p4mcp-server

Features

• Comprehensive P4 integration: Read/write tools across files, changelists, shelves, workspaces, jobs, reviews, streams, and server information.
• Code review workflows: P4 Code Review support for review discovery, voting, state transitions, commenting, and participant management.
• P4 DAM integration: Access P4 DAM assets and metadata through MCP-compatible AI assistants. Search for assets, retrieve metadata, manage reviews, create asset bundles, update asset tags, and browse projects. To learn more, see Configure P4 DAM access for P4 MCP Server in the P4 DAM documentation.
• Safety first: Read-only mode by default, ownership checks, interactive MCP elicitation (PROCEED/CANCEL) for destructive delete and obliterate operations.
• Flexible toolsets: Configure which tool categories to enable: server, files, changelists, shelves, workspaces, jobs, reviews, streams, and p4dam.
• Robust logging: Application and session logging to the logs/ directory.
• Optional telemetry: Consent-gated usage statistics. Disabled by default.
• Cross platform: Supported on macOS, Linux and Windows with pre-built binaries.

Prerequisites

• P4 Server access: Connection to a P4 Server with proper credentials
• Authentication: Valid P4 login (ticket-based or password)

System Requirements

Local P4 MCP Server Installation

If you have uv installed, you can run P4 MCP Server directly without any manual installation:

# Run the server
uvx p4mcp-server

# Check version
uvx p4mcp-server --version

# Run with arguments
uvx p4mcp-server --readonly --allow-usage

This automatically fetches and runs the latest version from PyPI. No Python virtual environment setup or dependency management needed.

Requirements:

• uv installed on your system
• Python 3.11+ (uv will handle this automatically)

Download the appropriate binary for your operating system:

• macOS: p4-mcp-server-mac.zip
• Windows: p4-mcp-server-win.zip
• Linux: p4-mcp-server-linux.zip

Extract and use the executable directly. No Python installation is required.

# macOS / Linux
unzip p4-mcp-server-mac.zip   # or p4-mcp-server-linux.zip
./p4-mcp-server --help

# Windows
Expand-Archive p4-mcp-server-win.zip -DestinationPath .
.\p4-mcp-server.exe --help

Requirements:

• Python 3.11+ (with Tkinter)

Build:

• macOS: chmod +x build.sh && ./build.sh package
• Linux: chmod +x build.sh && ./build.sh package
• Windows: build.bat package

Output:

• macOS & Linux: p4-mcp-server-<version>.tgz
• Windows: p4-mcp-server-<version>.zip

Deployment

STDIO-based deployment

Run the P4 MCP Server directly on your machine using the default STDIO transport.

Add the following to your mcp.json:

{
  "mcpServers": {
    "perforce-p4-mcp": {
      "command": "/absolute/path/to/p4-mcp-server",
      "env": {
        "P4PORT": "ssl:perforce.example.com:1666",
        "P4USER": "your_username",
        "P4CLIENT": "your_workspace",
        "P4DAM_API_KEY": "your_api_key"
      },
      "args": [
        "--readonly", "--allow-usage"
      ]
    }
  }
}

Note: This example shows explicit env values. If P4CONFIG is set, you can omit them and use the generic configuration example in the MCP client configuration section instead.

Run the P4 MCP Server from a Docker container with STDIO transport, allowing MCP clients to manage the container lifecycle.

Note: Docker-based execution is currently supported on macOS and Linux only.

Prerequisites

• Docker installed and running
• Valid P4 credentials and access to a P4 server

Pull the Docker image

docker pull ghcr.io/perforce/p4mcp-server:latest

cd /path/to/p4mcp-server
docker build -t ghcr.io/perforce/p4mcp-server .

Configure MCP Client

Add the following to your mcp.json:

{
    "servers": {
        "perforce-p4mcp-docker": {
            "command": "docker",
            "args": [
                "run", "-i", "--rm",
                "--hostname", "your-hostname",
                "-e", "P4PORT=ssl:perforce.example.com:1666",
                "-e", "P4USER=your_username",
                "-e", "P4CLIENT=your_workspace",
                "-e", "P4DAM_API_KEY=your_api_key",
                "-v", "/Users/your_username/.p4tickets:/home/mcpuser/.p4tickets:ro",
                "ghcr.io/perforce/p4mcp-server:latest"
            ]
        }
    }
}

Configuration Options

Authentication

Using P4 tickets:

# macOS/Linux
-v /Users/your_username/.p4tickets:/home/mcpuser/.p4tickets:ro

Note: Use the full path to your tickets file (not ~). After running p4 login, restart the MCP server to pick up the new ticket.

Note: By default the container starts as root, copies the bind-mounted tickets file to a location readable by the non-root mcpuser, then drops privileges (via gosu) so the server runs as mcpuser. This auto-copy lets an owner-only (0600) tickets file owned by a foreign uid work on runtimes that preserve host ownership (native Linux Docker/podman). A :ro bind mount of the ticket is supported — the file is copied, not modified in place (this is distinct from a read-only container root filesystem; see below). Note the auto-copy runs only when the container starts as root (the default); forcing a non-root uid or a read-only root filesystem changes this behavior, as described below.

Kubernetes / restricted (non-root-enforced) profiles: the image intentionally starts as root and drops to mcpuser (uid 1000) via gosu, so the server always runs non-root — both paths are supported. For runAsNonRoot / restricted PodSecurity / OpenShift restricted SCC, set securityContext.runAsUser: 1000 (and fsGroup: 1000 when mounting the ticket). In that mode the entrypoint's root-only ticket copy is skipped, so the mounted ticket must already be readable by uid 1000 (owner-matched mount, -e P4PASSWD="your_ticket_content", or podman -v <host>:/home/mcpuser/.p4tickets:U).

Read-only root filesystem (--read-only / readOnlyRootFilesystem): provide a writable/tmpfs /home/mcpuser (e.g. --tmpfs /home/mcpuser) so the ticket copy can be written; otherwise the ticket copy fails and P4 will report a normal auth error.

Using a password:

-e P4PASSWD="your_password"

Workspace Host Restrictions

⚠️ Important: Docker containers have their own hostname, which differs from your local machine. If your P4 workspace is restricted to a specific host, operations like sync will fail.

To resolve this, set the container hostname to match your workspace's host restriction:

--hostname your-hostname

To find your workspace host name:

# macOS/Linux
p4 client -o your_workspace | grep "^Host:"

**Mounting Client Root for