# mcp

> mcp — atlaso-labs-mcp. Use this tool when you need to access a shared, persistent memory across multiple AI tools, enabling seamless integration and data consistency. It solves problems of data fragmentation and tool isolation, providing a unified memory interface for all connected AI tools. With a simple API endpoint at https://mcp.atlaso.ai/mcp, you can input and output data, leveraging git capabilities for version control and collaboration.

Canonical page: https://skillsregistry.net/skills/atlaso-labs-mcp  
JSON: https://api.skillsregistry.net/v1/skills/atlaso-labs-mcp

## Description

Atlaso's hosted MCP server — one shared, persistent memory across every AI tool you connect. Endpoint: https://mcp.atlaso.ai/mcp

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/atlaso-labs/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": "atlaso-labs-mcp"
    }
  }
}
```

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