Merge branch 'main' into main

Author: amornpan

README.md

@@ -226,7 +226,7 @@ Official integrations are maintained by companies building production ready MCP
 - <img height="12" width="12" src="https://memgraph.com/favicon.png" alt="Memgraph Logo" /> **[Memgraph](https://github.com/memgraph/mcp-memgraph)** - Query your data in [Memgraph](https://memgraph.com/) graph database.
 - <img height="12" width="12" src="https://memgraph.com/favicon.png" alt="Memgraph Logo" /> **[Memgraph](https://github.com/memgraph/ai-toolkit/tree/main/integrations/mcp-memgraph)** - Query your data in [Memgraph](https://memgraph.com/) graph database.
 - <img height="12" width="12" src="https://www.mercadopago.com/favicon.ico" alt="MercadoPago Logo" /> **[Mercado Pago](https://mcp.mercadopago.com/)** - Mercado Pago's official MCP server.
-- <img height="12" width="12" src="https://metoro.io/static/images/logos/Metoro.svg" alt="Metoro Logo" /> **[Metoro](https://github.com/metoro-io/metoro-mcp-server)** - Query and interact with kubernetes environments monitored by Metoro
+- <img height="12" width="12" src="https://metoro.io/static/images/logos/MetoroLogo.png" alt="Metoro Logo" /> **[Metoro](https://github.com/metoro-io/metoro-mcp-server)** - Query and interact with kubernetes environments monitored by Metoro
 - <img height="12" width="12" src="https://claritystatic.azureedge.net/images/logo.ico" alt="Microsoft Clarity Logo"/> **[Microsoft Clarity](https://github.com/microsoft/clarity-mcp-server)** - Official MCP Server to get your behavioral analytics data and insights from [Clarity](https://clarity.microsoft.com)
 - <img height="12" width="12" src="https://conn-afd-prod-endpoint-bmc9bqahasf3grgk.b01.azurefd.net/releases/v1.0.1735/1.0.1735.4099/commondataserviceforapps/icon.png" alt="Microsoft Dataverse Logo" /> **[Microsoft Dataverse](https://go.microsoft.com/fwlink/?linkid=2320176)** - Chat over your business data using NL - Discover tables, run queries, retrieve data, insert or update records, and execute custom prompts grounded in business knowledge and context.
 - <img height="12" width="12" src="https://www.microsoft.com/favicon.ico" alt="microsoft.com favicon" /> **[Microsoft Learn Docs](https://github.com/microsoftdocs/mcp)** - An MCP server that provides structured access to Microsoft’s official documentation. Retrieves accurate, authoritative, and context-aware technical content for code generation, question answering, and workflow grounding.
@@ -342,7 +342,7 @@ Official integrations are maintained by companies building production ready MCP
 - <img height="12" width="12" src="https://verodat.io/assets/favicon-16x16.png" alt="Verodat Logo" /> **[Verodat](https://github.com/Verodat/verodat-mcp-server)** - Interact with Verodat AI Ready Data platform
 - <img height="12" width="12" src="https://www.veyrax.com/favicon.ico" alt="VeyraX Logo" /> **[VeyraX](https://github.com/VeyraX/veyrax-mcp)** - Single tool to control all 100+ API integrations, and UI components
 - <img height="12" width="12" src="https://avatars.githubusercontent.com/u/174736222?s=200&v=4" alt="VictoriaMetrics Logo" /> **[VictoriaMetrics](https://github.com/VictoriaMetrics-Community/mcp-victoriametrics)** - Comprehensive integration with [VictoriaMetrics APIs](https://docs.victoriametrics.com/victoriametrics/url-examples/) and [documentation](https://docs.victoriametrics.com/) for monitoring, observability, and debugging tasks related to your VictoriaMetrics instances.
-- <img src="https://framerusercontent.com/images/ijlYG00LOcMD6zR1XLMxHbAwZkM.png" alt="VideoDB Director" height="14"> **[VideoDB Director](https://github.com/video-db/agent-toolkit/tree/main/modelcontextprotocol)** - Create AI-powered video workflows including automatic editing, content moderation, voice cloning, highlight generation, and searchable video moments—all accessible via simple APIs and intuitive chat-based interfaces.
+- <img height="12" width="12" src="https://framerusercontent.com/images/ijlYG00LOcMD6zR1XLMxHbAwZkM.png" alt="VideoDB Director" /> **[VideoDB Director](https://github.com/video-db/agent-toolkit/tree/main/modelcontextprotocol)** - Create AI-powered video workflows including automatic editing, content moderation, voice cloning, highlight generation, and searchable video moments—all accessible via simple APIs and intuitive chat-based interfaces.
 - <img height="12" width="12" src="https://landing.ai/wp-content/uploads/2024/04/cropped-favicon-192x192.png" alt="LandingAI VisionAgent" /> **[VisionAgent MCP](https://github.com/landing-ai/vision-agent-mcp)** - A simple MCP server that enables your LLM to better reason over images, video and documents.
 - <img height="12" width="12" src="https://raw.githubusercontent.com/mckinsey/vizro/main/vizro-core/docs/assets/images/favicon.png" alt="Vizro Logo" /> **[Vizro](https://github.com/mckinsey/vizro/tree/main/vizro-mcp)** - Tools and templates to create validated and maintainable data charts and dashboards
 - <img height="12" width="12" src="https://wavespeed.ai/logo.webp" alt="WaveSpeed Logo" /> **[WaveSpeed](https://github.com/WaveSpeedAI/mcp-server)** - WaveSpeed MCP server providing AI agents with image and video generation capabilities.
@@ -526,7 +526,6 @@ A growing set of community-developed and maintained servers demonstrates various
 - **[Feyod](https://github.com/jeroenvdmeer/feyod-mcp)** - A server that answers questions about football matches, and specialised in the football club Feyenoord.
 - **[Fibaro HC3](https://github.com/coding-sailor/mcp-server-hc3)** - MCP server for Fibaro Home Center 3 smart home systems.
 - **[Figma](https://github.com/GLips/Figma-Context-MCP)** - Give your coding agent direct access to Figma file data, helping it one-shot design implementation.
-- **[Fingertip](https://github.com/fingertip-com/fingertip-mcp)** - MCP server for Fingertip.com to search and create new sites.
 - **[Firebase](https://github.com/gannonh/firebase-mcp)** - Server to interact with Firebase services including Firebase Authentication, Firestore, and Firebase Storage.
 - **[FireCrawl](https://github.com/vrknetha/mcp-server-firecrawl)** - Advanced web scraping with JavaScript rendering, PDF support, and smart rate limiting
 - **[FitBit MCP Server](https://github.com/NitayRabi/fitbit-mcp)** - An MCP server that connects to FitBit API using a token obtained from OAuth flow.
@@ -599,7 +598,6 @@ A growing set of community-developed and maintained servers demonstrates various
 - **[iTerm MCP](https://github.com/ferrislucas/iterm-mcp)** - Integration with iTerm2 terminal emulator for macOS, enabling LLMs to execute and monitor terminal commands.
 - **[iTerm MCP Server](https://github.com/rishabkoul/iTerm-MCP-Server)** - A Model Context Protocol (MCP) server implementation for iTerm2 terminal integration. Able to manage multiple iTerm Sessions.
 - **[Java Decompiler](https://github.com/idachev/mcp-javadc)** - Decompile Java bytecode into readable source code from .class files, package names, or JAR archives using CFR decompiler
-- **[JavaFX](https://github.com/mcpso/mcp-server-javafx)** - Make drawings using a JavaFX canvas
 - **[JavaFX](https://github.com/quarkiverse/quarkus-mcp-servers/tree/main/jfx)** - Make drawings using a JavaFX canvas
 - **[JDBC](https://github.com/quarkiverse/quarkus-mcp-servers/tree/main/jdbc)** - Connect to any JDBC-compatible database and query, insert, update, delete, and more. Supports MySQL, PostgreSQL, Oracle, SQL Server, sqllite and [more](https://github.com/quarkiverse/quarkus-mcp-servers/tree/main/jdbc#supported-jdbc-variants).
 - **[JMeter](https://github.com/QAInsights/jmeter-mcp-server)** - Run load testing using Apache JMeter via MCP-compliant tools.
@@ -799,7 +797,6 @@ A growing set of community-developed and maintained servers demonstrates various
 - **[Riot Games](https://github.com/jifrozen0110/mcp-riot)** - MCP server for League of Legends – fetch player info, ranks, champion stats, and match history via Riot API.
 - **[Rquest](https://github.com/xxxbrian/mcp-rquest)** - An MCP server providing realistic browser-like HTTP request capabilities with accurate TLS/JA3/JA4 fingerprints for bypassing anti-bot measures.
 - **[Rust MCP Filesystem](https://github.com/rust-mcp-stack/rust-mcp-filesystem)** - Fast, asynchronous MCP server for efficient handling of various filesystem operations built with the power of Rust.
-- **[Salesforce MCP](https://github.com/salesforce-mcp/salesforce-mcp)** -  Salesforce MCP server. Supports cloud version Salesforce-mcp.com and allows both data & metadata functions. 
 - **[Salesforce MCP](https://github.com/smn2gnt/MCP-Salesforce)** - Interact with Salesforce Data and Metadata
 - **[Salesforce MCP (AiondaDotCom)](https://github.com/AiondaDotCom/mcp-salesforce)** - Universal Salesforce integration with OAuth authentication, smart learning system, comprehensive backup capabilities, and full CRUD operations for any Salesforce org including custom objects and fields.
 - **[Salesforce MCP Server](https://github.com/tsmztech/mcp-server-salesforce)** - Comprehensive Salesforce integration with tools for querying records, executing Apex, managing fields/objects, and handling debug logs
@@ -874,7 +871,6 @@ A growing set of community-developed and maintained servers demonstrates various
 - **[Trello MCP Server](https://github.com/lioarce01/trello-mcp-server)** - An MCP server that interact with user Trello boards, modifying them with prompting.
 - **[Tripadvisor](https://github.com/pab1it0/tripadvisor-mcp)** - A MCP server that enables LLMs to interact with Tripadvisor API, supporting location data, reviews, and photos through standardized MCP interfaces
 - **[TrueNAS Core MCP](https://github.com/vespo92/TrueNasCoreMCP)** - An MCP server for interacting with TrueNAS Core.
-- **[Tsuki-Mcp-Filesystem-Server](https://github.com/yuutotsuki/tsuki_mcp_filesystem_server)** - A simple, fast, and fully MCP-compliant server for listing local filesystem files. Built with Python + FastAPI. Designed for OpenAI's Agent SDK via `resources/list`.
 - **[Tyk API Management](https://github.com/TykTechnologies/tyk-dashboard-mcp)** - Chat with all of your organization's managed APIs and perform other API lifecycle operations, managing tokens, users, analytics, and more.
 - **[Typesense](https://github.com/suhail-ak-s/mcp-typesense-server)** - A Model Context Protocol (MCP) server implementation that provides AI models with access to Typesense search capabilities. This server enables LLMs to discover, search, and analyze data stored in Typesense collections.
 - **[uniswap-poolspy-mcp](https://github.com/kukapay/uniswap-poolspy-mcp)** - An MCP server that tracks newly created liquidity pools on Uniswap across nine blockchain networks.

src/everything/README.md

@@ -72,6 +72,14 @@ This MCP server attempts to exercise all the features of the MCP protocol. It is
      - Embedded resource with `type: "resource"`
      - Text instruction for using the resource URI
 
+9. `startElicitation`
+   - Initiates an elicitation (interaction) within the MCP client.
+   - Inputs:
+      - `color` (string): Favorite color
+      - `number` (number, 1-100): Favorite number
+      - `pets` (enum): Favorite pet
+   - Returns: Confirmation of the elicitation demo with selection summary.
+
 ### Resources
 
 The server provides 100 test resources in two formats:

src/everything/everything.ts

@@ -86,6 +86,8 @@ const GetResourceReferenceSchema = z.object({
     .describe("ID of the resource to reference (1-100)"),
 });
 
+const ElicitationSchema = z.object({});
+
 const GetResourceLinksSchema = z.object({
   count: z
     .number()
@@ -104,6 +106,7 @@ enum ToolName {
   GET_TINY_IMAGE = "getTinyImage",
   ANNOTATED_MESSAGE = "annotatedMessage",
   GET_RESOURCE_REFERENCE = "getResourceReference",
+  ELICITATION = "startElicitation",
   GET_RESOURCE_LINKS = "getResourceLinks",
 }
 
@@ -126,6 +129,7 @@ export const createServer = () => {
         tools: {},
         logging: {},
         completions: {},
+        elicitation: {},
       },
       instructions
     }
@@ -216,6 +220,21 @@ export const createServer = () => {
     return await server.request(request, CreateMessageResultSchema);
   };
 
+  const requestElicitation = async (
+    message: string,
+    requestedSchema: any
+  ) => {
+    const request = {
+      method: 'elicitation/create',
+      params: {
+        message,
+        requestedSchema
+      }
+    };
+
+    return await server.request(request, z.any());
+  };
+
   const ALL_RESOURCES: Resource[] = Array.from({ length: 100 }, (_, i) => {
     const uri = `test://static/resource/${i + 1}`;
     if (i % 2 === 0) {
@@ -469,6 +488,11 @@ export const createServer = () => {
           "Returns a resource reference that can be used by MCP clients",
         inputSchema: zodToJsonSchema(GetResourceReferenceSchema) as ToolInput,
       },
+      {
+        name: ToolName.ELICITATION,
+        description: "Demonstrates the Elicitation feature by asking the user to provide information about their favorite color, number, and pets.",
+        inputSchema: zodToJsonSchema(ElicitationSchema) as ToolInput,
+      },
       {
         name: ToolName.GET_RESOURCE_LINKS,
         description:
@@ -664,6 +688,61 @@ export const createServer = () => {
       return { content };
     }
 
+    if (name === ToolName.ELICITATION) {
+      ElicitationSchema.parse(args);
+
+      const elicitationResult = await requestElicitation(
+        'What are your favorite things?',
+        {
+          type: 'object',
+          properties: {
+            color: { type: 'string', description: 'Favorite color' },
+            number: { type: 'integer', description: 'Favorite number', minimum: 1, maximum: 100 },
+            pets: { 
+              type: 'string', 
+              enum: ['cats', 'dogs', 'birds', 'fish', 'reptiles'], 
+              description: 'Favorite pets' 
+            },
+          }
+        }
+      );
+
+      // Handle different response actions
+      const content = [];
+      
+      if (elicitationResult.action === 'accept' && elicitationResult.content) {
+        content.push({
+          type: "text",
+          text: `✅ User provided their favorite things!`,
+        });
+        
+        // Only access elicitationResult.content when action is accept
+        const { color, number, pets } = elicitationResult.content;
+        content.push({
+          type: "text",
+          text: `Their favorites are:\n- Color: ${color || 'not specified'}\n- Number: ${number || 'not specified'}\n- Pets: ${pets || 'not specified'}`,
+        });
+      } else if (elicitationResult.action === 'decline') {
+        content.push({
+          type: "text",
+          text: `❌ User declined to provide their favorite things.`,
+        });
+      } else if (elicitationResult.action === 'cancel') {
+        content.push({
+          type: "text",
+          text: `⚠️ User cancelled the elicitation dialog.`,
+        });
+      }
+      
+      // Include raw result for debugging
+      content.push({
+        type: "text",
+        text: `\nRaw result: ${JSON.stringify(elicitationResult, null, 2)}`,
+      });
+
+      return { content };
+    }
+    
     if (name === ToolName.GET_RESOURCE_LINKS) {
       const { count } = GetResourceLinksSchema.parse(args);
       const content = [];

src/filesystem/README.md

@@ -9,8 +9,58 @@ Node.js server implementing Model Context Protocol (MCP) for filesystem operatio
 - Move files/directories
 - Search files
 - Get file metadata
+- Dynamic directory access control via [Roots](https://modelcontextprotocol.io/docs/concepts/roots)
+
+## Directory Access Control
+
+The server uses a flexible directory access control system. Directories can be specified via command-line arguments or dynamically via [Roots](https://modelcontextprotocol.io/docs/concepts/roots).
+
+### Method 1: Command-line Arguments
+Specify Allowed directories when starting the server:
+```bash
+mcp-server-filesystem /path/to/dir1 /path/to/dir2
+```
+
+### Method 2: MCP Roots (Recommended)
+MCP clients that support [Roots](https://modelcontextprotocol.io/docs/concepts/roots) can dynamically update the Allowed directories. 
+
+Roots notified by Client to Server, completely replace any server-side Allowed directories when provided.
+
+**Important**: If server starts without command-line arguments AND client doesn't support roots protocol (or provides empty roots), the server will throw an error during initialization.
+
+This is the recommended method, as this enables runtime directory updates via `roots/list_changed` notifications without server restart, providing a more flexible and modern integration experience.
+
+### How It Works
+
+The server's directory access control follows this flow:
+
+1. **Server Startup**
+   - Server starts with directories from command-line arguments (if provided)
+   - If no arguments provided, server starts with empty allowed directories
+
+2. **Client Connection & Initialization**
+   - Client connects and sends `initialize` request with capabilities
+   - Server checks if client supports roots protocol (`capabilities.roots`)
+   
+3. **Roots Protocol Handling** (if client supports roots)
+   - **On initialization**: Server requests roots from client via `roots/list`
+   - Client responds with its configured roots
+   - Server replaces ALL allowed directories with client's roots
+   - **On runtime updates**: Client can send `notifications/roots/list_changed`
+   - Server requests updated roots and replaces allowed directories again
+
+4. **Fallback Behavior** (if client doesn't support roots)
+   - Server continues using command-line directories only
+   - No dynamic updates possible
+
+5. **Access Control**
+   - All filesystem operations are restricted to allowed directories
+   - Use `list_allowed_directories` tool to see current directories
+   - Server requires at least ONE allowed directory to operate
+
+**Note**: The server will only allow operations within directories specified either via `args` or via Roots.
+
 
-**Note**: The server will only allow operations within directories specified via `args`.
 
 ## API