Discover Awesome MCP Servers

trinity-local

Enables running AI councils across Claude, GPT, and Gemini, synthesizing answers based on your personal taste lens, all locally without an API key.

mcpo-docker

Okay, here's an example Dockerfile and some accompanying explanation to help you create a Docker image for `mcpo` (assuming it's a command-line tool that exposes MCP servers as OpenAPI endpoints for OpenWebUI). I'll make some reasonable assumptions about how `mcpo` works, but you'll need to adapt this to your specific needs. **Dockerfile** ```dockerfile # Use a base image with Python (e.g., slim version for smaller size) FROM python:3.11-slim-bookworm AS builder # Set a working directory inside the container WORKDIR /app # Copy the mcpo requirements file (if you have one) COPY requirements.txt . # Install mcpo dependencies (if any) RUN pip install --no-cache-dir -r requirements.txt # Copy the mcpo source code COPY . . # --- Final Image --- FROM python:3.11-slim-bookworm # Set a working directory inside the container WORKDIR /app # Copy the mcpo executable from the builder stage COPY --from=builder /app . # Expose the port mcpo will listen on (adjust as needed) EXPOSE 8000 # Define the command to run mcpo when the container starts CMD ["python", "mcpo.py", "--host", "0.0.0.0", "--port", "8000"] ``` **Explanation:** 1. **`FROM python:3.11-slim-bookworm AS builder`**: * This line specifies the base image for the Docker image. We're using a Python 3.11 slim image based on Debian Bookworm. The `slim` version is smaller than the full Python image, which is good for reducing the image size. The `AS builder` part gives this stage a name, "builder," which we'll use later. 2. **`WORKDIR /app`**: * Sets the working directory inside the container to `/app`. All subsequent commands will be executed relative to this directory. 3. **`COPY requirements.txt .`**: * Copies the `requirements.txt` file (if you have one) from your local directory to the `/app` directory inside the container. This file should list all the Python packages that `mcpo` depends on. If you don't have a `requirements.txt` file, you can create one using `pip freeze > requirements.txt` in your local `mcpo` development environment. 4. **`RUN pip install --no-cache-dir -r requirements.txt`**: * Installs the Python packages listed in `requirements.txt`. The `--no-cache-dir` option prevents `pip` from caching downloaded packages, which helps reduce the image size. 5. **`COPY . .`**: * Copies all the files and directories from your current directory (where the Dockerfile is located) to the `/app` directory inside the container. This includes the `mcpo.py` script (or whatever the main `mcpo` executable is called), any configuration files, and other necessary files. 6. **`FROM python:3.11-slim-bookworm`**: * Starts a new stage in the Docker build. This is important for creating a smaller final image. We're using the same base image as before. 7. **`WORKDIR /app`**: * Sets the working directory for the new stage. 8. **`COPY --from=builder /app .`**: * This is the key to multi-stage builds. It copies the contents of the `/app` directory from the `builder` stage to the `/app` directory in the current stage. This means we're only copying the compiled code and dependencies, not the build tools or intermediate files. 9. **`EXPOSE 8000`**: * Declares that the container will listen on port 8000. This is just metadata; it doesn't actually publish the port. You'll need to use the `-p` option when running the container to map the container's port 8000 to a port on your host machine. Adjust the port number if `mcpo` uses a different port. 10. **`CMD ["python", "mcpo.py", "--host", "0.0.0.0", "--port", "8000"]`**: * Specifies the command to run when the container starts. This assumes that `mcpo` is a Python script named `mcpo.py`. The `--host 0.0.0.0` option tells `mcpo` to listen on all network interfaces, which is necessary for accessing it from outside the container. The `--port 8000` option tells `mcpo` to listen on port 8000. **You'll need to adjust this command to match the actual command-line arguments that `mcpo` requires.** For example, you might need to specify a configuration file or other options. **How to Build and Run the Image:** 1. **Save the Dockerfile:** Save the above code as a file named `Dockerfile` in the same directory as your `mcpo` source code and `requirements.txt` (if you have one). 2. **Build the Image:** Open a terminal in that directory and run the following command: ```bash docker build -t mcpo-image . ``` * `docker build`: The Docker command to build an image. * `-t mcpo-image`: Tags the image with the name `mcpo-image`. You can choose any name you like. * `.`: Specifies that the Dockerfile is in the current directory. 3. **Run the Container:** After the image is built, run it with the following command: ```bash docker run -d -p 8000:8000 mcpo-image ``` * `docker run`: The Docker command to run a container. * `-d`: Runs the container in detached mode (in the background). * `-p 8000:8000`: Maps port 8000 on your host machine to port 8000 inside the container. This allows you to access `mcpo` from your host machine. If `mcpo` uses a different port, adjust this accordingly. * `mcpo-image`: The name of the image to run. 4. **Access `mcpo`:** Once the container is running, you should be able to access the `mcpo` server in your web browser or using `curl` at `http://localhost:8000` (or whatever port you mapped). The exact URL will depend on how `mcpo` exposes its OpenAPI endpoint. You'll likely need to consult the `mcpo` documentation to determine the correct URL. **Important Considerations and Customization:** * **`mcpo` Command-Line Arguments:** The `CMD` instruction in the Dockerfile is crucial. Make sure you replace the example command with the correct command-line arguments for `mcpo`. This might include specifying a configuration file, API keys, or other options. * **Dependencies:** Ensure that your `requirements.txt` file includes all the necessary Python packages for `mcpo`. If you're missing dependencies, the container will likely fail to start. * **Port:** Adjust the `EXPOSE` and `-p` options to match the port that `mcpo` uses. * **Volumes:** If `mcpo` needs to access files on your host machine (e.g., configuration files, data files), you can use Docker volumes to mount directories from your host machine into the container. For example: ```bash docker run -d -p 8000:8000 -v /path/to/config:/app/config mcpo-image ``` This would mount the `/path/to/config` directory on your host machine to the `/app/config` directory inside the container. * **Environment Variables:** You can use environment variables to configure `mcpo` at runtime. For example: ```dockerfile ENV API_KEY=your_api_key CMD ["python", "mcpo.py", "--api-key", "$API_KEY"] ``` Then, when you run the container, you can set the `API_KEY` environment variable: ```bash docker run -d -p 8000:8000 -e API_KEY=another_api_key mcpo-image ``` * **Logging:** Consider how `mcpo` logs its output. You might want to configure logging to a file or to standard output so that you can easily monitor the container's activity. * **Security:** If `mcpo` handles sensitive data, be sure to take appropriate security measures, such as using HTTPS, restricting access to the container, and protecting API keys. * **OpenWebUI Integration:** This Dockerfile focuses on running `mcpo`. You'll need to configure OpenWebUI to connect to the `mcpo` server. This typically involves specifying the URL of the `mcpo` server in OpenWebUI's settings. This comprehensive example should give you a solid starting point for creating a Docker image for `mcpo`. Remember to adapt it to your specific needs and consult the `mcpo` documentation for more information.

cortex-mcp

An MCP server for the Cortex observable analysis and active response engine. It enables LLMs to automate security investigations by running analyzers on observables like IPs and URLs and executing automated response actions.

CreatorOS AI

MCP server that enables AI-powered content generation in multiple formats using Google Gemini and Tavily real-time research, accessible via MCP-compatible clients.

cadex-mcp

MCP server for CAD Exchanger SDK that enables loading, inspecting, and exporting CAD models via a path-based cache.

Zoho Inventory MCP Server by CData

This project builds a read-only MCP server. For full read, write, update, delete, and action capabilities and a simplified setup, check out our free CData MCP Server for Zoho Inventory (beta): https://www.cdata.com/download/download.aspx?sku=KZZK-V&type=beta

mcp-server-steam

Integrates with Steam Web API to enable querying user profiles, game libraries, store data, and community features like reviews and workshop items.

Tesouro Nacional: Capacidade de Pagamento (CAPAG)

Enables consulting the Brazilian Treasury's Payment Capacity (CAPAG) data through an MCP server, providing official information via natural language.

jq-docs-mcp

MCP server that provides AI with documentation for 221 JointQuant API functions and 2,479 data table fields, enabling accurate code generation without hallucination.

TypeScript Extractor MCP Server

Enables to extract TypeScript methods, functions, and their relevant imports and class properties for code analysis, refactoring, and documentation.

perfex-crm-mcp

MCP server that connects AI assistants to Perfex CRM via public web forms, enabling lead creation, ticket creation, quote requests, and health checks without API keys.

Google Sheets MCP Server

Enables AI assistants to interact with Google Sheets, performing operations like creating, reading, updating, and clearing spreadsheet data.

Model Context Protocol Server

Un repositorio de estudio para cuando probé un tutorial sobre cómo construir mi propio servidor MCP.

arcgis-mckinney

Enables querying and searching City of McKinney GIS open geospatial datasets (parcels, zoning, public works) via ArcGIS Feature Services.

The Mine Works MCP servers

Seven remote MCP servers exposing 51 published Apify scrapers as agent tools: company diligence, social listening, recruiting, real estate, lead generation, e-commerce and academic research. Billed per result, and a call that returns nothing is never charged.

RepoWeaver

MCP server that builds a local code intelligence layer, letting AI agents explore call graphs, blast radius, and source slices via a single tool without external APIs.

blastradius

Analyzes npm dependency upgrades to reveal which files and functions in your codebase break, with confidence tiers and transitive call chain tracing.

kb-graph

Provides a self-tending knowledge base for AI agents, automatically harvesting session transcripts into facts and state notes, and injecting relevant context into new sessions via MCP hooks.

MCP Translation Text

Provides text translation capabilities powered by NiuTrans API with support for 455+ languages. Includes translation tools and language catalog resources for seamless integration with MCP clients.

ThingsBoard Lighting MCP Server

An MCP server that lets Claude read and switch the 3 lights in the innovation room through ThingsBoard, using natural language.

mcp-gtm

Enables LLMs to manage Google Tag Manager containers through exported JSON files, with full CRUD operations on tags, triggers, variables, and folders, plus validation and analysis tools.

mcp-entur

Provides access to Norway's nationwide public transport data (all modes) via the Entur API, enabling queries about routes, stops, and departures through natural language.

mcp-server-zenn: Unofficial MCP server for Zenn (

Espejo de

SignalSumo MCP Server

Model Context Protocol server for SignalSumo that lets Claude, Cursor, and other MCP-compatible clients read SEO data, run technical audits, research keywords, and check backlink profiles through natural-language tool calls.

Tokyo WBGT MCP Server

Provides access to Tokyo's WBGT (Wet Bulb Globe Temperature) heat index forecast and real-time data from multiple observation points using Japan's Ministry of the Environment official data for heat stroke prevention.

mcp-fbiwanted

Enables AI agents to search and retrieve details of FBI Most Wanted people via the FBI public API, including photos, aliases, crimes, last known locations, and contact tips.

Markdrop MCP Server

Connects Claude to a Markdrop knowledge base, allowing it to search and retrieve markdown documentation for context-aware development assistance.

MonkeyPlanner

Local-first kanban and approval-gate issue tracker with a native MCP server (13 tools). Humans approve; agents claim, QA, and complete issues. Single Go binary + SQLite.

my-mcp-server

Un prototipo que utiliza mcp-framework para construir herramientas para IAs.

Severalnines CCX MCP Server

Enables management of CCX database clusters through AI assistants, supporting operations such as datastore creation, scaling, and performance monitoring. It provides a comprehensive toolset for handling backups, database users, and firewall rules across various database engines including PostgreSQL, MySQL, and Redis.