACCESS, used by every recipe that names none. The error for an unknown name lists the profiles.'),
+  parallel: z.int().min(1).max(16).optional().describe('How many input recipes run at once. Default 1. Iterations inside a recipe follow its limits.concurrency.')
 };
 /**
  * The `run` tool: crawls the recipes in `paths` or `recipes` (exactly one
@@ -163,15 +168,20 @@ async function runTool(args) {
     append: args.append
   });
   try {
-    const hooksFile = serverFile('OPENCRAW_HOOKS');
+    const pluginsFile = serverFile('OPENCRAW_PLUGINS') ?? serverFile('OPENCRAW_HOOKS');
+    const plugins = pluginsFile === undefined ? undefined : await loadPlugins(pluginsFile);
     crawler = createCrawler({
       sink,
-      hooks: hooksFile === undefined ? undefined : await loadHooks(hooksFile),
+      hooks: plugins?.hooks,
+      accessPlugins: plugins?.accessPlugins,
+      captchaSolvers: plugins?.captchaSolvers,
       access: await resolveAccess({
         insecureTls: false,
         access: serverFile('OPENCRAW_ACCESS'),
         accessProfile: args.access
       }),
+      profilesDir: serverFile('OPENCRAW_PROFILES'),
+      parallel: args.parallel,
       resume: args.resume,
       browser: {
         headless: args.headed !== true,
@@ -218,7 +228,7 @@ async function runTool(args) {
   }
 }
 /**
- * A file the server was started with (`OPENCRAW_ACCESS`, `OPENCRAW_HOOKS`).
+ * A file the server was started with (`OPENCRAW_ACCESS`, `OPENCRAW_PLUGINS` or `OPENCRAW_HOOKS`).
  * Never a tool argument: a caller picks a profile, never a file, and never
  * names a module for the server to run.
  */

package/dist/src/run-tool/run-tool.handler.d.ts

@@ -14,6 +14,7 @@ export declare const runInputShape: {
     insecureTls: z.ZodOptional<z.ZodBoolean>;
     userAgent: z.ZodOptional<z.ZodString>;
     access: z.ZodOptional<z.ZodString>;
+    parallel: z.ZodOptional<z.ZodInt>;
     paths: z.ZodOptional<z.ZodArray<z.ZodString>>;
     recipes: z.ZodOptional<z.ZodUnion<readonly [z.ZodString, z.ZodArray<z.ZodRecord<z.ZodString, z.ZodUnknown>>]>>;
 };
@@ -28,6 +29,7 @@ interface RunArgs extends RecipeSourceArgs {
     insecureTls?: boolean;
     userAgent?: string;
     access?: string;
+    parallel?: number;
 }
 /** What the `run` tool returns. */
 export interface RunResult {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@opencraw/mcp",
-  "version": "0.1.1",
+  "version": "0.1.3",
   "type": "module",
   "main": "./dist/index.esm.js",
   "module": "./dist/index.esm.js",
@@ -24,8 +24,8 @@
     "!**/*.js.map"
   ],
   "dependencies": {
-    "@opencraw/core": "^0.1.1",
-    "@opencraw/cli": "^0.1.1",
+    "@opencraw/core": "^0.1.3",
+    "@opencraw/cli": "^0.1.3",
     "@modelcontextprotocol/sdk": "^1.30.1",
     "playwright": "^1.63.0",
     "zod": "^4.6.5"