Discover Awesome MCP Servers

Gmail MCP Server

A high-performance MCP server that enables AI assistants to interact with Gmail securely via OAuth 2.0, supporting smart email retrieval and thread-aware drafting.

BOSSCORE MCP PACK

Modular MCP capabilities package for the BOSS ecosystem, enabling WordPress site management, file reading, and cPanel deployment with 63 tools across three profiles (wordpress, files, full) and two transport modes (stdio and HTTP/SSE).

Travel City Planner MCP

Converts natural language travel requests into customizable multi-city itineraries, with tools for planning, editing, and exporting trips across 69 global destinations.

Hitsteps

Enables access to Hitsteps analytics and website operations through a remote MCP server, using OAuth for authentication and Streamable HTTP transport.

CurAI

MCP server for a minimal note-taking app with text and images per user, enabling CRUD operations via Claude.

gitlab-mcp

A FastMCP server for GitLab 16.x that enables project, MR, pipeline, and commit queries, bugfix contribution summaries, release notes drafts, and comprehensive Runner management.

fallbooksonboard-mcp

MCP server for foldkit, exposing the 7-prime spine, 7 κ-bands, and 6 fold operations as native tools and resources in any MCP client.

yandex-station-mcp

MCP server to control Yandex Station speakers with Alice: manage music, radio, volume, playback, TTS, timers, alarms, reminders, and smart home scenarios via text commands or predefined tools.

Garmin Nutrition Coach

Enables Claude to act as a personal health coach by connecting to Garmin wearable data and Notion workspace for automated calorie tracking, photo food logging, and coaching insights.

ask-user-questions

Enables AI models to ask users questions through a local web interface, supporting batch questions, multi-select, and free text for human-in-the-loop interactions.

SuperBased Observer

Local MCP server that lets your AI coding agent query its own cross-tool project history - file/command freshness, past test failures, cost & token spend, cache status, and session handoff - over stdio, 100% local, no telemetry.

ChromaDB Remote MCP Server

A Streamable HTTP MCP server that provides remote access to ChromaDB for AI assistants like Claude. Enables semantic search and vector database operations from mobile devices and remote locations.

openlocal

A zero-dependency MCP and agent tool server for small local models that provides a measured, deterministic tool-calling interface with file, web, shell, and calculation tools.

codex-web-search-mcp

Zero-dependency MCP server that wraps OpenAI Codex's standalone search endpoint into codex_web_search and codex_web_research tools for Claude Code, enabling real-time web search and multi-step deep research independent of the underlying model.

Nall.Hangfire.Mcp

Remote MCP server for Hangfire that exposes background jobs as dynamic MCP tools, allowing clients like VS Code to inspect, trigger, and manage jobs in-process.

roblox-mcp-bridge

Connects Roblox Studio to local AI agents via HTTP, allowing them to control Studio tools.

memgrep

Enables AI agents to search and retrieve past chat transcripts from Cursor, Claude Code, and Kiro, providing a global, local memory for context-aware assistance.

Asgard MCP Server

A modular MCP server that provides file search, URL fetching, text reading, knowledge base search, and image embedding tools, with a web interface powered by an Ollama agent.

CloakBrowser MCP

CloakBrowser MCP server for AI agents: Playwright-powered browsing, clean tool forwarding, Docker support, and multi-session HTTP transport.

mcp-bing-webmaster

Provides secure, read-only access to Bing Webmaster Tools analytics and non-destructive URL submission for indexing, without destructive site management capabilities.

IndoAds Prompt MCP

A retrieval-first prompt engine for commercial advertising that curates, ranks, and composes visual ad prompts for image generation models like GPT Image, Midjourney, and Flux without generating images itself.

Parzley MCP Server

Enables AI-powered form filling through natural language by exposing the Parzley AI Form Filling Agent API as an MCP server.

Seamless

Local-first shared memory and task coordination for AI coding agents. One Go binary, MCP server, markdown files you own. Hooks for Claude Code and Codex CLI (and their desktop apps).

@node2flow/google-docs-mcp

MCP server for Google Docs — create, read, edit, format, and manage documents through 26 tools via the Model Context Protocol.

MCP Link - Convert Any OpenAPI V3 API to MCP Server

Okay, I can help you understand how to convert an OpenAPI V3 API definition to an MCP (presumably referring to a **Microservice Control Plane**) server. However, the process isn't a direct, one-step conversion. It involves several steps and considerations. Here's a breakdown of the general approach and key concepts: **Understanding the Goal** * **OpenAPI V3:** This describes your API's structure, endpoints, data models, authentication, etc. It's a *specification*. * **MCP (Microservice Control Plane):** This is an infrastructure layer that manages and orchestrates your microservices. It typically handles things like: * Service discovery * Traffic management (routing, load balancing) * Security (authentication, authorization) * Observability (metrics, logging, tracing) * Deployment and scaling The goal is to use the OpenAPI definition to *configure* your MCP to properly handle requests to your API. You're not "converting" the OpenAPI file into an MCP server itself. You're using it as a blueprint to tell the MCP how to manage your API. **General Steps** 1. **Choose an MCP:** The first step is to select a Microservice Control Plane. Popular options include: * **Istio:** A very popular and powerful open-source service mesh. * **Linkerd:** Another open-source service mesh, known for its simplicity. * **Kong:** An API gateway and service mesh. * **Envoy:** A high-performance proxy often used as a building block for service meshes. * **Commercial Solutions:** Many cloud providers (AWS, Azure, GCP) offer managed service mesh or API gateway solutions. The choice depends on your requirements (scale, complexity, existing infrastructure, budget, etc.). 2. **Deploy Your API (Microservice):** You need to have your actual API implementation running as a microservice. This is the code that handles the requests defined in your OpenAPI specification. This microservice needs to be deployed in an environment that the MCP can manage (e.g., Kubernetes). 3. **Configure the MCP using the OpenAPI Definition:** This is the core of the process. You'll use the OpenAPI definition to configure the MCP to: * **Route traffic:** Tell the MCP how to route incoming requests to the correct microservice based on the URL path, HTTP method, and other criteria defined in the OpenAPI spec. * **Apply security policies:** Configure authentication and authorization based on the security schemes defined in the OpenAPI spec (e.g., API keys, OAuth 2.0, JWT). * **Implement rate limiting:** Set limits on the number of requests allowed per client or API endpoint. * **Transform requests/responses (if needed):** The MCP can sometimes be used to transform requests or responses to match the expected format. * **Enable observability:** Configure the MCP to collect metrics, logs, and traces for your API. 4. **Specific MCP Configuration Methods:** The exact way you configure the MCP depends on the chosen MCP. Here are some common approaches: * **Istio:** * **Virtual Services:** Define how traffic is routed to your microservices. You can use the OpenAPI spec to help define the routing rules. * **Gateway:** Configures the entry point for external traffic into your service mesh. * **AuthorizationPolicy:** Defines access control rules. * **RequestAuthentication:** Configures how to authenticate requests. * **Istio API Definitions:** Istio has its own API definitions (CRDs - Custom Resource Definitions) that you use to configure its behavior. You'll need to translate the information from your OpenAPI spec into these Istio API definitions. * **Kong:** * **Plugins:** Kong uses plugins to add functionality like authentication, rate limiting, and request transformation. You can configure these plugins using the Kong Admin API or declarative configuration files. The OpenAPI spec can guide you in configuring these plugins. * **Services and Routes:** Define the upstream services and the routes that map to them. * **Other MCPs:** Each MCP will have its own configuration mechanisms. Consult the documentation for your chosen MCP. **Example (Conceptual - Istio)** Let's say your OpenAPI spec defines an endpoint: ```yaml paths: /users/{userId}: get: summary: Get a user by ID parameters: - name: userId in: path required: true schema: type: integer responses: '200': description: Successful operation content: application/json: schema: type: object properties: id: type: integer name: type: string ``` In Istio, you might create a `VirtualService` like this (simplified): ```yaml apiVersion: networking.istio.io/v1alpha3 kind: VirtualService metadata: name: user-service spec: hosts: - "user-service.example.com" # Or the hostname of your service gateways: - my-gateway http: - match: - uri: prefix: /users/ route: - destination: host: user-service # The Kubernetes service name of your microservice port: number: 8080 # The port your microservice is listening on ``` This `VirtualService` tells Istio to route any requests to `/users/*` to the `user-service` microservice. You would then configure other Istio resources (e.g., `AuthorizationPolicy`) to handle authentication and authorization for this endpoint, based on the security schemes defined in your OpenAPI spec. **Tools and Automation** * **OpenAPI to MCP Configuration Generators:** Some tools can help automate the process of generating MCP configuration from OpenAPI definitions. These tools are often specific to a particular MCP. Search for tools like "OpenAPI to Istio configuration generator" or "OpenAPI to Kong configuration generator." * **Scripting:** You can write scripts (e.g., using Python and the Istio or Kong API) to programmatically generate the MCP configuration based on your OpenAPI spec. * **Configuration Management Tools:** Tools like Terraform or Ansible can be used to manage the deployment and configuration of your MCP. **Important Considerations** * **Complexity:** Configuring an MCP can be complex, especially for large and complex APIs. * **Security:** Pay close attention to security when configuring your MCP. Make sure you properly authenticate and authorize requests. * **Testing:** Thoroughly test your API after configuring the MCP to ensure that everything is working as expected. * **Evolution:** As your API evolves, you'll need to update your OpenAPI definition and reconfigure your MCP. **In summary, there's no single "convert" button. You need to:** 1. **Choose an MCP.** 2. **Deploy your API as a microservice.** 3. **Use your OpenAPI definition as a blueprint to configure the MCP to manage traffic, security, and observability for your API.** 4. **Use tools and scripting to automate the configuration process where possible.** To give you more specific guidance, please tell me: * **Which MCP are you using (or considering)?** * **What is your deployment environment (e.g., Kubernetes, AWS, Azure)?** * **What are your key requirements (e.g., security, rate limiting, observability)?** Then I can provide more tailored advice.

Code Mode Bridge

An MCP server that aggregates multiple upstream MCP tools into a single 'codemode' tool for unified orchestration and execution. It enables agents to run generated code in an isolated sandbox to interact with various connected services through a single interface.

Remote Jobs MCP Server

Official Model Context Protocol (MCP) server to search, filter, and retrieve live remote job listings from the Jobicy database in real-time. Works with Claude Code, Cursor, Cline, and custom AI agents.

Weather MCP Server

Provides weather information for cities through a protected MCP interface with Nevermined payment integration. Demonstrates both high-level and low-level MCP server implementations with paywall protection for tools, resources, and prompts.

Turnale

Tournament software for tennis, padel, pickleball and more: fair draws, live standings, scores and dropout handling.

db-mcp

A secure MCP server for connecting AI assistants to MySQL, Redis, and MongoDB with preconfigured connections, runtime protections, and graded security modes.