# smart-search

> Use this tool when you need to perform semantic searches on local PDF and DOCX documents without relying on cloud services or GPU power. It solves problems of information retrieval and knowledge management by enabling structure-aware parsing and vector storage for efficient querying. The smart-search tool takes in PDF and DOCX files as input and outputs relevant search results through a Claude Code interface.

Canonical page: https://skillsregistry.net/skills/ekmungi-smart-search  
JSON: https://api.skillsregistry.net/v1/skills/ekmungi-smart-search

## Description

A local-first MCP server that enables semantic search over PDF and DOCX documents using structure-aware parsing and vector storage. It allows users to query their local knowledge base through Claude Code without cloud dependencies or GPU requirements.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/rjwcl88qot)
- **Repository:** <https://github.com/ekmungi/smart-search>

## 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": "ekmungi-smart-search"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ekmungi-smart-search` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ekmungi-smart-search/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