BrowseFull catalogOutcomesSolve a specific problemRolesStack by teamTrustFilter by risk tier
← Back to the Claude Observatory

kimbap

Skill Development Poor
Works inClaude Code
Poor Scanned — metadata only

AI agents are powerful but sandboxed — they cannot interact with arbitrary CLIs or local tools without custom integration.

Wraps REST APIs, CLI tools, and macOS apps into secure CLI commands an AI agent can call. You define a service in one YAML file (or generate it from an OpenAPI spec); credentials are injected outside the agent process so they never enter the agent's context. Ships built-in service definitions for GitHub, Slack, Stripe, kubectl, Docker, and dozens more, and connects to Claude Code via 'kimbap agents setup'.

16 starsFreeQuick setup
Below standard — Significant caveats apply. Not recommended without careful review of the security and evaluation sections.

AI agents are powerful but sandboxed — they cannot interact with arbitrary CLIs or local tools without custom integration. Kimbap wraps any CLI into an agent-accessible tool with built-in security, removing the integration bottleneck.

Developers who need their AI agents to call internal CLIs, scripts, or local tools securely without writing custom MCP server code.

Claude Code Claude Cowork Claude Chat

https://github.com/dunialabs/kimbap

By dunialabs

How to Get It

Option 1: Claude Desktop App (Code Mode)Click the + button next to the prompt box → PluginsAdd plugin. Search and click Install. Skills work in Claude Code only.
Option 2: Paste into Claude CodeCopy the command below and paste it into your conversation. Claude will install it.
Command
brew install dunialabs/kimbap/kimbap

Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.

First thing to try

After installing, paste this into Claude:

Help me wrap any CLI tool into a secure agent-callable interface
PrerequisitesAfter installing the binary, run 'kimbap init --services select' to pick services, then 'kimbap agents setup' to connect Claude Code or other agents.CostFree

Trust Signals Auto-scanned

Stars16Contributors3Last updated2026-04-20Known CVEsNone foundSources: GitHub Advisory Database + OSV.dev · Scanned 2026-08-03 · scanner v1

Reviewer notes

Auto-scanned review. These are observations, not a security certification.

catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 16 GitHub stars; 3 contributors; last commit 83d ago; license no license.

Things to check

  • Recently discovered. Looks promising but has limited community feedback so far.

How to evaluate tools before deploying →

Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.

Evaluation

Ease of Use
1/5
Versatility
2/5
Reliability
4/5
Security
3/5
Overall score2.30 / 5.00 PoorEvaluatedJul 2026
catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 16 GitHub stars; 3 contributors; last commit 83d ago; license no license.

← Back to the Claude Observatory

Rolling Claude out in your org? Let's talk.

Start a conversation →