Wireshark MCP Server (iflow-mcp/mixelpixx-wireshark-mcp) is an MCP server listed on the M8ven Trust Index. It scores 46 out of 100, grade D. It declares 19 tools. No publisher has claimed this listing.

D
Caution
46/100

Wireshark MCP Server

A comprehensive MCP server that provides AI assistants with professional-grade network analysis capabilities, combining Wireshark packet analysis, nmap scanning, and threat intelligence for enhanced network troubleshooting and security analysis.

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

iflow-mcp

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
⚠️
Tool descriptions don’t match what handlers do
1 tool describes read intent but its handler mutates — export_packets_csv (line 115: result = subprocess.run()
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 2 credentials: ABUSEIPDB_API_KEY, VIRUSTOTAL_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes19 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

analyze_pcap_file

Analyze an existing PCAP/PCAPNG file. Args: filepath: Path to the PCAP/PCAPNG file display_filter: Wireshark display filter (e.g., "http.request", "tcp.port == 443") max_packets: Maximum number of packets to analyze (max 1000) Returns: Packet analysis results Example: { "status": "success", "file":

get_protocol_statistics

Generate protocol hierarchy and conversation statistics from a PCAP file. Args: filepath: Path to the PCAP/PCAPNG file Returns: Protocol statistics including hierarchy and IP conversations Example: { "status": "success", "file": "/path/to/capture.pcap", "protocol_hierarchy": "...", "ip_conversations

get_capture_file_info

Get detailed information about a capture file. Args: filepath: Path to the PCAP/PCAPNG file Returns: File metadata including size, packet count, duration, etc. Example: { "status": "success", "file": "/path/to/capture.pcap", "info": "File name: ...\nFile size: ...\nPacket count: ..." }

get_network_interfaces

Get list of available network interfaces for packet capture. Returns: List of network interfaces with their names and numbers Example: { "status": "success", "interfaces": [ "1. eth0", "2. wlan0", "3. lo" ], "count": 3 }

capture_live_packets

Capture live network packets from a specified interface. Args: interface: Network interface name or number (e.g., "eth0", "1") count: Number of packets to capture (max 1000) capture_filter: BPF capture filter (e.g., "tcp port 80", "host 192.168.1.1") timeout: Capture timeout in seconds (max 60) form

export_packets_json

Export packets from PCAP to structured JSON format. Args: filepath: Path to PCAP file display_filter: Wireshark display filter max_packets: Maximum packets to export Returns: Full packet data in JSON format

export_packets_csv

Export packets to CSV format with custom fields. Args: filepath: Path to PCAP file fields: Comma-separated list of fields to export display_filter: Wireshark display filter Returns: CSV formatted packet data Example fields: - "frame.number,frame.time,ip.src,ip.dst" - "tcp.srcport,tcp.dstport,tcp.fla

convert_pcap_format

Convert PCAP file between formats. Args: filepath: Path to input PCAP file output_format: Target format ("pcap" or "pcapng") Returns: Conversion result with output file path Note: Output file is created in same directory with new extension.

follow_tcp_stream

Follow TCP stream to reconstruct conversation. Args: filepath: Path to PCAP file stream_index: TCP stream index (0-based) format: Output format ("ascii", "hex", "raw") Returns: Reconstructed TCP conversation Example: { "status": "success", "stream_index": 0, "format": "ascii", "data": "GET / HTTP/1.

follow_udp_stream

Follow UDP stream to reconstruct conversation. Args: filepath: Path to PCAP file stream_index: UDP stream index (0-based) format: Output format ("ascii", "hex", "raw") Returns: Reconstructed UDP conversation Example: { "status": "success", "stream_index": 0, "format": "ascii", "data": "DNS query dat

list_tcp_streams

Enumerate all TCP conversations in capture file. Args: filepath: Path to PCAP file Returns: List of TCP streams with endpoints and statistics Example: { "status": "success", "streams": "TCP Conversations\n192.168.1.1:50234 <-> 93.184.216.34:80 ..." }

nmap_port_scan

Scan target for open ports using nmap. Args: target: IP address, CIDR range, or hostname (e.g., "192.168.1.1", "10.0.0.0/24") ports: Port specification (e.g., "80,443", "1-1000", "22,80,443,3306") scan_type: Scan type ("connect", "syn", "udp"). Note: "syn" and "udp" require root. format: Output form

nmap_service_detection

Detect service versions on open ports. Args: target: IP address or hostname ports: Port specification (empty = detect on all open ports) Returns: Service version information Example: { "status": "success", "target": "192.168.1.1", "open_ports": [ { "port": "22", "service": "ssh", "product": "OpenSSH

nmap_os_detection

Detect operating system of target (requires root privileges). Args: target: IP address or hostname Returns: OS detection results Note: This scan requires root/administrator privileges. Example: { "status": "success", "target": "192.168.1.1", "os": { "name": "Linux 3.2 - 4.9", "accuracy": "95" } }

nmap_vulnerability_scan

Run NSE vulnerability detection scripts. Args: target: IP address or hostname ports: Port specification Returns: Vulnerability scan results with NSE script output Note: This is a longer-running scan (uses nmap --script vuln). Example: { "status": "success", "target": "192.168.1.1", "open_ports": [ {

nmap_quick_scan

Quick scan of top 100 most common ports. Args: target: IP address or hostname Returns: Quick scan results Example: { "status": "success", "target": "192.168.1.1", "open_ports": [...] }

nmap_comprehensive_scan

Comprehensive scan with OS detection, version detection, and default scripts. Args: target: IP address or hostname Returns: Comprehensive scan results Note: This is a long-running operation (may require root for some features). Example: { "status": "success", "target": "192.168.1.1", "open_ports": [

check_ip_threat_intel

Check IP addresses against threat intelligence databases. Args: ip_or_filepath: Single IP address, comma-separated IPs, or PCAP file path providers: Comma-separated providers ("urlhaus", "abuseipdb") Returns: Threat intelligence results for each IP Example: check_ip_threat_intel("1.2.3.4,5.6.7.8", "

scan_capture_for_threats

Comprehensive threat scan of PCAP file. Extracts all IPs and checks against threat intelligence, providing a summary report of malicious traffic. Args: filepath: Path to PCAP file providers: Comma-separated threat intel providers Returns: Threat analysis report Example: { "status": "success", "total

// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
🔐 secretABUSEIPDB_API_KEY"": "your_api_key_here"
🔐 secretVIRUSTOTAL_API_KEYexport ="your_api_key_here"
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

19/19 tools missing one or more hints — analyze_pcap_file (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_protocol_statistics (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_capture_file_info (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +16 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Descriptions match behaviour

1 tool describes read intent but its handler mutates — export_packets_csv (line 115: result = subprocess.run()

Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.

Tool inputs are validated

18/19 tool handlers declare input schemas (95%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tool handlers catch errors

12/19 tool handlers wrap calls in try/catch (63%)

Wrap each tool handler body in try/catch and return a structured error response.

Tests exist

No test files found

Add tests that exercise each declared tool.

Tool description accuracy

export_packets_csv: description implies read-only but handler writes/deletes/executes

Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 7 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/iflow-mcp/mixelpixx-wireshark-mcp?variant=verified)](https://m8ven.ai/mcp/iflow-mcp/mixelpixx-wireshark-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 99b4498b1db86315d1cff1d2478ef226ae66cba3
code hash: 7c0f7c880d9de9891c8e1096358a86506aaa9971eaf38ca251837c3620315756
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client