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

ktx

Skill Data & Analytics Solid
Works inClaude Code
Solid Scanned — metadata only

Enables AI agents to query data accurately and consistently through a standardized context layer, reducing hallucinations and improving reliability of analyt…

ktx is an executable context layer for data and analytics agents 🐙 Allow Claude Code, Codex, and any AI agent to query data accurately through MCP with skills, memory and a semantic layer

1,545 starsApache-2.0 (commercial OK)FreeQuick setup

Enables AI agents to query data accurately and consistently through a standardized context layer, reducing hallucinations and improving reliability of analytics workflows while maintaining audit trails.

Data engineering teams integrating Claude or other AI agents into analytics pipelines requiring governed, repeatable query execution.

Claude Code Claude Cowork Claude Chat

https://github.com/Kaelio/ktx

By Kaelio

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
npm install -g @kaelio/ktx

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:

Query my database and return accurate results without writing SQL manually
PrerequisitesNode.js with npm; your own LLM API keys or a local agent sign-in (Claude Pro/Max via Claude Code, or Codex auth) — ktx adds no usage billing of its own. Run 'ktx setup' after install to configure providers and connections.CostFree

Trust Signals Auto-scanned

Stars1,545Contributors11Last updated2026-07-19LicenseApache-2.0 (OK for commercial use)Known CVEsNone foundSources: GitHub Advisory Database + OSV.dev · Scanned 2026-08-18 · scanner v1

Community Pulse Growing

Discussed on Hacker News

2 mentions across 1 sources

Reviewer notes

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

Scored from trust signals (evidence-eval-v1): 835 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.

Things to check

  • Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.

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
4/5
Versatility
4/5
Reliability
3/5
Security
3/5
Overall score3.60 / 5.00 SolidEvaluatedJun 2026
Scored from trust signals (evidence-eval-v1): 835 GitHub stars; contributors unknown; last commit 0d ago; license Apache-2.0.

← Back to the Claude Observatory

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

Start a conversation →