# local-document-rag-agent

> Use this tool when you need to answer questions from local documents, such as Word and PDF files, by searching a vector index of their contents. It solves problems of information retrieval and question answering from local document collections, providing relevant answers based on the document contents. The tool takes local documents as input and outputs relevant answers to user queries, ideal for use cases where offline access to document information is required.

Canonical page: https://skillsregistry.net/skills/iupulk-local-document-rag-agent  
JSON: https://api.skillsregistry.net/v1/skills/iupulk-local-document-rag-agent

## Description

MCP server enabling Claude Desktop to answer questions from local Word and PDF documents by searching a vector index built from their contents.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/jk496xspah)
- **Repository:** <https://github.com/iupulk/local-document-rag-agent>

## 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": "iupulk-local-document-rag-agent"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/iupulk-local-document-rag-agent` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/iupulk-local-document-rag-agent/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