mcp-scraper 0.2.19 → 0.2.21

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (77) hide show
  1. package/README.md +36 -5
  2. package/dist/bin/api-server.cjs +1072 -349
  3. package/dist/bin/api-server.cjs.map +1 -1
  4. package/dist/bin/api-server.js +3 -3
  5. package/dist/bin/browser-agent-stdio-server.cjs +1274 -75
  6. package/dist/bin/browser-agent-stdio-server.cjs.map +1 -1
  7. package/dist/bin/browser-agent-stdio-server.js +4 -2
  8. package/dist/bin/browser-agent-stdio-server.js.map +1 -1
  9. package/dist/bin/mcp-scraper-cli.cjs +659 -210
  10. package/dist/bin/mcp-scraper-cli.cjs.map +1 -1
  11. package/dist/bin/mcp-scraper-cli.js +108 -9
  12. package/dist/bin/mcp-scraper-cli.js.map +1 -1
  13. package/dist/bin/mcp-scraper-combined-stdio-server.cjs +2104 -566
  14. package/dist/bin/mcp-scraper-combined-stdio-server.cjs.map +1 -1
  15. package/dist/bin/mcp-scraper-combined-stdio-server.js +7 -4
  16. package/dist/bin/mcp-scraper-combined-stdio-server.js.map +1 -1
  17. package/dist/bin/mcp-scraper-install.cjs +3 -3
  18. package/dist/bin/mcp-scraper-install.cjs.map +1 -1
  19. package/dist/bin/mcp-scraper-install.js +2 -2
  20. package/dist/bin/mcp-stdio-server.cjs +726 -387
  21. package/dist/bin/mcp-stdio-server.cjs.map +1 -1
  22. package/dist/bin/mcp-stdio-server.js +3 -2
  23. package/dist/bin/mcp-stdio-server.js.map +1 -1
  24. package/dist/bin/paa-harvest.cjs +5 -3
  25. package/dist/bin/paa-harvest.cjs.map +1 -1
  26. package/dist/bin/paa-harvest.js +5 -2
  27. package/dist/bin/paa-harvest.js.map +1 -1
  28. package/dist/{chunk-TL7YTFLH.js → chunk-DBQDG7EH.js} +99 -27
  29. package/dist/chunk-DBQDG7EH.js.map +1 -0
  30. package/dist/chunk-DUEW4EOO.js +214 -0
  31. package/dist/chunk-DUEW4EOO.js.map +1 -0
  32. package/dist/{chunk-F44RBOJ5.js → chunk-H2R232HK.js} +216 -108
  33. package/dist/chunk-H2R232HK.js.map +1 -0
  34. package/dist/chunk-HS6OKELW.js +1786 -0
  35. package/dist/chunk-HS6OKELW.js.map +1 -0
  36. package/dist/{chunk-CQTAKXBN.js → chunk-IPW4LFOT.js} +11 -116
  37. package/dist/chunk-IPW4LFOT.js.map +1 -0
  38. package/dist/chunk-LFATOGDF.js +111 -0
  39. package/dist/chunk-LFATOGDF.js.map +1 -0
  40. package/dist/{chunk-MCBOZ2JF.js → chunk-MLNCKQ2B.js} +3 -3
  41. package/dist/chunk-MLNCKQ2B.js.map +1 -0
  42. package/dist/{chunk-4UEVYYDW.js → chunk-O5J7E4VX.js} +394 -57
  43. package/dist/chunk-O5J7E4VX.js.map +1 -0
  44. package/dist/{chunk-BSYPATSM.js → chunk-SXTXMFEQ.js} +2 -2
  45. package/dist/chunk-WN7PBKMV.js +28 -0
  46. package/dist/chunk-WN7PBKMV.js.map +1 -0
  47. package/dist/chunk-XKUDVN2E.js +7 -0
  48. package/dist/chunk-XKUDVN2E.js.map +1 -0
  49. package/dist/{db-P5X6UQ3E.js → db-BE4JVB3V.js} +8 -2
  50. package/dist/index.cjs +5 -3
  51. package/dist/index.cjs.map +1 -1
  52. package/dist/index.d.cts +2 -2
  53. package/dist/index.d.ts +2 -2
  54. package/dist/index.js +3 -1
  55. package/dist/index.js.map +1 -1
  56. package/dist/{server-CRUSZA2Q.js → server-24XIQ6W6.js} +248 -40
  57. package/dist/server-24XIQ6W6.js.map +1 -0
  58. package/dist/{worker-OZSWIS3F.js → worker-SLQ375UG.js} +8 -5
  59. package/dist/{worker-OZSWIS3F.js.map → worker-SLQ375UG.js.map} +1 -1
  60. package/docs/adr/0001-in-page-graphql-interception-for-anti-bot-scraping.md +2 -2
  61. package/docs/mcp-tool-craft-lint.generated.md +51 -0
  62. package/docs/mcp-tool-manifest.generated.json +1534 -0
  63. package/docs/specs/local-competitive-audit-spec.md +1 -2
  64. package/docs/specs/mcp-tool-definition-quality-audit-spec.md +1602 -0
  65. package/package.json +4 -1
  66. package/dist/chunk-4UEVYYDW.js.map +0 -1
  67. package/dist/chunk-76P4DKWR.js +0 -793
  68. package/dist/chunk-76P4DKWR.js.map +0 -1
  69. package/dist/chunk-CQTAKXBN.js.map +0 -1
  70. package/dist/chunk-F44RBOJ5.js.map +0 -1
  71. package/dist/chunk-MCBOZ2JF.js.map +0 -1
  72. package/dist/chunk-RU2HZD55.js +0 -7
  73. package/dist/chunk-RU2HZD55.js.map +0 -1
  74. package/dist/chunk-TL7YTFLH.js.map +0 -1
  75. package/dist/server-CRUSZA2Q.js.map +0 -1
  76. /package/dist/{chunk-BSYPATSM.js.map → chunk-SXTXMFEQ.js.map} +0 -0
  77. /package/dist/{db-P5X6UQ3E.js.map → db-BE4JVB3V.js.map} +0 -0
@@ -2,9 +2,10 @@
2
2
  import {
3
3
  HttpMcpToolExecutor,
4
4
  buildPaaExtractorMcpServer
5
- } from "../chunk-4UEVYYDW.js";
5
+ } from "../chunk-O5J7E4VX.js";
6
6
  import "../chunk-M2S27J6Z.js";
7
- import "../chunk-RU2HZD55.js";
7
+ import "../chunk-LFATOGDF.js";
8
+ import "../chunk-XKUDVN2E.js";
8
9
 
9
10
  // bin/mcp-stdio-server.ts
10
11
  import { readFileSync } from "fs";
@@ -1 +1 @@
1
- {"version":3,"sources":["../../bin/mcp-stdio-server.ts"],"sourcesContent":["#!/usr/bin/env node\nimport { readFileSync } from 'node:fs'\nimport { homedir } from 'node:os'\nimport { join } from 'node:path'\nimport { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js'\nimport { HttpMcpToolExecutor } from '../src/mcp/http-mcp-tool-executor.js'\nimport { buildPaaExtractorMcpServer } from '../src/mcp/paa-mcp-server.js'\n\nfunction readApiKeyFile(): string | undefined {\n const explicitPath = process.env.MCP_SCRAPER_KEY_PATH?.trim()\n const paths = [explicitPath, join(homedir(), '.mcp-scraper-key')].filter(Boolean) as string[]\n for (const path of paths) {\n try {\n const value = readFileSync(path, 'utf8').trim()\n if (value) return value\n } catch {}\n }\n return undefined\n}\n\nconst apiKey = (\n process.env.MCP_SCRAPER_API_KEY ??\n process.env.MCP_SCRAPER_KEY ??\n process.env.MCP_API_KEY ??\n readApiKeyFile()\n)?.trim()\nif (!apiKey) {\n process.stderr.write('MCP_SCRAPER_API_KEY env var or ~/.mcp-scraper-key is required\\n')\n process.exit(1)\n}\n\nconst baseUrl = process.env.MCP_SCRAPER_BASE_URL?.trim() || process.env.MCP_BASE_URL?.trim() || 'https://mcpscraper.dev'\nconst executor = new HttpMcpToolExecutor(baseUrl, apiKey)\nconst server = buildPaaExtractorMcpServer(executor)\nconst transport = new StdioServerTransport()\n\nasync function main() {\n await server.connect(transport)\n}\n\nmain().catch((err) => {\n process.stderr.write(`${err instanceof Error ? err.message : String(err)}\\n`)\n process.exit(1)\n})\n"],"mappings":";;;;;;;;;AACA,SAAS,oBAAoB;AAC7B,SAAS,eAAe;AACxB,SAAS,YAAY;AACrB,SAAS,4BAA4B;AAIrC,SAAS,iBAAqC;AAC5C,QAAM,eAAe,QAAQ,IAAI,sBAAsB,KAAK;AAC5D,QAAM,QAAQ,CAAC,cAAc,KAAK,QAAQ,GAAG,kBAAkB,CAAC,EAAE,OAAO,OAAO;AAChF,aAAW,QAAQ,OAAO;AACxB,QAAI;AACF,YAAM,QAAQ,aAAa,MAAM,MAAM,EAAE,KAAK;AAC9C,UAAI,MAAO,QAAO;AAAA,IACpB,QAAQ;AAAA,IAAC;AAAA,EACX;AACA,SAAO;AACT;AAEA,IAAM,UACJ,QAAQ,IAAI,uBACZ,QAAQ,IAAI,mBACZ,QAAQ,IAAI,eACZ,eAAe,IACd,KAAK;AACR,IAAI,CAAC,QAAQ;AACX,UAAQ,OAAO,MAAM,iEAAiE;AACtF,UAAQ,KAAK,CAAC;AAChB;AAEA,IAAM,UAAU,QAAQ,IAAI,sBAAsB,KAAK,KAAK,QAAQ,IAAI,cAAc,KAAK,KAAK;AAChG,IAAM,WAAW,IAAI,oBAAoB,SAAS,MAAM;AACxD,IAAM,SAAS,2BAA2B,QAAQ;AAClD,IAAM,YAAY,IAAI,qBAAqB;AAE3C,eAAe,OAAO;AACpB,QAAM,OAAO,QAAQ,SAAS;AAChC;AAEA,KAAK,EAAE,MAAM,CAAC,QAAQ;AACpB,UAAQ,OAAO,MAAM,GAAG,eAAe,QAAQ,IAAI,UAAU,OAAO,GAAG,CAAC;AAAA,CAAI;AAC5E,UAAQ,KAAK,CAAC;AAChB,CAAC;","names":[]}
1
+ {"version":3,"sources":["../../bin/mcp-stdio-server.ts"],"sourcesContent":["#!/usr/bin/env node\nimport { readFileSync } from 'node:fs'\nimport { homedir } from 'node:os'\nimport { join } from 'node:path'\nimport { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js'\nimport { HttpMcpToolExecutor } from '../src/mcp/http-mcp-tool-executor.js'\nimport { buildPaaExtractorMcpServer } from '../src/mcp/paa-mcp-server.js'\n\nfunction readApiKeyFile(): string | undefined {\n const explicitPath = process.env.MCP_SCRAPER_KEY_PATH?.trim()\n const paths = [explicitPath, join(homedir(), '.mcp-scraper-key')].filter(Boolean) as string[]\n for (const path of paths) {\n try {\n const value = readFileSync(path, 'utf8').trim()\n if (value) return value\n } catch {}\n }\n return undefined\n}\n\nconst apiKey = (\n process.env.MCP_SCRAPER_API_KEY ??\n process.env.MCP_SCRAPER_KEY ??\n process.env.MCP_API_KEY ??\n readApiKeyFile()\n)?.trim()\nif (!apiKey) {\n process.stderr.write('MCP_SCRAPER_API_KEY env var or ~/.mcp-scraper-key is required\\n')\n process.exit(1)\n}\n\nconst baseUrl = process.env.MCP_SCRAPER_BASE_URL?.trim() || process.env.MCP_BASE_URL?.trim() || 'https://mcpscraper.dev'\nconst executor = new HttpMcpToolExecutor(baseUrl, apiKey)\nconst server = buildPaaExtractorMcpServer(executor)\nconst transport = new StdioServerTransport()\n\nasync function main() {\n await server.connect(transport)\n}\n\nmain().catch((err) => {\n process.stderr.write(`${err instanceof Error ? err.message : String(err)}\\n`)\n process.exit(1)\n})\n"],"mappings":";;;;;;;;;;AACA,SAAS,oBAAoB;AAC7B,SAAS,eAAe;AACxB,SAAS,YAAY;AACrB,SAAS,4BAA4B;AAIrC,SAAS,iBAAqC;AAC5C,QAAM,eAAe,QAAQ,IAAI,sBAAsB,KAAK;AAC5D,QAAM,QAAQ,CAAC,cAAc,KAAK,QAAQ,GAAG,kBAAkB,CAAC,EAAE,OAAO,OAAO;AAChF,aAAW,QAAQ,OAAO;AACxB,QAAI;AACF,YAAM,QAAQ,aAAa,MAAM,MAAM,EAAE,KAAK;AAC9C,UAAI,MAAO,QAAO;AAAA,IACpB,QAAQ;AAAA,IAAC;AAAA,EACX;AACA,SAAO;AACT;AAEA,IAAM,UACJ,QAAQ,IAAI,uBACZ,QAAQ,IAAI,mBACZ,QAAQ,IAAI,eACZ,eAAe,IACd,KAAK;AACR,IAAI,CAAC,QAAQ;AACX,UAAQ,OAAO,MAAM,iEAAiE;AACtF,UAAQ,KAAK,CAAC;AAChB;AAEA,IAAM,UAAU,QAAQ,IAAI,sBAAsB,KAAK,KAAK,QAAQ,IAAI,cAAc,KAAK,KAAK;AAChG,IAAM,WAAW,IAAI,oBAAoB,SAAS,MAAM;AACxD,IAAM,SAAS,2BAA2B,QAAQ;AAClD,IAAM,YAAY,IAAI,qBAAqB;AAE3C,eAAe,OAAO;AACpB,QAAM,OAAO,QAAQ,SAAS;AAChC;AAEA,KAAK,EAAE,MAAM,CAAC,QAAQ;AACpB,UAAQ,OAAO,MAAM,GAAG,eAAe,QAAQ,IAAI,UAAU,OAAO,GAAG,CAAC;AAAA,CAAI;AAC5E,UAAQ,KAAK,CAAC;AAChB,CAAC;","names":[]}
@@ -38,13 +38,15 @@ function browserServiceProxyId() {
38
38
 
39
39
  // src/schemas.ts
40
40
  var import_zod = require("zod");
41
+ var DEFAULT_PROXY_MODE = "configured";
42
+ var DEFAULT_MAPS_PROXY_MODE = "location";
41
43
  var HarvestOptionsSchema = import_zod.z.object({
42
44
  query: import_zod.z.string().min(1),
43
45
  location: import_zod.z.string().optional(),
44
46
  gl: import_zod.z.string().length(2).default("us"),
45
47
  hl: import_zod.z.string().length(2).default("en"),
46
48
  device: import_zod.z.enum(["desktop", "mobile"]).default("desktop"),
47
- proxyMode: import_zod.z.enum(["location", "configured", "none"]).default("location"),
49
+ proxyMode: import_zod.z.enum(["location", "configured", "none"]).default(DEFAULT_PROXY_MODE),
48
50
  proxyZip: import_zod.z.string().regex(/^\d{5}$/).optional(),
49
51
  debug: import_zod.z.boolean().default(false),
50
52
  depth: import_zod.z.number().int().min(1).max(30).default(3),
@@ -77,7 +79,7 @@ var MapsSearchOptionsSchema = import_zod.z.object({
77
79
  gl: import_zod.z.string().length(2).default("us"),
78
80
  hl: import_zod.z.string().length(2).default("en"),
79
81
  maxResults: import_zod.z.number().int().min(1).max(50).default(10),
80
- proxyMode: import_zod.z.enum(["location", "configured", "none"]).default("location"),
82
+ proxyMode: import_zod.z.enum(["location", "configured", "none"]).default(DEFAULT_MAPS_PROXY_MODE),
81
83
  proxyZip: import_zod.z.string().regex(/^\d{5}$/).optional(),
82
84
  debug: import_zod.z.boolean().default(false),
83
85
  kernelApiKey: import_zod.z.string().optional(),
@@ -2780,7 +2782,7 @@ async function harvest(rawOptions) {
2780
2782
  const signal = getAbortSignal(rawOptions);
2781
2783
  const onAttemptEvent = getAttemptLogSink(rawOptions);
2782
2784
  const requestedProxyMode = raw.proxyMode;
2783
- const proxyMode = requestedProxyMode === "none" ? "none" : requestedProxyMode === "configured" ? "configured" : "location";
2785
+ const proxyMode = requestedProxyMode === "location" || requestedProxyMode === "none" || requestedProxyMode === "configured" ? requestedProxyMode : DEFAULT_PROXY_MODE;
2784
2786
  const kernelApiKey = typeof raw.kernelApiKey === "string" ? raw.kernelApiKey.trim() : browserServiceApiKey();
2785
2787
  const configuredKernelProxyId = typeof raw.kernelProxyId === "string" ? raw.kernelProxyId.trim() : browserServiceProxyId();
2786
2788
  const proxyOpts = {