io.github.bx33661/wireshark-mcp

Wireshark MCP

Give your AI assistant a packet analyzer.

Drop a .pcap file, ask questions in plain English — get answers backed by real tshark data.

English • 中文 • Docs • Changelog • Roadmap • Contributing

What is this?

An MCP server that wraps tshark (and optional Wireshark suite tools) into a structured analysis interface. Works with Claude Desktop, Claude Code, Cursor, VS Code, and 18+ other MCP clients.

You:    "Find all DNS queries going to suspicious domains in this capture."
Claude: [calls wireshark_extract_dns_queries → wireshark_detect_dns_tunnel]
        "Found repeated high-entropy DNS queries consistent with tunneling: ..."

Install

Claude Code / Codex plugin route

Prerequisites: uv and Wireshark CLI (tshark). The plugin includes this project and both skills; the client runs the locked Python project through uv over stdio. It does not install Wireshark or capture drivers.

From a checkout containing these plugin manifests, choose your client:

# Codex
codex plugin marketplace add .
codex plugin add wireshark-mcp@wireshark-mcp

# Claude Code
claude plugin marketplace add .
claude plugin install wireshark-mcp@wireshark-mcp

See plugin distribution for local installation, old-version refresh, environment settings and the GitHub entrypoint after publication. Choose this route or the traditional registration route below, not both.

Traditional Python package route

Prerequisites: Python 3.10+ and Wireshark with tshark on PATH.

Wireshark MCP 3.0 uses the stable MCP Python SDK 2.x line (mcp>=2.1.1,<3).

pip install wireshark-mcp
wireshark-mcp install   # choose from detected MCP clients

For scripts/non-interactive terminals, select clients explicitly. Preview before installing into the current project:

wireshark-mcp install --client codex --scope project --dry-run
wireshark-mcp install --client codex --scope project

The default scope is global. Repeat --client or explicitly use --client all. Restart the client to load configuration. See the installation guide for updates, removal, backups and exit codes.

The project also ships MCP and full TShark CLI analysis skills; see skill discovery and usage.

Run wireshark-mcp doctor if anything looks off. See docs/manual-configuration.md for manual setup or platform-specific notes.

Quick Start

Point your AI client at a .pcap file and try:

Analyze capture.pcap using the Wireshark MCP tools.
Start with wireshark_open_file, then run wireshark_quick_analysis.
Use wireshark_aggregate for any capture-wide count or distribution.
Write findings to report.md.

Tools

54 tools, each backed by real tshark output — organized into categories:

One tool covers 25 protocols rather than 25 tools covering one each: wireshark_analyze_protocol takes a protocol argument (tls_handshakes, mqtt, modbus, s7comm, zigbee, wifi, rtp, kerberos, …) and applies the right fields and display filter for it. The field names are the point — s7comm.param.item.dbnum is not something a caller should have to guess, and a wrong guess returns an empty result that reads like a clean capture.

The server starts with only tshark required. Optional tools (capinfos, mergecap, editcap, dumpcap, text2pcap) are auto-detected and enable extra features when present.

Context cost

The tool list travels in the prompt prefix of every request your client sends, so its size is a fixed per-request cost. The default surface is ~23 KB — about 9 KB of parameter schema, 5 KB of descriptions, and 3 KB of read/write annotations — and it is byte-identical across restarts so clients can cache the prefix rather than re-reading it each session.

If your client never captures live traffic or writes pcaps, --profile advertises less:

wireshark-mcp serve --profile core

Runtime prompts and protocol recommendations respect the selected profile. Static guides may describe full-only workflows, but the server never recommends an excluded tool during capture discovery.

Tool results are bounded too, since a result stays in the conversation for the rest of the session. Output over 8000 characters is truncated head-and-tail with a marker, and the tool's offset / limit / display_filter parameters are the way to page through the rest. Raise or lower the ceiling with:

export WIRESHARK_MCP_MAX_RESULT_CHARS=16000

Every tool also declares whether it reads or writes, so clients can auto-approve the 41 read-only analysis tools and still prompt for the 12 that create files (live capture, merge, filter-save, editcap, text2pcap, frame extract, object export, case files). wireshark_index is marked non-destructive: it writes only the server's own index cache.

Since 3.0, those tools fail closed until WIRESHARK_MCP_ALLOWED_DIRS names existing directories. Remote HTTP/SSE binding also stays loopback-only unless --allow-insecure-http is explicitly supplied behind a trusted authenticated TLS proxy. See the 3.0 security migration guide.

Documentation

Development

pip install -e ".[dev]"
pytest tests/ -v
ruff check src/ tests/

See CONTRIBUTING.md for the full guide.

MIT License · Report a Bug