Cisco Meraki MCP Server

July 28, 2026 · View on GitHub

The Cisco Meraki MCP Server connects AI agents and coding assistants directly to the Meraki Dashboard API, enabling natural-language queries and agentic network automation through a standardized interface.

Use it to build agents that answer questions about your network, generate reports, troubleshoot connectivity issues, and audit configurations—without writing custom API integration code.

Beta notice: Cisco Meraki MCP Server is currently in beta. Features, tool schemas, supported API capabilities, and client configuration may change, including in ways that are not backward compatible. Cisco reserves the right to make breaking changes during the beta period to incorporate feedback and improvements.

What Is MCP?

Model Context Protocol (MCP) is an open standard for connecting AI agents to external tools and data sources. MCP lets clients such as Claude Code, Cursor, VS Code, and Codex call structured tools at runtime, so agents can read live data rather than rely on training knowledge alone.

The Cisco Meraki MCP Server implements this standard for the Meraki Dashboard API. Your AI agent calls MCP tools; the server translates those calls into authenticated Meraki API requests and returns the results.

Choose Your Meraki MCP Deployment

Meraki MCP is available as a Cisco-hosted remote service or as a self-hosted, open-source server. Both provide the same core MCP functionality; choose the deployment model that best fits your operational and compliance requirements.

	Cisco-hosted remote MCP	Local, open-source MCP
Deployment	Cisco hosts and manages the MCP server. Connect your client to `https://mcp.meraki.com/mcp`.	Run the MCP server in your own environment.
Core functionality	Provides the Meraki MCP capabilities described in this guide.	Provides the same core Meraki MCP functionality.
Meraki environments	Supports Meraki.com only. Federal, GovCloud, and localized Meraki environments are not supported.	Can work with any Meraki environment.
Code and customization	Cisco manages the service and its implementation.	Review and customize the source code to meet your requirements.
Setup and compatibility	Follow the hosted client configuration guidance below.	Follow the local stdio setup in this README.

Important: You are responsible for any changes you make to the local, open-source MCP. Meraki does not support modified local MCP code.

Meraki MCP Terms and Policy

Your use of the Cisco Meraki MCP Server and any Cisco API leveraged by the MCP Server is governed by the Cisco Networking Model Context Protocol (MCP) Server Terms, Cisco Baseline API License Terms, Cisco Acceptable Use Policy, Cisco Meraki Cloud Service Offer Description, and Cisco General Terms.

Prerequisites

A Meraki Dashboard account
A Meraki Dashboard API key, generated in Dashboard → Organization → API & Webhooks
An MCP-compatible client, such as Claude Code, Cursor, VS Code, or Codex

Warning: The MCP server supports only read operations. However, an AI agent with a Dashboard API key may attempt to call the Dashboard API directly. If the agent receives a read-write key, those direct calls could make changes outside the MCP server. Use an API key associated with read-only Dashboard access to ensure the agent cannot make changes.

Hosted Cloud Setup

Use the hosted MCP server for the fastest setup when you do not need to run the server locally.

MCP Server URL

https://mcp.meraki.com/mcp

Authentication

The hosted server authenticates with a Meraki Dashboard API key passed as a bearer token:

Authorization: Bearer <MERAKI_DASHBOARD_API_KEY>

Before configuring Cursor, VS Code, Codex, or Claude Code, set MERAKI_DASHBOARD_API_KEY in the environment used to launch that client. Restart the client after setting or changing the variable.

export MERAKI_DASHBOARD_API_KEY="your-meraki-dashboard-api-key"

Client Configuration

Claude Desktop

Claude Desktop does not support configuring remote MCP servers through claude_desktop_config.json. Add remote servers through Settings → Connectors instead. This flow currently supports unauthenticated and OAuth-based servers; an API-key-authenticated Meraki MCP connection is not yet supported in Claude Desktop.

Claude Code

Add the following to your .mcp.json:

{
  "mcpServers": {
    "meraki": {
      "type": "http",
      "url": "https://mcp.meraki.com/mcp",
      "headers": {
        "Authorization": "Bearer ${MERAKI_DASHBOARD_API_KEY}"
      },
      "env": {
        "MERAKI_DASHBOARD_API_KEY": "${MERAKI_DASHBOARD_API_KEY}"
      }
    }
  }
}

Cursor

Add the following to your .cursor/mcp.json:

{
  "mcpServers": {
    "meraki": {
      "url": "https://mcp.meraki.com/mcp",
      "headers": {
        "Authorization": "Bearer ${env:MERAKI_DASHBOARD_API_KEY}"
      }
    }
  }
}

VS Code

Add the following to your .vscode/mcp.json to avoid hardcoding your API key:

{
  "servers": {
    "meraki": {
      "type": "http",
      "url": "https://mcp.meraki.com/mcp",
      "headers": {
        "Authorization": "Bearer ${env:MERAKI_DASHBOARD_API_KEY}"
      }
    }
  }
}

Codex

Add the following to your ~/.codex/config.toml:

[mcp_servers.meraki]
url = "https://mcp.meraki.com/mcp"
bearer_token_env_var = "MERAKI_DASHBOARD_API_KEY"

Local Stdio Setup

Use local stdio when you want the MCP server to run entirely on your machine. This setup clones the public source repository and connects your AI client to the local command.

Security note: Secure remote HTTP deployment—including TLS, certificate management, authentication, and network controls—is outside the scope of this project. For local use, use stdio or bind the server to localhost and do not allow remote connections. To expose the service on any network, including a private intranet, work with a qualified infrastructure or security professional.

Prerequisites

Python 3.14+ installed on your machine
uv installed
A Meraki Dashboard API key with access to the organizations and networks you query
- To minimize surprises, create or reuse an API key from a read-only admin, not your primary admin

Clone and install

git clone https://github.com/CiscoDevNet/meraki-mcp-official.git
cd meraki-mcp-official
uv sync

Store your API key securely

For local stdio, do not put the raw API key in your MCP client configuration, shell history, prompts, or checked-in files. Store it in your operating system's credential store, then use a small launch script that reads the key at server startup.

macOS

Store the key in Keychain:

printf "Meraki API key: "
read -r -s KEY
printf "\n"

security add-generic-password \
  -U \
  -a "$USER" \
  -s cisco-meraki-mcp-meraki-api-key \
  -w "$KEY"

unset KEY

Create a launcher:

mkdir -p "$HOME/.local/bin"
cat > "$HOME/.local/bin/cisco-meraki-mcp-stdio" <<'EOF'
#!/bin/zsh
KEYCHAIN_SERVICE="cisco-meraki-mcp-meraki-api-key"
MERAKI_DASHBOARD_API_KEY="$(security find-generic-password \
  -a "$USER" \
  -s "$KEYCHAIN_SERVICE" \
  -w)"
export MERAKI_DASHBOARD_API_KEY
exec uv --directory "/path/to/meraki-mcp-official" \
  run cisco-meraki-mcp
EOF
chmod +x "$HOME/.local/bin/cisco-meraki-mcp-stdio"

Linux

On Linux desktops that support Secret Service, store the key with secret-tool:

secret-tool store \
  --label="Meraki MCP API key" \
  service cisco-meraki-mcp \
  username "$USER"

Create a launcher:

mkdir -p "$HOME/.local/bin"
cat > "$HOME/.local/bin/cisco-meraki-mcp-stdio" <<'EOF'
#!/bin/sh
MERAKI_DASHBOARD_API_KEY="$(secret-tool lookup \
  service cisco-meraki-mcp \
  username "$USER")"
export MERAKI_DASHBOARD_API_KEY
exec uv --directory "/path/to/meraki-mcp-official" \
  run cisco-meraki-mcp
EOF
chmod +x "$HOME/.local/bin/cisco-meraki-mcp-stdio"

For headless Linux, use your organization's secret manager or service manager to inject MERAKI_DASHBOARD_API_KEY into the MCP server process while keeping it out of client configuration and logs.

Windows

Use Microsoft SecretManagement with the local SecretStore vault:

Install-Module Microsoft.PowerShell.SecretManagement -Scope CurrentUser
Install-Module Microsoft.PowerShell.SecretStore -Scope CurrentUser
Register-SecretVault `
  -Name LocalStore `
  -ModuleName Microsoft.PowerShell.SecretStore `
  -DefaultVault

$apiKey = Read-Host "Meraki API key" -AsSecureString
$secretName = "cisco-meraki-mcp-meraki-api-key"
Set-Secret -Name $secretName -Secret $apiKey
Remove-Variable apiKey

Create cisco-meraki-mcp-stdio.ps1:

$secretName = "cisco-meraki-mcp-meraki-api-key"
$env:MERAKI_DASHBOARD_API_KEY = Get-Secret -Name $secretName -AsPlainText
uv --directory "C:\path\to\meraki-mcp-official" `
  run cisco-meraki-mcp

Configure your MCP client to use the launcher

{
  "mcpServers": {
    "cisco_meraki_mcp": {
      "command": "/path/to/cisco-meraki-mcp-stdio"
    }
  }
}

For VS Code, use the same server entry beneath servers in .vscode/mcp.json. For Windows clients, use PowerShell to run the launcher:

{
  "mcpServers": {
    "cisco_meraki_mcp": {
      "command": "pwsh",
      "args": [
        "-NoProfile",
        "-File",
        "C:\\path\\to\\cisco-meraki-mcp-stdio.ps1"
      ]
    }
  }
}

For Codex on macOS or Linux, edit ~/.codex/config.toml:

[mcp_servers.cisco_meraki_mcp]
command = "/path/to/cisco-meraki-mcp-stdio"

For Codex on Windows:

[mcp_servers.cisco_meraki_mcp]
command = "pwsh"
args = [
  "-NoProfile",
  "-File",
  "C:\\path\\to\\cisco-meraki-mcp-stdio.ps1",
]

Usage

Example Workflow

Tell your AI assistant:

"Find the Meraki API capability for listing wireless SSIDs on a network."

The assistant should:

Call semantic_search with your natural-language request.
Review the ranked capabilities and select the best capability_id.
Call execute_api with that capability_id and any required parameters.

semantic_search(query="list wireless SSIDs", top_k=5)
execute_api(
  capability_id="getNetworkWirelessSsids",
  parameters={"networkId": "N_123"}
)

execute_api validates the selected capability, passes the request through the Meraki Dashboard SDK using the configured MERAKI_DASHBOARD_API_KEY, and returns the live Dashboard API response.

Capabilities

Tools

Tool	Purpose
`semantic_search`	Search Meraki API capabilities with a natural-language query and return ranked `capability_id` results.
`execute_api`	Validate and execute a selected read-only API capability.

Resources

Resource URI	Content
`info://service`	Service metadata

Rate Limits

The server respects the Meraki Dashboard API rate limits:

Default limit: 10 requests per second per organization
Backoff behavior: The server automatically retries with exponential backoff on 429 Too Many Requests responses.
Per-organization isolation: Multi-organization sessions do not share a single rate-limit bucket.

Limitations (Current Release)

Read-only: Write operations are not supported.
API-key authentication only: OAuth is not yet supported; a bearer token is required for the hosted service.
Hosted service: The Cisco-hosted service supports Meraki.com only. Federal, GovCloud, and localized Meraki environments are not supported. The local, open-source server can work with any Meraki environment.

NOTICE describes the Cisco Meraki and API terms that apply when this software communicates with Meraki. Those terms are separate from the open-source license governing this code.
SECURITY explains how to report a security issue privately.
CONTRIBUTING describes the project's issue and contribution policy.
For Dashboard API help, use Meraki API docs or your normal Meraki support channel.

Cisco Meraki MCP Server

What Is MCP?

Choose Your Meraki MCP Deployment

Meraki MCP Terms and Policy

Prerequisites

Hosted Cloud Setup

MCP Server URL

Authentication

Client Configuration

Claude Desktop

Claude Code

Cursor

VS Code

Codex

Local Stdio Setup

Prerequisites

Clone and install

Store your API key securely

macOS

Linux

Windows

Configure your MCP client to use the launcher

Usage

Example Workflow

Capabilities

Tools

Resources

Rate Limits

Limitations (Current Release)

Troubleshooting

Dashboard API Key Errors

Local Install Errors

Client Cannot Find the Server

License

Policies and Support