mcp-wireshark
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| check_installationA | Check if Wireshark/tshark is installed and return version info. |
| list_interfacesA | List all network interfaces available for packet capture. |
| read_pcapA | Read and analyze packets from a .pcap or .pcapng file. Returns a preview of up to 5 packets in JSON plus the total match count. |
| display_filterA | Apply a Wireshark display filter to a pcap file and return a preview of matching packets. |
| summarize_pcapA | Get a high-level summary of a pcap file: I/O stats, protocol hierarchy, and top IP conversations. Prefer this over read_pcap when the goal is to characterize a capture. |
| stats_by_protoB | Generate the protocol hierarchy statistics for a pcap file. |
| follow_tcpA | Follow a TCP stream by index and return its ASCII payload. |
| follow_udpA | Follow a UDP stream by index and return its ASCII payload. |
| expert_infoA | Run tshark expert analysis on a pcap file. Returns warnings, errors, and notes grouped by severity. Useful for diagnosing protocol issues without reading individual packets. |
| decode_protocolA | Extract protocol-specific fields from a pcap file using tshark '-T fields'. Pass a known protocol name to use curated defaults (supported: dns, goose, http, icmp, mms, sip, sv, tls), or supply your own 'fields' list for any other protocol. Returns a tab-separated table — much smaller than full JSON. Use a 'filter' to narrow results (e.g. only request packets, only specific stNum values). |
| protocol_statsA | Run a tshark '-z' aggregate-statistics report on a pcap file and return its parsed output. Use this for protocol-hierarchy, conversation, endpoint, and per-protocol stat tables — much more compact than per-packet JSON. Supported (protocol, variant) pairs: conv: eth, ip, ipv6, tcp, udp; dns: tree; endpoints: eth, ip, ipv6, tcp, udp; http: stat, tree; http_req: tree; io: phs, stat; rpc: srt; sip: stat; smb: srt; smb2: srt. |
| analyze_iec61850A | Analyze an IEC 61850 capture for protocol health and return a compact, worst-first OK/WARN/FAIL report per source. protocol is one of 'goose' (stNum/sqNum gaps, timeAllowedtoLive violations, state-change storms), 'sv' (smpCnt continuity, loss of time sync, confRev changes), or 'mms' (error/reject PDUs, unpaired requests, slow responses). Streams matching frames and returns a bounded summary. |
| live_captureA | Capture live network traffic from an interface. Writes to a temporary pcap that is deleted after the preview is returned. |
| export_jsonA | Export packets from a pcap file to a JSON file at output_path. Creates the output file if it does not exist; overwrites if it does. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 14 tools
Several analysis tools overlap: summarize_pcap, stats_by_proto, and protocol_stats can all produce protocol-hierarchy-style output, and read_pcap vs display_filter are close but distinguishable. The descriptions help guide selection (e.g., prefer summarize_pcap over read_pcap), but stats_by_proto in particular looks like a narrower duplicate of protocol_stats.
Most names follow a verb_noun pattern: follow_tcp, read_pcap, summarize_pcap, decode_protocol, export_json. A few are noun phrases or non-verb-led (stats_by_proto, expert_info, protocol_stats, live_capture), but the overall convention remains readable and predictable.
Fourteen tools is well within the ideal range for a packet-analysis server and covers distinct stages from setup checks and capture to analysis and export. The count is well scoped, even if a couple of analysis tools are redundant.
The surface covers installation checks, interface discovery, live capture, pcap reading/filtering, summaries, protocol statistics, stream following, field decoding, and export. Minor gaps exist, such as detailed single-packet inspection and pcap-to-pcap filtering/merging, but core workflows are covered.