Provides tools for interacting with Cisco Catalyst Center APIs, enabling management and monitoring of Cisco network infrastructure through automatically parsed API endpoints from Swagger/OpenAPI definitions.
Provides containerized deployment of the MCP server through Docker, with configuration files and scripts for building and running the server.
Uses .env files for configuration management, storing API credentials and server settings for the MCP implementation.
Uses FastAPI to create the server endpoints that expose the MCP protocol interfaces for tool discovery and execution.
Enables LangChain agents to use Cisco Catalyst Center APIs as tools through the MCP protocol, with example client code demonstrating integration.
Integrates with OpenAI API for AI agent functionality, requiring an API key for authentication and operation with the MCP server.
Automatically parses Swagger/OpenAPI JSON files to extract API endpoints as tools, providing a standardized way to expose these endpoints to AI agents.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Cisco Catalyst Center MCP Server show me all network devices with high CPU usage"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This server implements the Model Context Protocol (MCP) for Cisco Catalyst Center APIs. It is designed to run exclusively as a Docker container.
Build and run the Docker container:
docker build -t mcp-server .
docker run -d -p 8000:8000 --env-file .env mcp-serverThe server will be available at http://<host>:8000 (replace <host> with your Docker host IP).
Related MCP server: cisco-secure-access-mcp
POST /mcp/tools: Get available tools in MCP format
POST /mcp/execute_tool/{tool_name}: Execute a specific tool with parameters
See .env for configuration options. The server expects the API definition file at the path specified by SWAGGER_JSON_PATH.
All development and testing should use a Python virtual environment (python -m venv venv).
The server is not intended to be run directly on the host.
Client scripts and instructions have been removed. This server is for containerized use only.
This server cannot be deployed
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
