# MTA_Plugin

> MTA_Plugin — gru953-mta-plugin. Use this tool when you need to give AI assistants a private and local memory of your files, converting attachments to Markdown and building a searchable knowledge graph. It solves the problem of token-free file access and recall for AI models, supporting various file formats and languages, including English and Bengali. It takes in file attachments and outputs a searchable knowledge graph, ideal for use cases requiring local, deterministic, and model-free file management.

Canonical page: https://skillsregistry.net/skills/gru953-mta-plugin  
JSON: https://api.skillsregistry.net/v1/skills/gru953-mta-plugin

## Description

Give any AI assistant a private, token-free memory of your files — Claude, Gemini, Cursor, VS Code, Windsurf, Codex & Grok. Converts attachments (PDF/Office/EPUB/archives) to Markdown and builds a searchable knowledge-graph memory to recall from. 100% local, deterministic, model-free (no LLM/GPU). Incremental & portable; English + Bengali. MIT.

## Trust

- **Trust score (0–1):** 0.47
- **Verification tier:** scanned
- **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/GRU953/MTA_Plugin)

## 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": "gru953-mta-plugin"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/gru953-mta-plugin` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/gru953-mta-plugin/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
