ββββ ββββ ββββββββββββββ βββββββββββββββ βββ βββ βββββ βββββββββββββββββββββββββββββββββββββββββ ββββ ββββββββββββββ ββββββββββββββββββββββββ βββββββ ββββββββββββββ βββββββ βββββββββββββββ βββββ βββ βββ ββββββββββββββ βββββββββββ βββ βββ βββ ββββββββββ βββββββββββ βββMCPSpy - Real-time monitoring for Model Context Protocol communication using eBPF
MCPSpy is a powerful command-line tool that leverages eBPF (Extended Berkeley Packet Filter) technology to monitor Model Context Protocol (MCP) communication at the kernel level. It provides real-time visibility into JSON-RPC 2.0 messages exchanged between MCP clients and servers by hooking into low-level system calls.
The Model Context Protocol supports three transport protocols for communication:
- Stdio: Communication over standard input/output streams
- Streamable HTTP: Direct HTTP request/response communication with server-sent events
- SSE (Server-Sent Events): HTTP-based streaming communication (Deprecated)
MCPSpy currently supports only Stdio transport monitoring, with plans to extend support to SSE and HTTP transports in future releases.
The Model Context Protocol is becoming the standard for AI tool integration, but understanding what's happening under the hood can be challenging. MCPSpy addresses this by providing:
- π Security Analysis: Monitor what data is being transmitted, detect PII leakage, and audit tool executions
- π Debugging: Troubleshoot MCP integrations by seeing the actual message flow
- π Performance Monitoring: Track message patterns and identify bottlenecks
- π Compliance: Ensure MCP communications meet regulatory requirements
- π Learning: Understand how MCP works by observing real communications
- Linux kernel version 5.10 or later
- Root privileges (required for eBPF)
Download the latest release from the releases page:
# Set platform-aware binary name
BIN="mcpspy-$(uname -s | tr '[:upper:]' '[:lower:]')-$(uname -m | sed -e 's/x86_64/amd64/' -e 's/aarch64/arm64/')"
# Download the correct binary
wget "https://github.com/alex-ilgayev/mcpspy/releases/latest/download/${BIN}"
# Make it executable and move to a directory in your PATH
chmod +x "${BIN}"
sudo mv "${BIN}" /usr/local/bin/mcpspy
β Note: Currently supported platforms: linux-amd64, linux-arm64
First, install the required system dependencies:
sudo apt-get update
# Install build essentials, eBPF dependencies
sudo apt-get install -y clang clang-format llvm make libbpf-dev build-essential
# Install Python 3 and pip (for e2e tests)
sudo apt-get install -y python3 python3-pip python3-venv
# Install docker and buildx (if not already installed)
sudo apt-get install -y docker.io docker-buildx
MCPSpy requires Go 1.24 or later. Install Go using one of these methods:
Option 1: Install from the official Go website (Recommended)
# Download and install Go 1.24.1 (adjust version as needed)
wget https://go.dev/dl/go1.24.1.linux-amd64.tar.gz
sudo rm -rf /usr/local/go
sudo tar -C /usr/local -xzf go1.24.1.linux-amd64.tar.gz
# Add Go to PATH (add this to your ~/.bashrc or ~/.profile for persistence)
export PATH=$PATH:/usr/local/go/bin
Option 2: Install via snap
sudo snap install go --classic
Clone the repository and build MCPSpy:
# Clone the repository
git clone https://github.com/alex-ilgayev/mcpspy.git
cd mcpspy
# Build the project
make all
# Build Docker image
make image
# Or pull the latest image
docker pull ghcr.io/alex-ilgayev/mcpspy:latest
# Or pull a specific image release
docker pull ghcr.io/alex-ilgayev/mcpspy:v0.1.0
# Run the container
docker run --rm -it --privileged ghcr.io/alex-ilgayev/mcpspy:latest
# Start monitoring MCP communication
sudo mcpspy
# Start monitoring with raw message buffers
sudo mcpspy -b
# Start monitoring and save output to JSONL file
sudo mcpspy -o output.jsonl
# Stop monitoring with Ctrl+C
12:34:56.789 python[12345] β python[12346] REQ tools/call (get_weather) Execute a tool
12:34:56.890 python[12346] β python[12345] RESP OK
{
"timestamp": "2024-01-15T12:34:56.789Z",
"transport_type": "stdio",
"stdio_transport": {
"from_pid": 12345,
"from_comm": "python",
"to_pid": 12346,
"to_comm": "python"
},
"type": "request",
"method": "tools/call",
"params": {
"name": "get_weather",
"arguments": { "city": "New York" }
}
}
MCPSpy consists of several components:
- Hooks into
vfs_read
andvfs_write
kernel functions - Filters potential MCP traffic by detecting JSON patterns
- Sends events to userspace via ring buffer
- Minimal performance impact with early filtering
- Manages the lifecycle of eBPF programs and resources
- Loads pre-compiled eBPF objects into the kernel using cilium/ebpf library
- Converts raw binary events from kernel space into structured Go data types
- Validates JSON-RPC 2.0 message format
- Parses MCP-specific methods and parameters
- Correlates read operations and write operations into a single MCP message (relevant for stdio transport)
- Currently supports stdio transport (streamable HTTP/SSE planned)
- Console display with colored, formatted output
- JSONL output for programmatic analysis
- Real-time statistics tracking
# Generate eBPF bindings and build
make all
# Build Docker image
make image
MCPSpy includes comprehensive end-to-end tests that simulate real MCP communication:
# (Optional) Set up test environment
make test-e2e-setup
# Run tests (requires root privileges)
make test-e2e
The test suite includes:
- MCP server and client simulators
- Message validation against expected outputs
- Multiple message type coverage
- FS Events Buffer Size: Limited to 16KB per message. This means MCP messages larger than 16KB will be missed / ignored.
- Platform: Linux only (kernel 5.10+).
- Transport: Currently supports stdio transport only. Support for streamable HTTP and SSE transports is planned.
We welcome contributions! Feel free to open an issue or a pull request.
- User-mode code (Mainly Go): Apache 2.0 (see LICENSE)
- eBPF C programs (
bpf/*
): GPL-2.0-only (see LICENSE-BPF)