feat: Add PDF text extraction and update MCP read_file to support documents

app/api/documents/process/route.ts

@@ -113,12 +113,24 @@ export async function POST(request: NextRequest) {
         break;
 
       case 'pdf':
-        content = {
-          type: 'pdf',
-          fileName,
-          size: fileBuffer.length,
-          message: 'PDF processing requires additional libraries for text extraction'
-        };
+        try {
+          const pdf = require('pdf-parse');
+          const data = await pdf(fileBuffer);
+          content = {
+            type: 'pdf',
+            text: data.text,
+            info: data.info,
+            metadata: data.metadata,
+            version: data.version,
+            numpages: data.numpages
+          };
+        } catch (error) {
+          content = {
+            type: 'pdf',
+            error: 'Failed to process PDF document',
+            details: error
+          };
+        }
         break;
 
       case 'pptx':

mcp-server.js

@@ -143,8 +143,6 @@ class ReubenOSMCPServer {
                           type: 'array',
                           items: { type: 'string' }
                         },
-                        correctAnswer: { type: ['string', 'number', 'boolean'] },
-                        explanation: { type: 'string' },
                         points: { type: 'number' },
                       },
                       required: ['id', 'question', 'type'],
@@ -229,6 +227,50 @@ class ReubenOSMCPServer {
         };
       }
 
+      const ext = fileName.split('.').pop().toLowerCase();
+      const isDocument = ['pdf', 'docx', 'xlsx', 'xls', 'pptx'].includes(ext);
+
+      if (isDocument) {
+        // Use document processing endpoint
+        const processUrl = `${BASE_URL}/api/documents/process`;
+        const response = await fetch(processUrl, {
+          method: 'POST',
+          headers: { 'Content-Type': 'application/json' },
+          body: JSON.stringify({
+            fileName,
+            key: passkey,
+            isPublic,
+            operation: 'read'
+          })
+        });
+
+        const data = await response.json();
+
+        if (response.ok && data.success) {
+          let textContent = '';
+          if (data.content.text) {
+            textContent = data.content.text;
+          } else if (data.content.sheets) {
+            textContent = JSON.stringify(data.content.sheets, null, 2);
+          } else {
+            textContent = JSON.stringify(data.content, null, 2);
+          }
+
+          return {
+            content: [
+              {
+                type: 'text',
+                text: `📄 Content of ${fileName} (${data.content.type}):\n\n${textContent}`,
+              },
+            ],
+          };
+        } else {
+          return {
+            content: [{ type: 'text', text: `❌ Failed to process document: ${data.error || 'Unknown error'}` }],
+          };
+        }
+      }
+
       const url = new URL(API_ENDPOINT);
       if (passkey) url.searchParams.set('passkey', passkey);
       if (isPublic) url.searchParams.set('isPublic', 'true');

package-lock.json

@@ -26,6 +26,7 @@
         "next": "16.0.1",
         "node-fetch": "^3.3.2",
         "officegen": "^0.6.5",
+        "pdf-parse": "^2.4.5",
         "pdfkit": "^0.17.2",
         "puppeteer-core": "^24.30.0",
         "react": "19.2.0",
@@ -9487,6 +9488,210 @@
         "url": "https://opencollective.com/express"
       }
     },
+    "node_modules/pdf-parse": {
+      "version": "2.4.5",
+      "resolved": "https://registry.npmjs.org/pdf-parse/-/pdf-parse-2.4.5.tgz",
+      "integrity": "sha512-mHU89HGh7v+4u2ubfnevJ03lmPgQ5WU4CxAVmTSh/sxVTEDYd1er/dKS/A6vg77NX47KTEoihq8jZBLr8Cxuwg==",
+      "license": "Apache-2.0",
+      "dependencies": {
+        "@napi-rs/canvas": "0.1.80",
+        "pdfjs-dist": "5.4.296"
+      },
+      "bin": {
+        "pdf-parse": "bin/cli.mjs"
+      },
+      "engines": {
+        "node": ">=20.16.0 <21 || >=22.3.0"
+      },
+      "funding": {
+        "type": "github",
+        "url": "https://github.com/sponsors/mehmet-kozan"
+      }
+    },
+    "node_modules/pdf-parse/node_modules/@napi-rs/canvas": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas/-/canvas-0.1.80.tgz",
+      "integrity": "sha512-DxuT1ClnIPts1kQx8FBmkk4BQDTfI5kIzywAaMjQSXfNnra5UFU9PwurXrl+Je3bJ6BGsp/zmshVVFbCmyI+ww==",
+      "license": "MIT",
+      "workspaces": [
+        "e2e/*"
+      ],
+      "engines": {
+        "node": ">= 10"
+      },
+      "optionalDependencies": {
+        "@napi-rs/canvas-android-arm64": "0.1.80",
+        "@napi-rs/canvas-darwin-arm64": "0.1.80",
+        "@napi-rs/canvas-darwin-x64": "0.1.80",
+        "@napi-rs/canvas-linux-arm-gnueabihf": "0.1.80",
+        "@napi-rs/canvas-linux-arm64-gnu": "0.1.80",
+        "@napi-rs/canvas-linux-arm64-musl": "0.1.80",
+        "@napi-rs/canvas-linux-riscv64-gnu": "0.1.80",
+        "@napi-rs/canvas-linux-x64-gnu": "0.1.80",
+        "@napi-rs/canvas-linux-x64-musl": "0.1.80",
+        "@napi-rs/canvas-win32-x64-msvc": "0.1.80"
+      }
+    },
+    "node_modules/pdf-parse/node_modules/@napi-rs/canvas-android-arm64": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-android-arm64/-/canvas-android-arm64-0.1.80.tgz",
+      "integrity": "sha512-sk7xhN/MoXeuExlggf91pNziBxLPVUqF2CAVnB57KLG/pz7+U5TKG8eXdc3pm0d7Od0WreB6ZKLj37sX9muGOQ==",
+      "cpu": [
+        "arm64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "android"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/pdf-parse/node_modules/@napi-rs/canvas-darwin-arm64": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-darwin-arm64/-/canvas-darwin-arm64-0.1.80.tgz",
+      "integrity": "sha512-O64APRTXRUiAz0P8gErkfEr3lipLJgM6pjATwavZ22ebhjYl/SUbpgM0xcWPQBNMP1n29afAC/Us5PX1vg+JNQ==",
+      "cpu": [
+        "arm64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "darwin"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/pdf-parse/node_modules/@napi-rs/canvas-darwin-x64": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-darwin-x64/-/canvas-darwin-x64-0.1.80.tgz",
+      "integrity": "sha512-FqqSU7qFce0Cp3pwnTjVkKjjOtxMqRe6lmINxpIZYaZNnVI0H5FtsaraZJ36SiTHNjZlUB69/HhxNDT1Aaa9vA==",
+      "cpu": [
+        "x64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "darwin"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/pdf-parse/node_modules/@napi-rs/canvas-linux-arm-gnueabihf": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-arm-gnueabihf/-/canvas-linux-arm-gnueabihf-0.1.80.tgz",
+      "integrity": "sha512-eyWz0ddBDQc7/JbAtY4OtZ5SpK8tR4JsCYEZjCE3dI8pqoWUC8oMwYSBGCYfsx2w47cQgQCgMVRVTFiiO38hHQ==",
+      "cpu": [
+        "arm"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/pdf-parse/node_modules/@napi-rs/canvas-linux-arm64-gnu": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-arm64-gnu/-/canvas-linux-arm64-gnu-0.1.80.tgz",
+      "integrity": "sha512-qwA63t8A86bnxhuA/GwOkK3jvb+XTQaTiVML0vAWoHyoZYTjNs7BzoOONDgTnNtr8/yHrq64XXzUoLqDzU+Uuw==",
+      "cpu": [
+        "arm64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/pdf-parse/node_modules/@napi-rs/canvas-linux-arm64-musl": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-arm64-musl/-/canvas-linux-arm64-musl-0.1.80.tgz",
+      "integrity": "sha512-1XbCOz/ymhj24lFaIXtWnwv/6eFHXDrjP0jYkc6iHQ9q8oXKzUX1Lc6bu+wuGiLhGh2GS/2JlfORC5ZcXimRcg==",
+      "cpu": [
+        "arm64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/pdf-parse/node_modules/@napi-rs/canvas-linux-riscv64-gnu": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-riscv64-gnu/-/canvas-linux-riscv64-gnu-0.1.80.tgz",
+      "integrity": "sha512-XTzR125w5ZMs0lJcxRlS1K3P5RaZ9RmUsPtd1uGt+EfDyYMu4c6SEROYsxyatbbu/2+lPe7MPHOO/0a0x7L/gw==",
+      "cpu": [
+        "riscv64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/pdf-parse/node_modules/@napi-rs/canvas-linux-x64-gnu": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-x64-gnu/-/canvas-linux-x64-gnu-0.1.80.tgz",
+      "integrity": "sha512-BeXAmhKg1kX3UCrJsYbdQd3hIMDH/K6HnP/pG2LuITaXhXBiNdh//TVVVVCBbJzVQaV5gK/4ZOCMrQW9mvuTqA==",
+      "cpu": [
+        "x64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/pdf-parse/node_modules/@napi-rs/canvas-linux-x64-musl": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-linux-x64-musl/-/canvas-linux-x64-musl-0.1.80.tgz",
+      "integrity": "sha512-x0XvZWdHbkgdgucJsRxprX/4o4sEed7qo9rCQA9ugiS9qE2QvP0RIiEugtZhfLH3cyI+jIRFJHV4Fuz+1BHHMg==",
+      "cpu": [
+        "x64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "linux"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
+    "node_modules/pdf-parse/node_modules/@napi-rs/canvas-win32-x64-msvc": {
+      "version": "0.1.80",
+      "resolved": "https://registry.npmjs.org/@napi-rs/canvas-win32-x64-msvc/-/canvas-win32-x64-msvc-0.1.80.tgz",
+      "integrity": "sha512-Z8jPsM6df5V8B1HrCHB05+bDiCxjE9QA//3YrkKIdVDEwn5RKaqOxCJDRJkl48cJbylcrJbW4HxZbTte8juuPg==",
+      "cpu": [
+        "x64"
+      ],
+      "license": "MIT",
+      "optional": true,
+      "os": [
+        "win32"
+      ],
+      "engines": {
+        "node": ">= 10"
+      }
+    },
     "node_modules/pdfjs-dist": {
       "version": "5.4.296",
       "resolved": "https://registry.npmjs.org/pdfjs-dist/-/pdfjs-dist-5.4.296.tgz",

package.json

@@ -30,6 +30,7 @@
     "next": "16.0.1",
     "node-fetch": "^3.3.2",
     "officegen": "^0.6.5",
+    "pdf-parse": "^2.4.5",
     "pdfkit": "^0.17.2",
     "puppeteer-core": "^24.30.0",
     "react": "19.2.0",