# svdb-mcp

> svdb-mcp — nelson-demarchi-svdb-mcp. Use this tool when you need to perform local semantic searches over Markdown files, enabling large language models (LLMs) to access and query your repository through an MCP server. It solves the problem of efficiently searching and retrieving relevant information from Markdown files, leveraging Ollama for embedding generation. Ideal for use cases where you have a git repository of Markdown files and want to enhance LLM-based search capabilities.

Canonical page: https://skillsregistry.net/skills/nelson-demarchi-svdb-mcp  
JSON: https://api.skillsregistry.net/v1/skills/nelson-demarchi-svdb-mcp

## Description

Local semantic search over your Markdown files, exposed to an LLM as an MCP server. Embeddings run on Ollama.

## Trust

- **Trust score (0–1):** 0.93
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/Nelson-Demarchi/svdb-mcp)

## 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": "nelson-demarchi-svdb-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/nelson-demarchi-svdb-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/nelson-demarchi-svdb-mcp/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