Meraki Magic MCP is an MCP server that integrates Cisco's Meraki Dashboard API with Model Context Protocol clients such as Claude Desktop and Cursor. Built in Python, it serves network administrators, DevOps engineers, and IT specialists who monitor and administer Meraki environments. The server allows language models to discover networks, manage wireless SSIDs, configure switch ports, analyze network clients, inspect firewall rules, and pull real-time health data across an organization. It provides two operational modes: a curated manual version with type-safe schema coverage for forty common endpoints, and a dynamic version exposing over eight hundred endpoints mapped directly from the Meraki Python SDK. Built-in performance optimizations include response caching, automatic retries, rate-limiting handlers, and a read-only safety setting that prevents unintended modifications to production network topologies.
Category: Cloud & Infrastructure
Tags: cisco, dashboard, infrastructure, meraki, networking
bash git clone https://github.com/CiscoDevNet/meraki-magic-mcp-community.git cd meraki-magic-mcp-community 2. Create and activate a Python virtual environment, then install dependencies: bash python3 -m venv .venv source .venv/bin/activate pip install -r requirements.txt 3. Open your Claude Desktop configuration file (claude_desktop_config.json) and configure the server: json { "mcpServers": { "Meraki_Magic_MCP": { "command": "/path/to/meraki-magic-mcp-community/.venv/bin/fastmcp", "args": [ "run", "-t", "stdio", "/path/to/meraki-magic-mcp-community/meraki-mcp-dynamic.py" ], "env": { "MERAKI_API_KEY": "your_api_key_here", "MERAKI_ORG_ID": "your_org_id_here", "MERAKI_BASE_URL": "https://api.meraki.com/api/v1", "READ_ONLY_MODE": "true" } } } } 4. Restart Claude Desktop completely to verify server connectivity.Part of MCP Servers
Clone the repository, create a Python virtual environment, install requirements using pip, and add the server definition to your Claude Desktop configuration. Supply your Meraki API key, Organization ID, and base URL in the environment block.
The manual mode exposes forty curated, type-safe endpoints with custom schemas. The dynamic mode exposes over eight hundred endpoints by dynamically wrapping the Meraki Python SDK, enabling full coverage of available Meraki Dashboard API methods.
Yes, but it runs in read-only mode by default to prevent unintended changes. To execute write or delete actions, set READ_ONLY_MODE to false and supply required confirmation parameters for destructive commands.
The server supports local stdio transport for client apps like Claude Desktop and Cursor. It also supports remote StreamableHTTP transport via standalone Python execution or Docker deployment for shared team use.
Yes, Meraki Magic MCP is an open-source project hosted on GitHub and available under an open-source repository license for community contributions and use.