cncf / cncf/mentoring

[CNCF LFX Proposal] Kmesh Develop MCP Server for AI-Native Kmesh Service Mesh Management

Open
#2,005 14 comments 0 reactions 0 assignees View on GitHub
2026 CNCF Approved Exported lfx mentorship Maintainer/Contribex Approved Mentors Confirmed Proposal Term 3: Sept-Nov Validation Passed
Dominant language
JavaScript
Stars
3.1k
Forks
816
Avg merge
12h 32m
Merged PRs (30d)
8

Description

### CNCF Project

Kmesh

### Term

2026 Term 3 (Sep-Nov)

### Program Name

Develop MCP Server for AI-Native Kmesh Service Mesh Management

### Program Description

## Description:

Build a Model Context Protocol (MCP) server that exposes Kmesh's capabilities as callable tools for AI agents (Claude, Cursor, GitHub Copilot). The MCP server acts as a middle layer between AI tools and Kmesh infrastructure, enabling natural language queries like "What services are running?" or "Why is service A not reaching service B?" instead of requiring users to learn complex `kmeshctl` commands, xDS APIs, and eBPF internals.

## Expected Outcome:

- **MCP Server** — Go-based, 10 core tools, MCP v1.0+ compliant (HTTP/SSE transport), under `mcp/` directory
- **Integration** — Makefile targets (`make mcp-server`, `make mcp-test`, `make mcp-image`), container image
- **Testing** — Unit tests (>80% coverage), integration tests, E2E tests, MCP protocol compliance tests
- **Documentation** — User guide, developer guide (architecture + adding new tools), AI client setup examples (Claude Desktop, Cursor, Copilot)
- **Community** — Blog post on kmesh.net, demo video showing AI agents interacting with Kmesh, community meeting presentation
- **Stretch Goals** — 5 additional tools (total 15), read-write mode with safeguards, `kmeshctl mcp serve` subcommand, MCP resource templates

### Technologies

go/kubernetes/RUST API/MCP

### Skills same as Technologies?

- [x] Yes, the required skills are the same as the technologies listed above.

### Required/Desirable Skills

_No response_

### Mentors

Yash Israni | @yashisrani | imailyash57@gmail.com | yashisrani
Sumit Goyal | @itvi-1234 | sumit.goyal.cse@gmail.com | sumit15012005

### Upstream Issue URL

https://github.com/kmesh-net/kmesh/issues/1800

### Application Prerequisites

- [x] Resume
- [x] Cover Letter
- [ ] School Enrollment Verification
- [ ] Participation Permission from school or employer
- [ ] Coding Challenge
- [ ] Custom Prerequisite (fill in details below)

### Coding Challenge URL

_No response_

### Custom Prerequisite Name

_No response_

### Custom Prerequisite Description

_No response_

### Custom Prerequisite — File Upload

- [ ] Yes — completion of this task requires the mentee to submit a file.

---
**LFX program:** [CNCF - Kmesh: Develop MCP Server for AI-Native Kmesh Service Mesh Management (2026 Term 3)](https://mentorship.lfx.linuxfoundation.org/project/267f9270-0d36-4999-bdf5-c942b95c8e7a)

Contributor guide

Open the contributing guide

Research direction

Start by reading the upstream Kmesh issue 1800 and the proposal requirements for the mcp/ directory. Review the planned Makefile targets and the MCP, Kubernetes, and Kmesh integration boundaries before defining the ten core tools. Done means a compliant Go MCP server, integration and end-to-end tests, container support, and the listed user and developer documentation.

Written by the indexing model from the issue text.

Assessment

Tech stack
go, kubernetes, rust
Domain
ai, devops, networking
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.