Scira Chat MCP Server

Chat interface for MCP servers using HTTP and SSE transports.

Data last scanned yesterday · Reviewed today

37★ 827TypeScriptApache-2.0

Overview

Scira Chat is an open-source AI chatbot built with Next.js and Vercel's AI SDK. It provides a dedicated interface for managing and interacting with various Model Context Protocol servers directly from your browser. By utilizing the app's settings menu, you can connect to external MCP providers via HTTP or Server-Sent Events (SSE) to extend the chatbot's native capabilities. The application features a modern UI powered by Tailwind CSS and shadcn/ui. It supports reasoning models and allows users to swap between different AI providers for responses. Once a server is configured with a URL, users can enable it for active chat sessions to leverage specialized tools provided by external integrations like Composio, Zapier, or Hugging Face.

Our verdict

With a security score of 37/100, this server carries a high risk level. The score reflects that the repository is community-maintained rather than vendor-official and has not undergone editorial security review, meaning users should exercise caution regarding its integration into sensitive environments. It is best suited for experimental use by developers looking to test MCP server configurations via HTTP or SSE.

Supports both HTTP and SSE transport protocols
Integrates with Vercel's AI SDK for streaming responses
Licensed under the Apache-2.0 open source license
Provides a modern UI built with Next.js and Tailwind

Last code commit occurred over 238 days ago
Lacks an official vendor-backed security audit
Authentication methods have not been editorially reviewed

Setup

Claude Desktop

{
  "mcpServers": {
    "scira-mcp-chat": {
      "args": [
        "-y",
        "mcp-chat"
      ],
      "command": "npx"
    }
  }
}

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows), then restart Claude Desktop. Some servers require API keys or tokens as environment variables — check the project's README and add an "env" object if needed.

No read-only mode — running this grants full read/write access.
No built-in authentication — anyone with access to this config can invoke every tool it exposes.

Compatibility

Client	Local	Docker	Remote	Read-only
Claude Desktop
Cursor
VS Code
Windsurf
ChatGPT

Frequently asked questions

›Which transport types does Scira MCP Chat support?

The application supports both HTTP and SSE (Server-Sent Events) transport types for connecting to remote MCP servers.

›How do I add an MCP server to the application?

You can add and manage servers by clicking the settings icon next to the model selector in the chat interface, providing a name and URL, and then clicking 'Add Server'.

›Is it required to manually enable a server after adding it?

Yes, you must click 'Enable Server' in the settings menu to activate the server for your current chat session.

›Does Scira support reasoning models?

Yes, the application includes support for reasoning models.