Merge branch 'main' into patch-1

Author: 1kko-ahnlabio

README.md

@@ -74,6 +74,7 @@ Official integrations are maintained by companies building production ready MCP
 - <img height="12" width="12" src="https://cdn.prod.website-files.com/6605a2979ff17b2cd1939cd4/6605a460de47e7596ed84f06_icon256.png" alt="gotoHuman Logo" /> **[gotoHuman](https://github.com/gotohuman/gotohuman-mcp-server)** - Human-in-the-loop platform - Allow AI agents and automations to send requests for approval to your [gotoHuman](https://www.gotohuman.com) inbox.
 - <img height="12" width="12" src="https://grafana.com/favicon.ico" alt="Grafana Logo" /> **[Grafana](https://github.com/grafana/mcp-grafana)** - Search dashboards, investigate incidents and query datasources in your Grafana instance
 - <img height="12" width="12" src="https://framerusercontent.com/images/KCOWBYLKunDff1Dr452y6EfjiU.png" alt="Graphlit Logo" /> **[Graphlit](https://github.com/graphlit/graphlit-mcp-server)** - Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a searchable [Graphlit](https://www.graphlit.com) project.
+- <img height="12" width="12" src="https://greptime.com/favicon.ico" alt="Greptime Logo" /> **[GreptimeDB](https://github.com/GreptimeTeam/greptimedb-mcp-server)** - Provides AI assistants with a secure and structured way to explore and analyze data in [GreptimeDB](https://github.com/GreptimeTeam/greptimedb).
 - <img height="12" width="12" src="https://img.alicdn.com/imgextra/i3/O1CN01d9qrry1i6lTNa2BRa_!!6000000004364-2-tps-218-200.png" alt="Hologres Logo" /> **[Hologres](https://github.com/aliyun/alibabacloud-hologres-mcp-server)** - Connect to a [Hologres](https://www.alibabacloud.com/en/product/hologres) instance, get table metadata, query and analyze data.
 - <img height="12" width="12" src="https://hyperbrowser-assets-bucket.s3.us-east-1.amazonaws.com/Hyperbrowser-logo.png" alt="Hyperbrowsers23 Logo" /> **[Hyperbrowser](https://github.com/hyperbrowserai/mcp)** - [Hyperbrowser](https://www.hyperbrowser.ai/) is the next-generation platform empowering AI agents and enabling effortless, scalable browser automation.
 - **[IBM wxflows](https://github.com/IBM/wxflows/tree/main/examples/mcp/javascript)** - Tool platform by IBM to build, test and deploy tools for any data source
@@ -83,6 +84,7 @@ Official integrations are maintained by companies building production ready MCP
 - <img height="12" width="12" src="https://integration.app/favicon.ico" alt="Integration App Icon" /> **[Integration App](https://github.com/integration-app/mcp-server)** - Interact with any other SaaS applications on behalf of your customers.
 - <img height="12" width="12" src="https://cdn.simpleicons.org/jetbrains" /> **[JetBrains](https://github.com/JetBrains/mcp-jetbrains)** – Work on your code with JetBrains IDEs
 - <img height="12" width="12" src="https://kagi.com/favicon.ico" alt="Kagi Logo" /> **[Kagi Search](https://github.com/kagisearch/kagimcp)** - Search the web using Kagi's search API
+- <img height="12" width="12" src="https://connection.keboola.com/favicon.ico" alt="Keboola Logo" /> **[Keboola](https://github.com/keboola/keboola-mcp-server)** - Build robust data workflows, integrations, and analytics on a single intuitive platform.
 - <img height="12" width="12" src="https://logfire.pydantic.dev/favicon.ico" alt="Logfire Logo" /> **[Logfire](https://github.com/pydantic/logfire-mcp)** - Provides access to OpenTelemetry traces and metrics through Logfire.
 - <img height="12" width="12" src="https://langfuse.com/favicon.ico" alt="Langfuse Logo" /> **[Langfuse Prompt Management](https://github.com/langfuse/mcp-server-langfuse)** - Open-source tool for collaborative editing, versioning, evaluating, and releasing prompts.
 - <img height="12" width="12" src="https://lingo.dev/favicon.ico" alt="Lingo.dev Logo" /> **[Lingo.dev](https://github.com/lingodotdev/lingo.dev/blob/main/mcp.md)** - Make your AI agent speak every language on the planet, using [Lingo.dev](https://lingo.dev) Localization Engine.
@@ -107,6 +109,7 @@ Official integrations are maintained by companies building production ready MCP
 - <img height="12" width="12" src="https://pics.fatwang2.com/56912e614b35093426c515860f9f2234.svg" /> [Search1API](https://github.com/fatwang2/search1api-mcp) - One API for Search, Crawling, and Sitemaps
 - <img height="12" width="12" src="https://screenshotone.com/favicon.ico" alt="ScreenshotOne Logo" /> **[ScreenshotOne](https://github.com/screenshotone/mcp/)** - Render website screenshots with [ScreenshotOne](https://screenshotone.com/)
 - <img height="12" width="12" src="https://semgrep.dev/favicon.ico" alt="Semgrep Logo" /> **[Semgrep](https://github.com/semgrep/mcp)** - Enable AI agents to secure code with [Semgrep](https://semgrep.dev/).
+- <img height="12" width="12" src="https://www.singlestore.com/favicon-32x32.png?v=277b9cbbe31e8bc416504cf3b902d430"/> **[SingleStore](https://github.com/singlestore-labs/mcp-server-singlestore)** - Interact with the SingleStore database platform
 - <img height="12" width="12" src="https://www.starrocks.io/favicon.ico" alt="StarRocks Logo" /> **[StarRocks](https://github.com/StarRocks/mcp-server-starrocks)** - Interact with [StarRocks](https://www.starrocks.io/)
 - <img height="12" width="12" src="https://stripe.com/favicon.ico" alt="Stripe Logo" /> **[Stripe](https://github.com/stripe/agent-toolkit)** - Interact with Stripe API
 - <img height="12" width="12" src="https://tavily.com/favicon.ico" alt="Tavily Logo" /> **[Tavily](https://github.com/tavily-ai/tavily-mcp)** - Search engine for AI agents (search + extract) powered by [Tavily](https://tavily.com/)
@@ -118,6 +121,7 @@ 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://www.xero.com/favicon.ico" alt="Xero Logo" /> **[Xero](https://github.com/XeroAPI/xero-mcp-server)** - Interact with the accounting data in your business using our official MCP server
+- <img height="12" width="12" src="https://cdn.zapier.com/zapier/images/favicon.ico" alt="Zapier Logo" /> **[Zapier](https://zapier.com/mcp)** - Connect your AI Agents to 8,000 apps instantly.
 - **[ZenML](https://github.com/zenml-io/mcp-zenml)** - Interact with your MLOps and LLMOps pipelines through your [ZenML](https://www.zenml.io) MCP server
 
 ### 🌎 Community Servers
@@ -153,6 +157,7 @@ A growing set of community-developed and maintained servers demonstrates various
 - **[Bitable MCP](https://github.com/lloydzhou/bitable-mcp)** (by lloydzhou) - MCP server provides access to Lark Bitable through the Model Context Protocol. It allows users to interact with Bitable tables using predefined tools.
 - **[Blender](https://github.com/ahujasid/blender-mcp)** (by ahujasid) - Blender integration allowing prompt enabled 3D scene creation, modeling and manipulation.
 - **[Bsc-mcp](https://github.com/TermiX-official/bsc-mcp)** The first MCP server that serves as the bridge between AI and BNB Chain, enabling AI agents to execute complex on-chain operations through seamless integration with the BNB Chain, including transfer, swap, launch, security check on any token and even more.
+- **[Calculator](https://github.com/githejie/mcp-server-calculator)** - This server enables LLMs to use calculator for precise numerical calculations.
 - **[CFBD API](https://github.com/lenwood/cfbd-mcp-server)** - An MCP server for the [College Football Data API](https://collegefootballdata.com/).
 - **[ChatMCP](https://github.com/AI-QL/chat-mcp)** – An Open Source Cross-platform GUI Desktop application compatible with Linux, macOS, and Windows, enabling seamless interaction with MCP servers across dynamically selectable LLMs, by **[AIQL](https://github.com/AI-QL)**
 - **[ChatSum](https://github.com/mcpso/mcp-server-chatsum)** - Query and Summarize chat messages with LLM. by [mcpso](https://mcp.so)
@@ -223,6 +228,7 @@ A growing set of community-developed and maintained servers demonstrates various
 - **[HubSpot](https://github.com/buryhuang/mcp-hubspot)** - HubSpot CRM integration for managing contacts and companies. Create and retrieve CRM data directly through Claude chat.
 - **[HuggingFace Spaces](https://github.com/evalstate/mcp-hfspace)** - Server for using HuggingFace Spaces, supporting Open Source Image, Audio, Text Models and more. Claude Desktop mode for easy integration.
 - **[Hyperliquid](https://github.com/mektigboy/server-hyperliquid)** - An MCP server implementation that integrates the Hyperliquid SDK for exchange data.
+- **[iFlytek Workflow](https://github.com/iflytek/ifly-workflow-mcp-server)** - Connect to iFlytek Workflow via the MCP server and run your own Agent.
 - **[Image Generation](https://github.com/GongRzhe/Image-Generation-MCP-Server)** - This MCP server provides image generation capabilities using the Replicate Flux model.
 - **[InfluxDB](https://github.com/idoru/influxdb-mcp-server)** - Run queries against InfluxDB OSS API v2.
 - **[Inoyu](https://github.com/sergehuber/inoyu-mcp-unomi-server)** - Interact with an Apache Unomi CDP customer data platform to retrieve and update customer profiles
@@ -364,6 +370,7 @@ These are high-level frameworks that make it easier to build MCP servers or clie
 - **[FastAPI to MCP auto generator](https://github.com/tadata-org/fastapi_mcp)** – A zero-configuration tool for automatically exposing FastAPI endpoints as MCP tools by **[Tadata](https://tadata.com/)**
 * **[FastMCP](https://github.com/punkpeye/fastmcp)** (TypeScript)
 * **[Foxy Contexts](https://github.com/strowk/foxy-contexts)** – A library to build MCP servers in Golang by **[strowk](https://github.com/strowk)**
+* **[Higress MCP Server Hosting](https://github.com/alibaba/higress/tree/main/plugins/wasm-go/mcp-servers)** - A solution for hosting MCP Servers by extending the API Gateway (based on Envoy) with wasm plugins.
 * **[MCP-Framework](https://mcp-framework.com)** Build MCP servers with elegance and speed in Typescript. Comes with a CLI to create your project with `mcp create app`. Get started with your first server in under 5 minutes by **[Alex Andru](https://github.com/QuantGeekDev)**
 * **[Quarkus MCP Server SDK](https://github.com/quarkiverse/quarkus-mcp-server)** (Java)
 * **[Template MCP Server](https://github.com/mcpdotdirect/template-mcp-server)** - A CLI tool to create a new Model Context Protocol server project with TypeScript support, dual transport options, and an extensible structure

src/fetch/README.md

@@ -107,6 +107,10 @@ ModelContextProtocol/1.0 (User-Specified; +https://github.com/modelcontextprotoc
 
 This can be customized by adding the argument `--user-agent=YourUserAgent` to the `args` list in the configuration.
 
+### Customization - Proxy
+
+The server can be configured to use a proxy by using the `--proxy-url` argument.
+
 ## Debugging
 
 You can use the MCP inspector to debug the server. For uvx installations:

src/fetch/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "mcp-server-fetch"
-version = "0.6.2"
+version = "0.6.3"
 description = "A Model Context Protocol server providing tools to fetch and convert web content for usage by LLMs"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -16,6 +16,7 @@ classifiers = [
     "Programming Language :: Python :: 3.10",
 ]
 dependencies = [
+    "httpx<0.28",
     "markdownify>=0.13.1",
     "mcp>=1.1.3",
     "protego>=0.3.1",

src/fetch/src/mcp_server_fetch/__init__.py

@@ -15,9 +15,10 @@ def main():
         action="store_true",
         help="Ignore robots.txt restrictions",
     )
+    parser.add_argument("--proxy-url", type=str, help="Proxy URL to use for requests")
 
     args = parser.parse_args()
-    asyncio.run(serve(args.user_agent, args.ignore_robots_txt))
+    asyncio.run(serve(args.user_agent, args.ignore_robots_txt, args.proxy_url))
 
 
 if __name__ == "__main__":

src/fetch/src/mcp_server_fetch/server.py

@@ -63,7 +63,7 @@ def get_robots_txt_url(url: str) -> str:
     return robots_url
 
 
-async def check_may_autonomously_fetch_url(url: str, user_agent: str) -> None:
+async def check_may_autonomously_fetch_url(url: str, user_agent: str, proxy_url: str | None = None) -> None:
     """
     Check if the URL can be fetched by the user agent according to the robots.txt file.
     Raises a McpError if not.
@@ -72,7 +72,7 @@ async def check_may_autonomously_fetch_url(url: str, user_agent: str) -> None:
 
     robot_txt_url = get_robots_txt_url(url)
 
-    async with AsyncClient() as client:
+    async with AsyncClient(proxies=proxy_url) as client:
         try:
             response = await client.get(
                 robot_txt_url,
@@ -109,14 +109,14 @@ async def check_may_autonomously_fetch_url(url: str, user_agent: str) -> None:
 
 
 async def fetch_url(
-    url: str, user_agent: str, force_raw: bool = False
+    url: str, user_agent: str, force_raw: bool = False, proxy_url: str | None = None
 ) -> Tuple[str, str]:
     """
     Fetch the URL and return the content in a form ready for the LLM, as well as a prefix string with status information.
     """
     from httpx import AsyncClient, HTTPError
 
-    async with AsyncClient() as client:
+    async with AsyncClient(proxies=proxy_url) as client:
         try:
             response = await client.get(
                 url,
@@ -173,19 +173,22 @@ class Fetch(BaseModel):
         bool,
         Field(
             default=False,
-            description="Get the actual HTML content if the requested page, without simplification.",
+            description="Get the actual HTML content of the requested page, without simplification.",
         ),
     ]
 
 
 async def serve(
-    custom_user_agent: str | None = None, ignore_robots_txt: bool = False
+    custom_user_agent: str | None = None,
+    ignore_robots_txt: bool = False,
+    proxy_url: str | None = None,
 ) -> None:
     """Run the fetch MCP server.
 
     Args:
         custom_user_agent: Optional custom User-Agent string to use for requests
         ignore_robots_txt: Whether to ignore robots.txt restrictions
+        proxy_url: Optional proxy URL to use for requests
     """
     server = Server("mcp-fetch")
     user_agent_autonomous = custom_user_agent or DEFAULT_USER_AGENT_AUTONOMOUS
@@ -229,10 +232,10 @@ async def call_tool(name, arguments: dict) -> list[TextContent]:
             raise McpError(ErrorData(code=INVALID_PARAMS, message="URL is required"))
 
         if not ignore_robots_txt:
-            await check_may_autonomously_fetch_url(url, user_agent_autonomous)
+            await check_may_autonomously_fetch_url(url, user_agent_autonomous, proxy_url)
 
         content, prefix = await fetch_url(
-            url, user_agent_autonomous, force_raw=args.raw
+            url, user_agent_autonomous, force_raw=args.raw, proxy_url=proxy_url
         )
         original_length = len(content)
         if args.start_index >= original_length:
@@ -259,7 +262,7 @@ async def get_prompt(name: str, arguments: dict | None) -> GetPromptResult:
         url = arguments["url"]
 
         try:
-            content, prefix = await fetch_url(url, user_agent_manual)
+            content, prefix = await fetch_url(url, user_agent_manual, proxy_url=proxy_url)
             # TODO: after SDK bug is addressed, don't catch the exception
         except McpError as e:
             return GetPromptResult(

src/filesystem/README.md

@@ -41,22 +41,16 @@ Node.js server implementing Model Context Protocol (MCP) for filesystem operatio
   - Features:
     - Line-based and multi-line content matching
     - Whitespace normalization with indentation preservation
-    - Fuzzy matching with confidence scoring
     - Multiple simultaneous edits with correct positioning
     - Indentation style detection and preservation
     - Git-style diff output with context
     - Preview changes with dry run mode
-    - Failed match debugging with confidence scores
   - Inputs:
     - `path` (string): File to edit
     - `edits` (array): List of edit operations
       - `oldText` (string): Text to search for (can be substring)
       - `newText` (string): Text to replace with
     - `dryRun` (boolean): Preview changes without applying (default: false)
-    - `options` (object): Optional formatting settings
-      - `preserveIndentation` (boolean): Keep existing indentation (default: true)
-      - `normalizeWhitespace` (boolean): Normalize spaces while preserving structure (default: true)
-      - `partialMatch` (boolean): Enable fuzzy matching (default: true)
   - Returns detailed diff and match information for dry runs, otherwise applies changes
   - Best Practice: Always use dryRun first to preview changes before applying them
 

src/filesystem/index.ts

@@ -42,7 +42,7 @@ const allowedDirectories = args.map(dir =>
 // Validate that all directories exist and are accessible
 await Promise.all(args.map(async (dir) => {
   try {
-    const stats = await fs.stat(dir);
+    const stats = await fs.stat(expandHome(dir));
     if (!stats.isDirectory()) {
       console.error(`Error: ${dir} is not a directory`);
       process.exit(1);

src/git/uv.lock

@@ -157,7 +157,7 @@ export const GitHubLabelSchema = z.object({
   name: z.string(),
   color: z.string(),
   default: z.boolean(),
-  description: z.string().optional(),
+  description: z.string().nullable().optional(),
 });
 
 export const GitHubMilestoneSchema = z.object({