# Kumbuka

> Kumbuka — ai-kumbuka-kumbuka-server. Use this tool when you need to manage and govern knowledge for your AI assistants, ensuring data accuracy and auditability. Kumbuka solves the problem of maintaining trustworthy and transparent AI training data, allowing teams to curate and self-host their knowledge base. It provides a controlled interface for inputting and outputting governed knowledge, making it ideal for use cases requiring high data integrity and compliance.

Canonical page: https://skillsregistry.net/skills/ai-kumbuka-kumbuka-server  
JSON: https://api.skillsregistry.net/v1/skills/ai-kumbuka-kumbuka-server

## Description

Governed, auditable knowledge your team curates for its AI assistants, self-hostable

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-09-28

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/ai.kumbuka%2Fkumbuka-server)
- **Repository:** <https://github.com/kumbuka-ai/kumbuka>

## Use it

MCP endpoint published by the skill: `https://mcp.kumbuka.ai/mcp`

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "ai-kumbuka-kumbuka-server"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ai-kumbuka-kumbuka-server` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ai-kumbuka-kumbuka-server/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt