# kb-mcp-server

> Use this tool when you need to efficiently retrieve semantic information from large txtai embeddings databases. The kb-mcp-server solves problems related to graph-based data retrieval, providing a portable and local solution for loading and querying txtai embeddings databases in tar.gz form. It accepts database files as input and outputs relevant semantic information, making it ideal for use cases that require convenient and easy access to embedded data.

Canonical page: https://skillsregistry.net/skills/geeksfino-kb-mcp-server  
JSON: https://api.skillsregistry.net/v1/skills/geeksfino-kb-mcp-server

## Description

An MCP server aimed to be portable, local, easy and convenient to support semantic/graph based retrieval of txtai "all in one" embeddings database. Any txtai embeddings db in tar.gz form can be loaded

## Trust

- **Trust score (0–1):** 0.57
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/eo9jwi0b3o)
- **Repository:** <https://github.com/Geeksfino/kb-mcp-server>

## Use it

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": "geeksfino-kb-mcp-server"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/geeksfino-kb-mcp-server` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/geeksfino-kb-mcp-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