#3535th of 111 in MCP servers for developers
kubeshark
eBPF network traffic indexing for Kubernetes, with an MCP server for AI agents
Live demo ↗
(opens in a new tab)Documentation ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 12.1k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Go
11,805 on 21 Apr 202612,135 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Kubeshark captures and indexes cluster-wide traffic at the kernel level with eBPF, parses L7 protocols such as HTTP, gRPC, Redis, Kafka and DNS, and decrypts TLS without key management. It offers a web dashboard, a workload dependency map, a CEL-based filter language (KFL) and PCAP export for Wireshark. An MCP server and Claude Code skills let AI agents query traffic for root cause analysis.
Who it is for: SREs and platform engineers debugging Kubernetes network traffic
Strengths
- eBPF TLS/mTLS decryption without sidecars or key management
- Retrospective PCAP export by time, node, workload and IP, with S3, Azure Blob or GCS storage
- MCP server plus Network RCA and KFL skills installable as a Claude Code plugin
- Parses HTTP, gRPC, GraphQL, Redis, Kafka and DNS with no code instrumentation
Weaknesses
- Only useful on Kubernetes clusters; no standalone or non-Kubernetes mode is described
- Kernel-level capture on every node; resource overhead is not documented in the README
- Port-forward setup is not for production; an ingress controller is recommended
- KFL is a custom query language that users must learn to filter effectively
What it needs
- no GPU
- Needs Kubernetes, Helm
- Models: MCP-compatible assistants (Claude Code, Cursor, Copilot)
- port 8899
Quick answers
Is kubeshark open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Also in MCP servers for developers
See all 111| Rank | Project | Score |
|---|---|---|
| 1 | gitnexusCode knowledge graph exposed to coding agents through MCP tools | 96 out of 100 |
| 2 | codegraphLocal code knowledge graph that coding agents query over MCP | 95 out of 100 |
| 3 | playwright-mcpMCP server that lets LLMs drive a browser through Playwright accessibility snapshots | 92 out of 100 |
| #4 | code-review-graphLocal Tree-sitter code graph that gives coding assistants review context over MCP | 92 out of 100 |
| #5 | serenaMCP server giving coding agents symbol-level code search, editing and refactoring | 91 out of 100 |