Scira Mcp Chat
- web-chat
A minimalistic MCP client with a good feature set.
About
What is Scira Mcp Chat?
Scira Mcp Chat is an open-source AI chatbot app powered by Model Context Protocol (MCP), built with Next.js and the AI SDK by Vercel. It runs in a web browser and allows users to connect to MCP servers, enabling the AI to access external tools and services through a modern, responsive interface.
How to use Scira Mcp Chat?
To use Scira Mcp Chat, click the settings icon (⚙️) next to the model selector in the chat interface. Enter a name for your MCP server, select a transport type (SSE for remote HTTP servers or stdio for local commands), and provide the required configuration details (e.g., server URL or command with arguments). After adding the server, click “Use” to activate it for the current chat session.
Key features of Scira Mcp Chat
- Streaming text responses with multiple AI provider support
- Full integration with MCP for expanding tools and capabilities
- Multiple MCP transport types (SSE and stdio)
- Built‑in tool integration for extending AI capabilities
- Reasoning model support
- Modern responsive UI with shadcn/ui and Tailwind CSS
Use cases of Scira Mcp Chat
- Connect to Composio MCP for search and code interpreter tools
- Connect to Zapier MCP for access to Zapier automation workflows
- Use any MCP server via stdio transport with npx or python3
- Extend the AI chatbot with custom tools through the MCP protocol
FAQ from Scira Mcp Chat
What makes Scira Mcp Chat different from other AI chatbots?
Scira Mcp Chat natively supports the Model Context Protocol, allowing it to connect to any MCP‑compatible server, and uses the AI SDK by Vercel to support multiple AI providers interchangeably.
Which AI models or providers are supported?
The app is built on the AI SDK by Vercel, which allows multiple AI providers to be used with just a few lines of code. Specific models are not listed, but the architecture supports switching between providers.
How do I add an MCP server?
Click the settings icon (⚙️) next to the model selector, enter a server name, choose between SSE or stdio transport, and fill in the required fields (URL for SSE, command and arguments for stdio). Then click “Add Server” and “Use” to activate it.
Is Scira Mcp Chat free and open‑source?
Yes, it is fully open‑source under the Apache License 2.0. There is no mention of paid tiers or usage limits.
Can I use any MCP server with Scira Mcp Chat?
Yes, you can connect any MCP‑compatible server that supports either SSE or stdio transport. The README provides examples such as Composio, Zapier, and custom servers running via npx or python3.
Details
- Author
- zaidmukaddam
- GitHub stars
- 536
- Category
- web-chat
- Repository
- zaidmukaddam/scira-mcp-chat
<a href="https://mcp.scira.ai">
<h1 align="center">Scira MCP Chat</h1>
</a>
<p align="center">
An open-source AI chatbot app powered by Model Context Protocol (MCP), built with Next.js and the AI SDK by Vercel.
</p>
<p align="center">
<a href="#features"><strong>Features</strong></a> •
<a href="#mcp-server-configuration"><strong>MCP Configuration</strong></a> •
<a href="#license"><strong>License</strong></a>
</p>
<br/>
Features
- Streaming text responses powered by the AI SDK by Vercel, allowing multiple AI providers to be used interchangeably with just a few lines of code.
- Full integration with Model Context Protocol (MCP) servers to expand available tools and capabilities.
- Multiple MCP transport types (SSE and stdio) for connecting to various tool providers.
- Built-in tool integration for extending AI capabilities.
- Reasoning model support.
- shadcn/ui components for a modern, responsive UI powered by Tailwind CSS.
- Built with the latest Next.js App Router.
MCP Server Configuration
This application supports connecting to Model Context Protocol (MCP) servers to access their tools. You can add and manage MCP servers through the settings icon in the chat interface.
Adding an MCP Server
1. Click the settings icon (⚙️) next to the model selector in the chat interface.
2. Enter a name for your MCP server.
3. Select the transport type:
- SSE (Server-Sent Events): For HTTP-based remote servers
- stdio (Standard I/O): For local servers running on the same machine
SSE Configuration
If you select SSE transport:
1. Enter the server URL (e.g., https://mcp.example.com/token/sse)
2. Click "Add Server"
stdio Configuration
If you select stdio transport:
1. Enter the command to execute (e.g., npx)
2. Enter the command arguments (e.g., -y @modelcontextprotocol/server-google-maps)
- You can enter space-separated arguments or paste a JSON array
3. Click "Add Server"
4. Click "Use" to activate the server for the current chat session.
Available MCP Servers
You can use any MCP-compatible server with this application. Here are some examples:
- Composio - Provides search, code interpreter, and other tools
- Zapier MCP - Provides access to Zapier tools
- Any MCP server using stdio transport with npx and python3
License
This project is licensed under the Apache License 2.0 - see the LICENSE file for details.
