Merge pull request modelcontextprotocol#720 from StreetLamb/feat/update-mcp-agent-entry

docs: update mcp-agent entry to include support for prompts, resources and roots

Author: dsp-ant

docs/clients.mdx

@@ -39,7 +39,7 @@ This page provides an overview of applications that support the Model Context Pr
 | [Klavis AI Slack/Discord/Web][Klavis AI]         | ✅          | ❌        | ✅      | ❓                     | ❌         | ❌    | Supports tools and resources.                                                                   |
 | [LibreChat][LibreChat]                           | ❌          | ❌        | ✅      | ❓                     | ❌         | ❌    | Supports tools for Agents                                                                       |
 | [Lutra][Lutra]                                   | ✅          | ✅        | ✅      | ❓                     | ❌         | ❌    | Supports any MCP server for reusable playbook creation.                                         |
-| [mcp-agent][mcp-agent]                           | ❌          | ❌        | ✅      | ❓                     | ⚠️         | ❌    | Supports tools, server connection management, and agent workflows.                              |
+| [mcp-agent][mcp-agent]                           | ✅          | ✅        | ✅      | ❓                     | ⚠️         | ✅    | Supports tools, prompts, resources, roots, server connection management, and agent workflows.   |
 | [mcp-use][mcp-use]                               | ✅          | ✅        | ✅      | ❓                     | ❌         | ❌    | Support tools, resources, stdio & http connection, local llms-agents.                           |
 | [MCPHub][MCPHub]                                 | ✅          | ✅        | ✅      | ❓                     | ❌         | ❌    | Supports tools, resources, and prompts in Neovim                                                |
 | [MCPOmni-Connect][MCPOmni-Connect]               | ✅          | ✅        | ✅      | ❓                     | ✅         | ❌    | Supports tools with agentic mode, ReAct, and orchestrator capabilities.                         |