@arcede/air-mcp - npm Package Compare versions

Comparing version 0.1.0 to 0.2.0

dist/server.js

 #!/usr/bin/env node
 "use strict";
+var __create = Object.create;
+var __defProp = Object.defineProperty;
+var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
+var __getOwnPropNames = Object.getOwnPropertyNames;
+var __getProtoOf = Object.getPrototypeOf;
+var __hasOwnProp = Object.prototype.hasOwnProperty;
+var __copyProps = (to, from, except, desc) => {
+  if (from && typeof from === "object" || typeof from === "function") {
+    for (let key of __getOwnPropNames(from))
+      if (!__hasOwnProp.call(to, key) && key !== except)
+        __defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
+  }
+  return to;
+};
+var __toESM = (mod, isNodeMode, target) => (target = mod != null ? __create(__getProtoOf(mod)) : {}, __copyProps(
+  // If the importer is in node compatibility mode or this is not an ESM
+  // file that has been converted to a CommonJS file using a Babel-
+  // compatible transform (i.e. "__esModule" has not been set), then set
+  // "default" to the CommonJS "module.exports" for node compatibility.
+  isNodeMode || !mod || !mod.__esModule ? __defProp(target, "default", { value: mod, enumerable: true }) : target,
+  mod
+));
 
@@ -48,8 +70,12 @@ // src/server.ts
     url: import_zod.z.string().url().describe("The URL to extract data from"),
-    force: import_zod.z.boolean().optional().describe("Bypass cache for fresh extraction (costs 1.0 credit vs 0.1 for cached)")
+    force: import_zod.z.boolean().optional().describe("Bypass cache for fresh extraction (costs 1.0 credit vs 0.1 for cached)"),
+    full_text: import_zod.z.boolean().optional().describe("Return the full page plaintext in content.text (default: false). Useful for document import pipelines.")
   },
-  async ({ url, force }) => {
+  async ({ url, force, full_text }) => {
+    const options = {};
+    if (force) options.force = true;
+    if (full_text) options.fullText = true;
     const result = await apiRequest("POST", "/v1/extract", {
       url,
-      options: { force: force || false }
+      options
     });
@@ -66,3 +92,3 @@ if (!result.success) {
     const data = result.data;
-    const summary = [
+    const lines = [
       `# ${data.title}`,
@@ -79,7 +105,11 @@ data.description ? `
 Credits used: ${result.credits_used} | Remaining: ${result.credits_remaining}`
-    ].filter(Boolean).join("\n");
-    return {
-      content: [
-        { type: "text", text: summary },
-        { type: "text", text: `
+    ].filter(Boolean);
+    if (full_text && data.content?.text) {
+      lines.push("", "## Full Text", "", data.content.text);
+    }
+    const contentBlocks = [
+      { type: "text", text: lines.join("\n") }
+    ];
+    if (!full_text) {
+      contentBlocks.push({ type: "text", text: `
 
@@ -89,5 +119,5 @@ ## Raw Data
 ${JSON.stringify(data, null, 2)}
-\`\`\`` }
-      ]
-    };
+\`\`\`` });
+    }
+    return { content: contentBlocks };
   }
@@ -191,2 +221,103 @@ );
 );
+server.tool(
+  "extract_content",
+  "Extract text from a file (PDF, DOCX, PPTX, XLSX, CSV, TXT, MD, HTML, EML). Returns structured sections and full text. Any agent can use this \u2014 no browser needed. Use for document import: extract_content \u2192 research_import.",
+  {
+    file_url: import_zod.z.string().optional().describe("URL to fetch the file from (HTTP/HTTPS). Provide file_url or file_path, not both."),
+    file_path: import_zod.z.string().optional().describe("Local file path (for desktop agents). Provide file_url or file_path, not both."),
+    force_ocr: import_zod.z.boolean().optional().describe("Force OCR for scanned PDFs (default: false)")
+  },
+  async ({ file_url, file_path, force_ocr }) => {
+    if (!file_url && !file_path) {
+      return {
+        content: [{ type: "text", text: "Error: Provide either file_url or file_path." }],
+        isError: true
+      };
+    }
+    let fileBlob;
+    let fileName;
+    if (file_url) {
+      try {
+        const resp = await fetch(file_url, { signal: AbortSignal.timeout(3e4) });
+        if (!resp.ok) {
+          return {
+            content: [{ type: "text", text: `Failed to fetch file: ${resp.status} ${resp.statusText}` }],
+            isError: true
+          };
+        }
+        fileBlob = await resp.blob();
+        fileName = new URL(file_url).pathname.split("/").pop() || "document";
+      } catch (err) {
+        return {
+          content: [{ type: "text", text: `Failed to fetch file: ${err?.message || "Unknown error"}` }],
+          isError: true
+        };
+      }
+    } else {
+      try {
+        const { promises: fsp } = await import("fs");
+        const path = await import("path");
+        const buffer = await fsp.readFile(file_path);
+        fileBlob = new Blob([buffer]);
+        fileName = path.basename(file_path);
+      } catch (err) {
+        return {
+          content: [{ type: "text", text: `Failed to read file: ${err?.message || "Unknown error"}` }],
+          isError: true
+        };
+      }
+    }
+    const formData = new FormData();
+    formData.append("file", fileBlob, fileName);
+    if (force_ocr) formData.append("force_ocr", "true");
+    let result;
+    try {
+      const resp = await fetch(`${API_BASE}/v1/extract-content`, {
+        method: "POST",
+        headers: { "Authorization": `Bearer ${API_KEY}` },
+        body: formData,
+        signal: AbortSignal.timeout(12e4)
+      });
+      try {
+        result = await resp.json();
+      } catch {
+        return {
+          content: [{ type: "text", text: `Extraction failed: API returned ${resp.status} with non-JSON response` }],
+          isError: true
+        };
+      }
+    } catch (err) {
+      return {
+        content: [{ type: "text", text: `Extraction failed: ${err?.message || "Service unavailable"}` }],
+        isError: true
+      };
+    }
+    if (!result.success) {
+      return {
+        content: [{ type: "text", text: `Extraction failed: ${result.error || result.message}` }],
+        isError: true
+      };
+    }
+    const data = result.data;
+    const diag = data.diagnostics;
+    const lines = [
+      `# ${data.title || fileName}`,
+      "",
+      `Source: ${file_url || file_path}`,
+      `Parser: ${diag?.extractionMethod || "unknown"}`,
+      `Confidence: ${diag?.confidenceScore ? (diag.confidenceScore * 100).toFixed(0) + "%" : "unknown"}`,
+      `Sections: ${diag?.itemsExtracted || 0}`,
+      `Time: ${diag?.extractionTimeMs || 0}ms`
+    ];
+    if (data.metadata?.pageCount) lines.push(`Pages: ${data.metadata.pageCount}`);
+    if (data.metadata?.wordCount) lines.push(`Words: ${data.metadata.wordCount}`);
+    if (result.credits_used !== void 0) {
+      lines.push(`Credits: ${result.credits_used} used | ${result.credits_remaining ?? "?"} remaining`);
+    }
+    if (data.content?.text) {
+      lines.push("", "## Full Text", "", data.content.text);
+    }
+    return { content: [{ type: "text", text: lines.join("\n") }] };
+  }
+);
 server.resource(
@@ -204,4 +335,5 @@ "api-status",
       "Endpoints:",
-      "  POST /v1/extract        \u2014 Extract structured data from a URL (1.0 credits)",
-      "  POST /v1/capabilities   \u2014 Query site capabilities (0.25 credits)",
+      "  POST /v1/extract         \u2014 Extract structured data from a URL (1.0 credits)",
+      "  POST /v1/extract-content \u2014 Extract text from files (PDF, DOCX, etc.)",
+      "  POST /v1/capabilities    \u2014 Query site capabilities (0.25 credits)",
       "",
@@ -208,0 +340,0 @@ "Pricing:",

package.json

 {
   "name": "@arcede/air-mcp",
-  "version": "0.1.0",
+  "version": "0.2.0",
   "description": "MCP server for the Agent Internet Runtime — extract web data and query site capabilities from any AI coding tool",
@@ -14,19 +14,33 @@ "bin": {
   "dependencies": {
-    "@modelcontextprotocol/sdk": "^1.0.0",
-    "zod": "^3.23.0"
+    "@modelcontextprotocol/sdk": "^1.28.0",
+    "zod": "^3.25.76"
   },
   "devDependencies": {
-    "tsup": "^8.0.0",
-    "tsx": "^4.7.0",
-    "typescript": "^5.3.0",
-    "@types/node": "^20.11.0"
+    "tsup": "^8.5.1",
+    "tsx": "^4.21.0",
+    "typescript": "^5.9.3",
+    "@types/node": "^20.19.37"
   },
   "keywords": [
-    "mcp", "model-context-protocol", "air", "extract", "capabilities",
-    "web-extraction", "ai-agent", "agent-internet-runtime",
-    "claude-code", "cursor", "windsurf"
+    "mcp",
+    "model-context-protocol",
+    "air",
+    "extract",
+    "capabilities",
+    "web-extraction",
+    "ai-agent",
+    "agent-internet-runtime",
+    "claude-code",
+    "cursor",
+    "windsurf"
   ],
   "license": "MIT",
-  "engines": { "node": ">=18" },
-  "files": ["dist/", "README.md", "LICENSE"]
+  "engines": {
+    "node": ">=18"
+  },
+  "files": [
+    "dist/",
+    "README.md",
+    "LICENSE"
+  ]
 }

No alert changes

Improved metrics

Total package byte prevSize

16710

51.22%

Lines of code

357

58.67%

Worsened metrics

Number of medium supply chain risk alerts

3

200%

Dependency changes

• Updated

  @modelcontextprotocol/sdk@^1.28.0

• Updated

  zod@^3.25.76