agent-avatar-mcp 1.0.1 → 1.1.0

package/README.md

@@ -21,9 +21,7 @@ Each AI agent has a **DNA** — a detailed description of their human physical a
 ## Prerequisites
 
 - **Node.js** >= 18
-- **[Nano Banana Pro](https://github.com/RodrigoFlorencio86)** — Python script for image generation via Google Gemini
-- **Google Gemini API Key** (`GEMINI_API_KEY`)
-- **`uv`** (recommended) or Python with `google-genai` and `pillow` installed
+- **Google Gemini API Key** (`GEMINI_API_KEY`) — the only external dependency
 
 ---
 
@@ -68,10 +66,9 @@ Each AI agent has a **DNA** — a detailed description of their human physical a
 ### Environment variables
 
 | Variable | Required | Description |
-|---|---|---|
+| --- | --- | --- |
 | `AGENT_NAME` | Recommended | Agent name/handle. If omitted and only one agent is configured, it is auto-detected. |
-| `NANO_BANANA_SCRIPT` | Yes | Absolute path to `generate_image.py` from Nano Banana Pro |
-| `GEMINI_API_KEY` | Yes | Google Gemini API key used by the image generator |
+| `GEMINI_API_KEY` | Yes | Google Gemini API key for image generation |
 | `AVATAR_OUTPUT_DIR` | No | Where generated images are saved. Default: `~/.agent-avatar/generated/` |
 
 ---
@@ -80,27 +77,30 @@ Each AI agent has a **DNA** — a detailed description of their human physical a
 
 ### Initial setup (run once)
 
-```
+```text
 1. read_identity_files   →  reads your soul.md / persona files to extract appearance
 2. save_dna              →  saves your human visual DNA
 3. generate_reference    →  generates reference portrait (front, neutral, three_quarter, side)
 ```
 
 Or, if you already have a photo:
-```
+
+```text
 3. set_reference_image   →  registers an existing photo as reference for a given angle
 ```
 
 ### Generating photos
 
 **Normal photo:**
-```
+
+```text
 generate_image
   scene: "selfie at the beach at sunset"
 ```
 
 **Sponsored post (agent + product):**
-```
+
+```text
 generate_image
   scene: "holding the bottle in a luxury bathroom mirror"
   product_name: "Chanel No.5"
@@ -113,7 +113,7 @@ generate_image
 ## Available tools
 
 | Tool | Description |
-|---|---|
+| --- | --- |
 | `read_identity_files` | Reads soul.md / persona files to extract your physical appearance |
 | `save_dna` | Saves your visual DNA (human appearance only — never robotic) |
 | `show_dna` | Displays your current DNA and reference image status |
@@ -128,7 +128,7 @@ generate_image
 ## Supported scenarios
 
 | Scenario | Supported |
-|---|---|
+| --- | --- |
 | Agent alone in any scene | ✅ |
 | Agent featuring a physical product | ✅ |
 | Two agents in the same scene | ⚠️ Approximate (no precise likeness for secondary person) |

package/dist/generate.js

@@ -1,16 +1,38 @@
-import { spawn } from "child_process";
-import { existsSync, mkdirSync } from "fs";
+import { GoogleGenAI } from "@google/genai";
+import { readFileSync, writeFileSync, existsSync, mkdirSync } from "fs";
 import { join } from "path";
 import { homedir } from "os";
-const SCRIPT_PATH = process.env.NANO_BANANA_SCRIPT ??
-    join(homedir(), ".openclaw", "skills", "nano-banana-pro", "scripts", "generate_image.py");
 const OUTPUT_DIR = process.env.AVATAR_OUTPUT_DIR ??
     join(homedir(), ".agent-avatar", "generated");
+const MODEL = "gemini-3-pro-image-preview";
 export function ensureOutputDir() {
     if (!existsSync(OUTPUT_DIR))
         mkdirSync(OUTPUT_DIR, { recursive: true });
     return OUTPUT_DIR;
 }
+function getClient() {
+    const apiKey = process.env.GEMINI_API_KEY;
+    if (!apiKey) {
+        throw new Error("GEMINI_API_KEY environment variable is required.\n" +
+            "Set it in your MCP server config under 'env'.");
+    }
+    return new GoogleGenAI({ apiKey });
+}
+function imageToInlinePart(imagePath) {
+    const ext = imagePath.toLowerCase().split(".").pop() ?? "png";
+    const mimeTypes = {
+        png: "image/png",
+        jpg: "image/jpeg",
+        jpeg: "image/jpeg",
+        webp: "image/webp",
+    };
+    return {
+        inlineData: {
+            mimeType: mimeTypes[ext] ?? "image/png",
+            data: readFileSync(imagePath).toString("base64"),
+        },
+    };
+}
 export function buildConsistencyPrompt(dna, sceneDescription, hasReference, product) {
     const productBlock = product
         ? [
@@ -32,7 +54,6 @@ export function buildConsistencyPrompt(dna, sceneDescription, hasReference, prod
             productBlock,
         ].join("\n");
     }
-    // First generation — full DNA description
     return [
         `Ultra-realistic portrait photography. No artistic style. No illustration.`,
         ``,
@@ -51,47 +72,31 @@ export function buildConsistencyPrompt(dna, sceneDescription, hasReference, prod
     ].join("\n");
 }
 export async function generateImage(prompt, outputFilename, referenceImages = []) {
-    if (!existsSync(SCRIPT_PATH)) {
-        throw new Error(`Nano Banana Pro script not found at: ${SCRIPT_PATH}\n` +
-            `Set NANO_BANANA_SCRIPT env var to the correct path.`);
-    }
+    const client = getClient();
     const outDir = ensureOutputDir();
     const outputPath = join(outDir, outputFilename);
-    // Try uv first (handles inline script dependencies), fall back to python directly
-    // if uv is not in PATH (packages must already be installed in that case).
-    const uvAvailable = await new Promise((res) => {
-        const check = spawn("uv", ["--version"], { env: process.env });
-        check.on("close", (code) => res(code === 0));
-        check.on("error", () => res(false));
-    });
-    const [cmd, args] = uvAvailable
-        ? ["uv", ["run", SCRIPT_PATH, "--prompt", prompt, "--filename", outputPath, "--resolution", "1K", ...referenceImages.flatMap((img) => ["-i", img])]]
-        : ["python", [SCRIPT_PATH, "--prompt", prompt, "--filename", outputPath, "--resolution", "1K", ...referenceImages.flatMap((img) => ["-i", img])]];
-    return new Promise((resolve, reject) => {
-        const proc = spawn(cmd, args, { env: process.env });
-        let mediaPath = "";
-        let stderr = "";
-        proc.stdout.on("data", (data) => {
-            const line = data.toString();
-            if (line.includes("MEDIA:")) {
-                mediaPath = line.replace("MEDIA:", "").trim();
-            }
-        });
-        proc.stderr.on("data", (data) => {
-            stderr += data.toString();
-        });
-        proc.on("close", (code) => {
-            if (code !== 0) {
-                reject(new Error(`Image generation failed (exit ${code}):\n${stderr}`));
-            }
-            else {
-                resolve(mediaPath || outputPath);
-            }
-        });
-        proc.on("error", (err) => {
-            reject(new Error(`Failed to spawn image generator: ${err.message}\nTry installing uv: winget install astral-sh.uv`));
-        });
+    // Build parts: reference images first (anchor), then prompt text
+    const parts = [
+        ...referenceImages.map(imageToInlinePart),
+        { text: prompt },
+    ];
+    const response = await client.models.generateContent({
+        model: MODEL,
+        contents: [{ role: "user", parts }],
+        config: {
+            responseModalities: ["IMAGE"],
+            imageConfig: { imageSize: "1K" },
+        },
     });
+    const responseParts = response.candidates?.[0]?.content?.parts ?? [];
+    for (const part of responseParts) {
+        if (part.inlineData?.data) {
+            const imageBuffer = Buffer.from(part.inlineData.data, "base64");
+            writeFileSync(outputPath, imageBuffer);
+            return outputPath;
+        }
+    }
+    throw new Error("No image was generated in the response. Check your GEMINI_API_KEY and model availability.");
 }
 export function makeFilename(agentName, scene) {
     const slug = scene.toLowerCase().replace(/[^a-z0-9]/g, "-").slice(0, 30);

package/package.json

@@ -1,12 +1,15 @@
 {
   "name": "agent-avatar-mcp",
-  "version": "1.0.1",
+  "version": "1.1.0",
   "description": "MCP Server — visual identity and self-portrait generation for AI agents",
   "type": "module",
   "bin": {
     "agent-avatar-mcp": "dist/index.js"
   },
-  "files": ["dist", "README.md"],
+  "files": [
+    "dist",
+    "README.md"
+  ],
   "scripts": {
     "build": "tsc",
     "dev": "tsx src/index.ts",
@@ -15,13 +18,16 @@
     "prepublishOnly": "npm run build"
   },
   "dependencies": {
+    "@google/genai": "^1.45.0",
     "@modelcontextprotocol/sdk": "^1.5.0"
   },
   "devDependencies": {
-    "typescript": "^5.4.0",
     "@types/node": "^20.0.0",
-    "tsx": "^4.0.0"
+    "tsx": "^4.0.0",
+    "typescript": "^5.4.0"
+  },
+  "engines": {
+    "node": ">=18"
   },
-  "engines": { "node": ">=18" },
   "license": "MIT"
 }