Cisco APIC

Provides a local MCP server that interfaces with Cisco APIC, exposing tools to manage and query APIC resources.

python

9

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "datacenter-mcp_server_for_cisco_aci": {
      "command": "C:\\Users\\cpaggen\\.local\\bin\\uv.EXE",
      "args": [
        "run",
        "--with",
        "mcp[cli]",
        "mcp",
        "run",
        "C:\\MCP\\app\\main.py"
      ]
    }
  }
}

You run an MCP server that provides a lightweight bridge between a Cisco APIC controller and MCP clients. It operates in STDIO mode for local execution, exposing a couple of tools to interact with APIC while letting you configure credentials and runtime behavior via environment variables.

How to use

You connect an MCP client to the server to perform actions against the Cisco APIC. Use the MCP client’s built-in commands to start tasks, issue queries, or trigger APIC operations. The server is designed for local development and testing, so you run it on your machine or within a local tooling environment. When you start the server, your MCP client can send requests that the server translates into APIC API calls and returns results back to you.

How to install

Prerequisites include having a runtime suitable for executing the MCP server and the MCP client tooling. You will also need access credentials for the APIC controller stored in a local environment file.

Install the MCP client tooling locally so you can invoke the server from your development environment.

Install the client via one of these options:

Additional setup notes

Configure APIC credentials in your local environment so the server can authenticate with the APIC controller. The credentials are expected to reside in a local environment file and can be referenced by the server at runtime.

Optionally run the server using a local runtime such as UV with a command that starts the MCP server script. If you plan to deploy or test in a container, you can adapt to a containerized workflow but ensure the same STDIO-based invocation remains available.

Config example for local STDIO setup

{
  "mcpServers": {
    "cisco_apic": {
      "type": "stdio",
      "command": "C:\\Users\\cpaggen\\.local\\bin\\uv.EXE",
      "args": [
        "run",
        "--with",
        "mcp[cli]",
        "mcp",
        "run",
        "C:\\MCP\\app\\main.py"
      ]
    }
  }
}

Troubleshooting and tips

If you encounter connection issues, verify that the UV runtime is available on your path and that the APIC credentials in your local environment file are correct. Ensure you are using the STDIO-based invocation and that the path to the Python script is accessible from the environment running the MCP server. For debugging, run the command block shown above in a shell to confirm the server starts and listens for MCP client connections.

Notes on deployment and security

Keep APIC credentials secure and limit access to the local environment where the MCP server runs. If you move to containerized workflows, mirror the same STDIO invocation and mount the environment file into the container so the server can read credentials.