Is Kawa Code MCP safe to install?
codeawareness · Dev tools · stdio (local process)
Intent tracking, decision recording, and team coordination for AI coding assistants
Capabilities
What Kawa Code MCP declares it can do
A server's blast radius is the most powerful thing each of its tools can do. This grades the tools it declares, read-only, not whether it is secure.
- Execute0
- Delete0
- Write1
- Read16
- mediumTool input schema asks for a credential×2
- mediumTool declares a high-privilege capability
Tools
Every tool Kawa Code MCP exposes
17 tools
Control
Govern Kawa Code MCP with AxioRank
Installed as-is, all 17 of Kawa Code MCP's tools are callable by your agent without restriction, including any that write, delete, or execute.
Flip the switch to see the policy AxioRank would apply.
Advisories
Informational content flags
Keyword matches in tool descriptions and schemas. These are shown for transparency and are not part of the grade.
- highShell/command injection×3
- highCredential / secret access capability×2
- highSQL DELETE/UPDATE without WHERE×2
Install
Add Kawa Code MCP to your client
Drop this into your MCP client config (Claude Desktop, Cursor, and others).
{
"mcpServers": {
"ai-kawacode-mcp": {
"command": "npx",
"args": [
"-y",
"@kawacode/mcp@5.0.2"
]
}
}
}Embed
Show the grade in your README
[](https://axiorank.com/mcp-index/ai-kawacode-mcp)Directory
More Dev tools servers
How it works
About this grade
The grade reflects the blast radius of what Kawa Code MCP declares it can do, read-only, not whether it is secure or trustworthy, and not a judgment of the vendor. Maintain this server? Claim this listing or request a re-scan. See the methodology.
Email me this scorecard
Get the Kawa Code MCP grade in your inbox.
Let your agents use Kawa Code MCP safely
Route this server through AxioRank to allowlist its tools, hold risky calls for approval, and keep a signed audit trail of every action.
Start free