@gotza02/sequential-thinking 2026.1.31 → 2026.2.1

package/README.md

@@ -1,302 +1,237 @@
-# Sequential Thinking MCP Server
+# Sequential Thinking MCP Server (Extended Edition) 🧠✨
 
-An MCP server implementation that provides a tool for dynamic and reflective problem-solving through a structured thinking process (Tree of Thoughts, Self-Reflexion).
+**MCP Server ที่ช่วยให้ AI "คิดก่อนทำ" อย่างเป็นระบบ พร้อมความสามารถในการค้นหาเว็บ, วิเคราะห์โค้ด และจดจำข้อมูลระยะยาว**
 
-## Features
+โปรเจกต์นี้คือส่วนขยายของ Sequential Thinking ที่เพิ่มเครื่องมือสำคัญเพื่อให้ AI ทำงานเป็น "Autonomous Agent" ได้อย่างสมบูรณ์แบบ ทั้งการวางแผน (Planning), การหาข้อมูล (Research), และการลงมือทำ (Execution)
 
-- **Sequential Analysis**: Break down complex problems into manageable linear steps.
-- **Iterative Reasoning**: Think step-by-step in a structured manner, refining insights in loops.
-- **Tree of Thoughts**: Generate and evaluate multiple options, exploring Conservative, Balanced, and Aggressive strategies.
-- **Self-Critique**: Actively check for risks, biases, and potential errors in the thinking process.
-- **Branch Merging**: Synthesize and combine insights from multiple divergent reasoning paths.
-- **Hypothesis Testing**: Formulate specific hypotheses and verify them against evidence or logic.
-- **Option Evaluation**: Score and weigh different options (`evaluation`) to make informed decisions.
-- **Self-Reflexion**: Review and correct previous thoughts (`reflexion`) to improve accuracy.
-- **Dynamic Adjustment**: Adjust the total number of thoughts dynamically as understanding deepens.
+---
 
-## System Instruction for AI
+## 🔑 Environment Variables (การตั้งค่าตัวแปร)
 
-When connected to this server, you should follow these guidelines to maximize problem-solving effectiveness:
+นี่คือตัวแปรทั้งหมดที่ระบบรองรับ คุณสามารถเลือกตั้งค่าได้ตามฟีเจอร์ที่ต้องการใช้งาน:
 
-1.  **Iterative Thinking**: Use the `sequentialthinking` tool for every complex task. Do not try to provide a final answer immediately. Instead, break the problem into steps, generate hypotheses, and evaluate them.
-2.  **Context Discovery**: Before modifying code, always use `build_project_graph` followed by `get_project_graph_summary` to understand the project architecture. Use `get_file_relationships` to see how specific files are connected.
-3.  **Fact Verification**: Use `web_search` to verify current facts, library versions, or documentation. Use `fetch` to retrieve raw data from external sources when needed.
-4.  **Local Execution**: Use `shell_execute` to run tests, linters, or build commands to verify your changes. Always read files using `read_file` before attempting to write or modify them.
-5.  **Persistence**: The thinking process is saved automatically. You can resume previous sessions by reviewing the `thoughts_history.json` file if needed.
+### 1. Web Search APIs (เลือกอย่างน้อย 1 อย่างเพื่อใช้ `web_search`)
+| Variable Name | Description | Required? |
+|--------------|-------------|-----------|
+| `BRAVE_API_KEY` | สำหรับค้นหาผ่าน Brave Search | ❌ (Optional) |
+| `EXA_API_KEY` | สำหรับค้นหาผ่าน Exa.ai (แนะนำสำหรับงาน Deep Research) | ❌ (Optional) |
+| `GOOGLE_SEARCH_API_KEY` | Google Custom Search API Key | ❌ (Optional) |
+| `GOOGLE_SEARCH_CX` | Google Custom Search Engine ID (CX) | ❌ (Optional) |
 
-## Detailed Tool Guide
+### 2. Storage & Memory (การจัดเก็บข้อมูล)
+| Variable Name | Description | Default Value |
+|--------------|-------------|---------------|
+| `THOUGHTS_STORAGE_PATH` | ไฟล์เก็บประวัติการคิด (Thinking History) | `thoughts_history.json` |
+| `NOTES_STORAGE_PATH` | ไฟล์เก็บความจำระยะยาว (Long-term Notes) | `project_notes.json` |
 
-### 🧠 Cognitive Tools
+### 3. System Behavior (พฤติกรรมระบบ)
+| Variable Name | Description | Default Value |
+|--------------|-------------|---------------|
+| `THOUGHT_DELAY_MS` | เวลาหน่วงระหว่างความคิด (ms) เพื่อกัน Rate Limit | `0` |
+| `DISABLE_THOUGHT_LOGGING`| ปิดการแสดงผล Log สีสวยงามใน Console (`true`/`false`) | `false` |
 
-#### `sequentialthinking`
-The core engine for structured problem-solving. It forces a step-by-step analysis before arriving at a conclusion.
+---
 
-**Inputs:**
-- `thought` (string, required): The content of the current thinking step.
-- `thoughtNumber` (integer, required): Current step number (starts at 1).
-- `totalThoughts` (integer, required): Estimated total steps needed (can be adjusted dynamically).
-- `nextThoughtNeeded` (boolean, required): `true` if you need to think more, `false` only when the final answer is ready.
-- `thoughtType` (enum): The nature of the thought:
-  - `analysis`: Breaking down the problem.
-  - `generation`: Brainstorming solutions.
-  - `evaluation`: Weighing options (use with `score`).
-  - `reflexion`: Reviewing previous thoughts (use with `isRevision`).
-  - `selection`: Choosing a path.
-- `isRevision` (boolean): Set to `true` if you are correcting a previous mistake.
-- `revisesThought` (integer): The thought number you are fixing.
-- `branchFromThought` (integer): The parent thought number if creating a new reasoning branch.
-- `branchId` (string): A name for the new branch.
+## 🚀 Installation & Usage (การติดตั้งและใช้งาน)
 
-**Best Practice:** Use this for ANY non-trivial task. Don't just answer; think first.
+สามารถติดตั้งผ่าน npm ได้โดยตรง:
 
-#### `clear_thought_history`
-Clears the stored thinking history. Use this to start fresh or free up context.
-
-#### `summarize_history`
-Compresses multiple thoughts into a single summary thought. This is essential for long reasoning chains to save token context while preserving the core insights.
-
-**Inputs:**
-- `startIndex` (integer): Start of the range to summarize.
-- `endIndex` (integer): End of the range to summarize.
-- `summary` (string): The summary text that replaces the range.
-
-### 🌐 External Knowledge
-
-#### `web_search`
-Retrieves real-time information from the internet.
-
-**Inputs:**
-- `query` (string, required): What you want to find.
-- `provider` (enum, optional):
-  - `brave`: General web search (Requires `BRAVE_API_KEY`).
-  - `exa`: AI-optimized search for deep content (Requires `EXA_API_KEY`).
-  - `google`: Google Custom Search (Requires `GOOGLE_SEARCH_API_KEY` & `GOOGLE_SEARCH_CX`).
-
-#### `fetch`
-Performs a direct HTTP request to a URL. Useful for getting raw HTML, JSON, or text from a specific source found via search.
-
-**Inputs:**
-- `url` (string, required): The target URL.
-- `method`: `GET` (default), `POST`, `PUT`, `DELETE`.
-- `headers`: JSON object for headers (e.g., `{"Authorization": "Bearer..."}`).
-- `body`: Request body for POST/PUT.
-
-#### `read_webpage`
-Reads a webpage and converts it to clean Markdown, removing ads and navigation. Great for reading articles or documentation to save tokens.
-
-**Inputs:**
-- `url` (string, required): The URL to read.
-
-### 🏗 Codebase Intelligence
-
-#### `build_project_graph`
-**RUN THIS FIRST** when entering a new project. It scans the directory and builds a map of file dependencies using TypeScript AST analysis. Now also extracts **exported symbols** (Functions, Classes, Variables) to provide deeper structural insight.
-
-**Inputs:**
-- `path` (string, optional): Root directory (defaults to `.`).
-
-#### `get_project_graph_summary`
-Get overview of project structure and most referenced files.
-
-#### `get_project_graph_visualization`
-Get a Mermaid Diagram string representing the project's dependency graph. You can render this string in a Markdown viewer that supports Mermaid.
-
-### 🛠 System Operations
-
-#### `read_file`
-Reads the content of a file. Always read a file before editing it to ensure you have the latest context.
-
-**Inputs:**
-- `path` (string, required): File path.
-
-#### `write_file`
-Creates or overwrites a file.
-
-**Inputs:**
-- `path` (string, required): File path.
-- `content` (string, required): The full content to write.
-
-#### `edit_file`
-Replace a specific string in a file with a new string. Use this for surgical edits to avoid overwriting the whole file.
-
-**Inputs:**
-- `path` (string, required): File path.
-- `oldText` (string, required): The exact text segment to replace.
-- `newText` (string, required): The new text to insert.
-- `allowMultiple` (boolean, optional): Allow replacing multiple occurrences (default: false).
-
-#### `manage_notes`
-Manage long-term memory/notes. Use this to save important information, rules, or learnings that should persist across sessions.
-
-**Inputs:**
-- `action` (enum, required): 'add', 'list', 'search', 'update', 'delete'.
-- `title` (string): Title of the note.
-- `content` (string): Content of the note.
-- `tags` (array): Tags for categorization.
-- `searchQuery` (string): Query to search notes.
-- `noteId` (string): ID of the note.
-
-#### `shell_execute`
-Executes a shell command. Use for running tests (`npm test`), building (`npm run build`), or file operations (`ls`, `mkdir`).
-
-**Inputs:**
-- `command` (string, required): The command line string.
-**Warning:** Use with caution. Avoid commands that might delete data or expose secrets.
-
-## Recommended System Instruction
-
-To optimize your AI agent's performance with these tools, we recommend adding the following instructions to its system prompt:
-
-```text
-# Tools & Workflow
-
-1.  **Core Reasoning (`sequentialthinking`)**
-    *   **Mandatory Step:** For any complex query, bug fix, or feature request, you MUST start by using the `sequentialthinking` tool.
-    *   **Methodology:** Break the problem down. If your first hypothesis fails, use the tool again to revise your plan (`isRevision: true`).
-    *   **Goal:** Do not output code or final answers until you have a clear, verified plan.
-
-2.  **Codebase Navigation**
-    *   **Initial Scan:** On start, run `build_project_graph`.
-    *   **Context:** Before reading a file, check its context with `get_file_relationships`. This prevents "hallucinating" imports or breaking existing dependencies.
-
-3.  **External Verification**
-    *   **Docs & Facts:** If you need to use a library you aren't 100% sure about, use `web_search` to check the documentation.
-
-4.  **Safety & Persistence**
-    *   **Files:** Always `read_file` before `write_file`.
-    *   **History:** Your thoughts are saved. If you get stuck, review your previous thoughts.
+```bash
+npm install @gotza02/sequential-thinking
 ```
 
-## Usage
-
-The Sequential Thinking tool is designed for:
-- Breaking down complex problems into steps
-- Planning and design with room for revision
-- Analysis that might need course correction
-- Problems where the full scope might not be clear initially
-- Tasks that need to maintain context over multiple steps
-- Situations where irrelevant information needs to be filtered out
-
-## Configuration
+รองรับทั้ง **Gemini CLI** และ **Claude Desktop**
 
-### Environment Variables
-- `THOUGHT_DELAY_MS`: (Optional) Milliseconds to wait before processing each thought. Default: `0`.
-- `DISABLE_THOUGHT_LOGGING`: (Optional) Set to `true` to hide colored logs.
-- `THOUGHTS_STORAGE_PATH`: (Optional) Path to history file. Default: `thoughts_history.json`.
+### Option A: ใช้งานผ่าน npx (แนะนำสำหรับผู้ใช้ทั่วไป)
+*ไม่ต้องโหลดโค้ด แค่แก้ Config แล้วใช้งานได้เลย*
 
-### Usage with Claude Desktop
+#### 1. สำหรับ Gemini CLI
+แก้ไขไฟล์ `~/.gemini/settings.json` (หรือ `config.json`):
 
-Add this to your `claude_desktop_config.json`. You can configure API keys directly here:
+```json
+{
+  "mcpServers": {
+    "smartagent": {
+      "command": "npx",
+      "args": ["-y", "@gotza02/sequential-thinking"],
+      "env": {
+        "BRAVE_API_KEY": "YOUR_BRAVE_KEY",
+        "EXA_API_KEY": "YOUR_EXA_KEY",
+        "GOOGLE_SEARCH_API_KEY": "YOUR_GOOGLE_KEY",
+        "GOOGLE_SEARCH_CX": "YOUR_GOOGLE_CX",
+        "THOUGHTS_STORAGE_PATH": "thoughts_history.json",
+        "NOTES_STORAGE_PATH": "project_notes.json",
+        "THOUGHT_DELAY_MS": "1000",
+        "DISABLE_THOUGHT_LOGGING": "false"
+      }
+    }
+  }
+}
+```
 
-#### npx
+#### 2. สำหรับ Claude Desktop
+แก้ไขไฟล์ `claude_desktop_config.json`:
 
 ```json
 {
   "mcpServers": {
     "sequential-thinking": {
       "command": "npx",
-      "args": [
-        "-y",
-        "@gotza02/sequential-thinking"
-      ],
+      "args": ["-y", "@gotza02/sequential-thinking"],
       "env": {
-        "BRAVE_API_KEY": "YOUR_BRAVE_API_KEY",
-        "EXA_API_KEY": "YOUR_EXA_API_KEY",
-        "GOOGLE_SEARCH_API_KEY": "YOUR_GOOGLE_SEARCH_API_KEY",
-        "GOOGLE_SEARCH_CX": "YOUR_GOOGLE_SEARCH_CX"
+        "BRAVE_API_KEY": "YOUR_BRAVE_KEY",
+        "EXA_API_KEY": "YOUR_EXA_KEY",
+        "GOOGLE_SEARCH_API_KEY": "YOUR_GOOGLE_KEY",
+        "GOOGLE_SEARCH_CX": "YOUR_GOOGLE_CX",
+        "THOUGHTS_STORAGE_PATH": "thoughts_history.json",
+        "NOTES_STORAGE_PATH": "project_notes.json",
+        "THOUGHT_DELAY_MS": "1000"
       }
     }
   }
 }
 ```
 
-### Usage with VS Code
-
-For quick installation, click one of the installation buttons below...
+---
+
+### Option B: ใช้งานแบบ Local Source (สำหรับนักพัฒนา)
+*สำหรับคนที่ต้องการแก้ไขโค้ด หรือรันจากเครื่องตัวเอง*
+
+1. **Clone & Build:**
+   ```bash
+   git clone <repo_url>
+   cd sequential-thinking
+   npm install
+   npm run build
+   ```
+
+2. **ตั้งค่า Config (ตัวอย่างสำหรับ Gemini CLI):**
+   *เปลี่ยน Path ให้ตรงกับที่อยู่ไฟล์ในเครื่องคุณ*
+
+   ```json
+   {
+     "mcpServers": {
+       "smartagent": {
+         "command": "node",
+         "args": ["/Users/username/projects/sequential-thinking/dist/index.js"],
+         "env": {
+            "BRAVE_API_KEY": "YOUR_BRAVE_KEY",
+            "EXA_API_KEY": "YOUR_EXA_KEY",
+            "GOOGLE_SEARCH_API_KEY": "YOUR_GOOGLE_KEY",
+            "GOOGLE_SEARCH_CX": "YOUR_GOOGLE_CX",
+            "THOUGHTS_STORAGE_PATH": "thoughts_history.json",
+            "NOTES_STORAGE_PATH": "project_notes.json",
+            "THOUGHT_DELAY_MS": "1000",
+            "DISABLE_THOUGHT_LOGGING": "false"
+         }
+       }
+     }
+   }
+   ```
+
+---
+
+## 🛠️ Tools Capability (ความสามารถเครื่องมือ)
+
+### 🧠 1. Cognitive Tools (สมองและการคิด)
+*   **`sequentialthinking`**: เครื่องมือหลัก! ช่วยแตกปัญหาใหญ่เป็นขั้นตอนย่อย (Step-by-step), แตกกิ่งความคิด (Branching), และทบทวนตัวเอง (Reflexion)
+*   **`summarize_history`**: ย่อสรุปประวัติการคิดที่ยาวเหยียดให้สั้นลง
+*   **`clear_thought_history`**: ล้างสมอง เริ่มต้นคิดเรื่องใหม่
+
+### 🌐 2. Web Capabilities (การเข้าถึงอินเทอร์เน็ต)
+*   **`web_search`**: ค้นหาข้อมูลล่าสุด (รองรับ Brave, Exa, Google)
+*   **`read_webpage`**: อ่านเนื้อหาในเว็บแบบ Markdown (ตัดโฆษณาออกให้อัตโนมัติ)
+*   **`fetch`**: ดึงข้อมูล Raw JSON/HTML จาก API
+
+### 🏗️ 3. Codebase Intelligence (ความเข้าใจโค้ด)
+*   **`build_project_graph`**: สแกนโปรเจกต์เพื่อสร้างแผนผังความสัมพันธ์ (Dependency Graph)
+*   **`get_file_relationships`**: ดูว่าไฟล์นี้ถูกใครเรียกใช้บ้าง (ป้องกันการแก้แล้วพัง)
+*   **`search_code`**: ค้นหาโค้ดทั้งโปรเจกต์แบบฉลาด
+
+### 📝 4. Long-term Memory (ความจำระยะยาว)
+*   **`manage_notes`**: บันทึก/อ่าน/แก้ไข ข้อความที่ต้องการให้ AI จำได้ข้าม Session (เช่น กฎของโปรเจกต์, ความชอบของผู้ใช้)
+
+### 💻 5. System Operations (จัดการระบบ)
+*   **`read_file`**: อ่านไฟล์ (ต้องทำก่อนแก้ไฟล์เสมอ)
+*   **`edit_file`**: แก้ไขไฟล์เฉพาะจุด (Search & Replace) ปลอดภัยกว่าเขียนทับ
+*   **`write_file`**: สร้างไฟล์ใหม่ หรือเขียนทับทั้งไฟล์
+*   **`shell_execute`**: รันคำสั่ง Terminal (เช่น `npm test`, `git status`)
+
+---
+
+## 🤖 Recommended System Instruction (คำสั่งระบบที่แนะนำ)
+
+เพื่อประสิทธิภาพสูงสุด ให้ Copy ข้อความด้านล่างนี้ไปใส่ใน **System Prompt** ของ AI Agent ที่คุณใช้งาน:
 
-[![Install with NPX in VS Code](https://img.shields.io/badge/VS_Code-NPM-0098FF?style=flat-square&logo=visualstudiocode&logoColor=white)](https://insiders.vscode.dev/redirect/mcp/install?name=sequentialthinking&config=%7B%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40gotza02%2Fsequential-thinking%22%5D%7D)
+```bash
+# 🤖 System Instruction: Enhanced Sequential Engineer
 
-## Building
+You are an advanced AI Software Engineer enhanced with the **Sequential Thinking MCP Server**. Your goal is to solve complex problems autonomously, accurately, and safely.
 
-```bash
-npm install
-npm run build
-```
+## 🧠 PRIME DIRECTIVE: Sequential Thinking
 
-## Testing
+**Rule #1: NEVER answer complex queries immediately.**
+You MUST use the `sequentialthinking` tool to structure your reasoning process.
 
-```bash
-npm test
-```
+1.  **Analyze:** Break the user's request into atomic requirements.
+2.  **Plan:** Formulate a step-by-step plan.
+3.  **Execute:** Carry out the plan, one step at a time.
+4.  **Reflect:** Critique your own work. If a step fails, use `isRevision: true` to correct your course.
 
-## Recent Updates (v2026.1.31)
-- **New Tools**:
-  - `manage_notes`: Long-term memory system to store and retrieve information across sessions.
+**Constraints:**
+-   Do not output code until you have a clear plan.
+-   If you are unsure, generate a hypothesis and verify it.
 
-## Recent Updates (v2026.1.30)
-- **New Tools**:
-  - `get_project_graph_visualization`: Generate Mermaid diagrams of your project structure.
+## 🏗 Codebase Intelligence Protocol
 
-## Recent Updates (v2026.1.29)
-- **New Tools**:
-  - `edit_file`: Surgically replace text in files without overwriting the entire content.
+**On Start:**
+1.  **Map the Territory:** Run `build_project_graph` immediately to understand the project structure.
+2.  **Summarize:** Run `get_project_graph_summary` to identify key files.
 
-## Recent Updates (v2026.1.28)
-- **Robustness**:
-  - Implemented **Atomic Writes** for `thoughts_history.json` to prevent file corruption.
-  - Added **Internal Locking** to handle concurrent save requests gracefully.
-  - Added **API Retry Logic** with exponential backoff for all search and web tools (handles HTTP 429/5xx).
-  - Improved HTTP requests with browser-like headers (User-Agent) to reduce blocking.
-- **New Tools**:
-  - `summarize_history`: Archive and condense long reasoning chains.
-- **Graph Enhancements**:
-  - Added **Symbol Extraction**: The project graph now tracks exported functions, classes, and variables.
+**Before Editing:**
+1.  **Context Check:** Run `get_file_relationships` to see what depends on the file you are changing.
+2.  **Read First:** ALWAYS run `read_file` to get the *current* content. Never rely on memory or assumptions.
 
-## Recent Updates (v2026.1.27)
-- **New Tools**:
-  - `read_webpage`: Convert webpages to Markdown for efficient reading.
-  - `search_code`: Recursive text search in code files.
-  - `clear_thought_history`: Reset the thinking process.
+## 🛠 File Operations Protocol
 
-## Recent Updates (v2026.1.26)
+-   **Small Changes:** Use `edit_file` for surgical replacements. This minimizes the risk of context loss or accidental deletions.
+-   **New/Large Files:** Use `write_file`.
+-   **Verification:** After editing, ALWAYS verify the syntax or logic (e.g., run `npm run build` or `npm test` using `shell_execute`).
 
-- **Rate Limiting**:
-  - Added `THOUGHT_DELAY_MS` environment variable to introduce a delay between thought steps. This helps prevent request flooding and rate limit issues.
+## 🌐 External Knowledge Protocol
 
-## Recent Updates (v2026.1.24)
+-   **Unknown Libs:** If you see a library you don't know, use `web_search` to find its docs.
+-   **Reading:** Use `read_webpage` to ingest documentation efficiently (markdown format).
+-   **Errors:** If you hit a cryptic error, search for it.
 
-- **Bug Fixes**:
-  - Fixed `get_file_relationships` to correctly resolve absolute imports and imports from project root (e.g., `src/utils`), ensuring the dependency graph is complete for projects using path aliases or absolute paths.
+## 📝 Memory & Persistence
 
-## Recent Updates (v2026.1.22)
+-   **Long-Term:** Use `manage_notes` to save architectural decisions, user preferences, or "lessons learned" that should survive this session.
+-   **Session:** Your thought process is automatically saved. If you crash or restart, review `thoughts_history.json`.
 
-- **Environment Variables**:
-  - Renamed Google Search environment variables to `GOOGLE_SEARCH_API_KEY` and `GOOGLE_SEARCH_CX` to avoid conflicts and improve clarity.
+## 🔄 The Golden Workflow
 
-## Recent Updates (v2026.1.21)
+1.  **Discovery:** `build_project_graph` -> `sequentialthinking` (Plan)
+2.  **Research:** `web_search` -> `read_webpage`
+3.  **Implementation:** `read_file` -> `sequentialthinking` (Refine) -> `edit_file`
+4.  **Verification:** `shell_execute` (Test/Build)
+5.  **Completion:** Final answer with summary of changes.
+```
 
-- **Performance & Accuracy**:
-  - Replaced Regex-based code analysis with **TypeScript Compiler API (AST)** for 100% accurate import/export detection.
-  - Improved `web_search` robustness and error handling.
-- **Persistence**:
-  - Implemented **File-based Persistence** for the thinking process. Your thoughts are now saved to `thoughts_history.json` automatically.
-  - Switched to **Asynchronous File I/O** to prevent server blocking.
-- **Bug Fixes**:
-  - Fixed duplicate import entries in the project graph.
-  - Resolved memory growth issues in long-running sessions.
+---
 
-## Recent Updates (v2026.1.20)
+## 📦 Development
 
-- **New Features**:
-  - Added support for **Google Custom Search** in the `web_search` tool. (Requires `GOOGLE_API_KEY` and `GOOGLE_CX`).
+```bash
+# Install dependencies
+npm install
 
-## Recent Updates (v2026.1.18)
+# Build the project
+npm run build
 
-- **Bug Fixes**:
-  - Fixed an issue where commented-out imports were incorrectly parsed by the graph analyzer.
-  - Resolved a branching logic issue where branch IDs could collide.
-  - Fixed version mismatch between package.json and server instance.
+# Run tests
+npm test
+```
 
 ## License
-
-This MCP server is licensed under the MIT License.
+MIT