INDIVIDUAL MCP TOOL

get_agent_catalog

Return the complete Can Agents Use catalog with all tools, categories, capabilities, use cases, weighted scoreBreakdown, and agent guidance.

canagentsuse.comnone authenticationAvailability not checked

Input schema

{}

Inferred read-only · medium confidence · heuristic, not a guarantee.

No write-capable action terms were found; this is not proof that invocation has no side effects.

CONNECT WITH APPROVAL

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

Codex

~/.codex/config.toml

[mcp_servers.canagentsuse]
url = "https://www.canagentsuse.com/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "canagentsuse": {
      "type": "http",
      "url": "https://www.canagentsuse.com/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: canagentsuse
Remote MCP URL: https://www.canagentsuse.com/api/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": {
    "canagentsuse": {
      "url": "https://www.canagentsuse.com/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "canagentsuse": {
      "type": "http",
      "url": "https://www.canagentsuse.com/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

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

MCP Inspector

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

search_agent_tools — Search Can Agents Use for tools by free text, category slug, capability slug, page, and result limit.
get_agent_tool — Get one Can Agents Use tool record by slug, including weighted scoreBreakdown, evidence, and limitations.
list_agent_categories — List browsing categories in the Can Agents Use catalog.
list_agent_capabilities — List normalized agent affordances such as CLI, API, MCP, browser support, sandbox, and pricing clarity.
get_agent_score_model — Return the weighted signal models used to rank agent friendliness and launch presence.
get_agent_install_guide — Return CLI, MCP, skill, HTTP API, Markdown, and guardrail setup paths for connecting Can Agents Use to an AI agent.