Developer Tools

claudeatlas.com

Searches and retrieves information about Claude skills and MCP servers from a catalog.

1 endpoint3 known toolsFirst detected August 15, 2026Last detected August 15, 2026

ENDPOINT 1

https://claudeatlas.com/mcp

No auth detected

Capabilities

tools

Server instructions

Search the ClaudeAtlas catalog with search_skills, fetch one record with get_skill, and list the 8 catalog categories with get_categories.

Semantic search over the ClaudeAtlas catalog of Claude skills, plugins, and MCP servers.

Inferred read-only

Fetch one catalog record by slug.

Inferred read-only

List the 8 catalog categories.

Inferred read-only

CONNECT WITH APPROVAL

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.claudeatlas]
url = "https://claudeatlas.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "claudeatlas": {
      "type": "http",
      "url": "https://claudeatlas.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: claudeatlas
Remote MCP URL: https://claudeatlas.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "claudeatlas": {
      "url": "https://claudeatlas.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "claudeatlas": {
      "type": "http",
      "url": "https://claudeatlas.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "claudeatlas",
  "transport": "streamable-http",
  "url": "https://claudeatlas.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

BuiltWith Trust API v2 evidence for claudeatlas.com was fetched 2026-08-24T07:45:58.779Z.

Trust status Neutral

claudeatlas.com is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.