Get up and running
in minutes.

Prerequisites

Installation

git clone https://github.com/Mats2208/MCP-Packet-Tracer.git
cd MCP-Packet-Tracer

pip install -e .

claude mcp add --scope user --transport stdio packet-tracer -- python -m packet_tracer_mcp --stdio

Run the Server

Want one shared instance for multiple clients? Run it yourself in streamable-HTTP mode:

$ python -m packet_tracer_mcp
INFO  Packet Tracer MCP v0.4.0
INFO  Transport: streamable-http
INFO  Listening on http://127.0.0.1:39000/mcp

Then point any client at http://127.0.0.1:39000/mcp.

Connect a Client

{
  "servers": {
    "packet-tracer": {
      "type": "stdio",
      "command": "python",
      "args": ["-m", "packet_tracer_mcp", "--stdio"]
    }
  }
}

{
  "mcpServers": {
    "packet-tracer": {
      "command": "python",
      "args": ["-m", "packet_tracer_mcp", "--stdio"]
    }
  }
}

On Windows, if your client can't spawn the server, use the full path to python.exe in the command field.

Your First Topology

Once connected, ask your AI agent to build a topology. You can also call tools directly:

Quick Build (one-shot)

pt_full_build(
  routers=2,
  pcs_per_lan=2,
  dhcp=True,
  routing="ospf",
  has_wan=True
)

# Returns: plan + script + configs + explanation

Step by Step

# 1. Generate plan
plan = pt_plan_topology(routers=2, pcs_per_lan=2, routing="static")

# 2. Validate
pt_validate_plan(plan)

# 3. Auto-fix if needed
pt_fix_plan(plan)

# 4. Generate artifacts
pt_generate_script(plan)    # topology build script (JS)
pt_generate_configs(plan)   # IOS CLI configs

# 5. Get explanation
pt_explain_plan(plan)       # Natural language summary

Export to Files

# Save everything to a directory
pt_export(plan, path="./my_lab/")

Live Deploy Setup

1

Install the MCP Control Center extension (one-time)

Download the latest .pts (e.g. V4.0.pts) from Releases, then in Packet Tracer:

Extensions → Scripting → Configure PT Script Modules → Add… → select the .pts

This installs our own extension — you do not need any third-party tool.

# Check the bridge — should report ACTIVE and CONNECTED
pt_bridge_status()

# Deploy a plan in real-time
pt_live_deploy(plan)

Project Management

Save and load topologies for later reuse.

# List saved projects
pt_list_projects()

# Load a previously saved project
pt_load_project("my_lab")

# Export creates a project automatically
pt_export(plan, path="./my_lab/")

Troubleshooting