# CVAT MCP

> Use this tool when you need to streamline task management, project operations, and annotation handling in Computer Vision Annotation Tool (CVAT) using natural language interaction. It solves problems related to manual annotation and project management by providing a convenient interface to the CVAT REST API. Ideal for use cases where efficient and automated annotation workflows are required, it accepts natural language inputs and outputs corresponding CVAT actions.

Canonical page: https://skillsregistry.net/skills/jangjs1216-cvat-mcp  
JSON: https://api.skillsregistry.net/v1/skills/jangjs1216-cvat-mcp

## Description

Enables natural language interaction with CVAT (Computer Vision Annotation Tool) for task management, project operations, and annotation handling via the CVAT REST API.

## Trust

- **Trust score (0–1):** 0.94
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** productivity
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/x81bx6buaz)
- **Repository:** <https://github.com/jangjs1216/CVAT-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": "jangjs1216-cvat-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jangjs1216-cvat-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jangjs1216-cvat-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