# opencode-document-rag-mcp

> opencode-document-rag-mcp — humbertolvarona-opencode-document-rag-mcp. Use this tool when you need to perform local semantic searches on various document formats, such as PDF, DOCX, PPTX, and EPUB, and require structure-aware section retrieval with tables and equations. It solves problems related to document indexing, search, and retrieval by converting documents to Markdown and indexing them in ChromaDB. Ideal for use cases where precise and efficient document search is crucial, with input documents and outputting relevant sections in Markdown format.

Canonical page: https://skillsregistry.net/skills/humbertolvarona-opencode-document-rag-mcp  
JSON: https://api.skillsregistry.net/v1/skills/humbertolvarona-opencode-document-rag-mcp

## Description

Enables local semantic search over PDF, DOCX, PPTX, and EPUB documents by converting them to Markdown, indexing them in ChromaDB, and retrieving complete structure-aware sections with tables and equations.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-09-04

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** search
- **Updated:** 2026-09-04

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/muz7fl6de6)
- **Repository:** <https://github.com/humbertolvarona/opencode-document-rag-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": "humbertolvarona-opencode-document-rag-mcp"
    }
  }
}
```

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