# docsonar

> docsonar — ribhav-jain-docsonar. Use this tool when you need to efficiently search and interact with local documents using a combination of keyword and semantic search. Docsonar solves the problem of information overload by indexing folders and allowing users to chat with their documents via MCP clients. It takes in folders and document content as input and provides relevant search results and document summaries as output.

Canonical page: https://skillsregistry.net/skills/ribhav-jain-docsonar  
JSON: https://api.skillsregistry.net/v1/skills/ribhav-jain-docsonar

## Description

A local document search MCP server that indexes folders and provides hybrid keyword+semantic search, enabling users to chat with their documents via MCP clients like Claude Desktop or Claude Code.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** search
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/lcmvwq0qmx)
- **Repository:** <https://github.com/ribhav-jain/docsonar>

## 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": "ribhav-jain-docsonar"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ribhav-jain-docsonar` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ribhav-jain-docsonar/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