Install Kāhea in Claude Code
MCP Bundle (.mcpb)
curl -LO https://github.com/copyleftdev/kahea/releases/download/v0.3.1/kahea-mcp-Linux-X64.mcpbDownload kahea-mcp-Linux-X64.mcpb and double-click it to install in Claude Desktop.MCP Bundles install in one click in Claude Desktop. Download the file, then open it.
MCP Bundle (.mcpb)
curl -LO https://github.com/copyleftdev/kahea/releases/download/v0.3.1/kahea-mcp-Windows-X64.mcpbDownload kahea-mcp-Windows-X64.mcpb and double-click it to install in Claude Desktop.MCP Bundles install in one click in Claude Desktop. Download the file, then open it.
MCP Bundle (.mcpb)
curl -LO https://github.com/copyleftdev/kahea/releases/download/v0.3.1/kahea-mcp-macOS-ARM64.mcpbDownload kahea-mcp-macOS-ARM64.mcpb and double-click it to install in Claude Desktop.MCP Bundles install in one click in Claude Desktop. Download the file, then open it.
Frequently asked questions
What does the Kāhea MCP server do?
Deterministic HTTP/WebSocket testing and policy-gated API execution for AI agents.
Is the Kāhea MCP server free?
Yes, most likely. Open source and no paid account or API key is mentioned in the listing. Check the provider for current pricing.
Does Kāhea run locally or remotely?
Local. Runs on your machine (stdio). You install it with npx, uvx, Docker or from source.
How do I add Kāhea to Claude Code?
Run: curl -LO https://github.com/copyleftdev/kahea/releases/download/v0.3.1/kahea-mcp-Linux-X64.mcpb
More ai agents & coding agents MCP servers
View allKampung
jztan/kampung-mcp
Messaging between coding-agent sessions on different machines, through a server you host.
jsonloupe
priyanshuN/jsonloupe
Open huge JSON locally and give agents its shape, queries and exact values, never the whole blob.
Kasbah Core
Al-Adnane/Kasbah-Core
Governance layer for agentic AI — signed, verifiable receipts for every agent action.
JobScout
SarutobiSasuke8/jobscout-mcp
Multi-source job discovery, deduplication and AI/Web3 classification for AI agents.
Layoza
layoza/layoza
Design systems, layout and motion guidance for AI agents, plus headless Chromium visual QA.
Inspectrum
yannmenec/inspectrum
Review coding-agent plans on demand with peer models, attributed findings, and a structured verdict.