# Signallama

> lightweight chat interface designed to work seamlessly with your own MCP servers

- **Type:** MCP server
- **Install:** `agentstack add mcp-fbarresi-signallama`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [fbarresi](https://agentstack.voostack.com/s/fbarresi)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [fbarresi](https://github.com/fbarresi)
- **Source:** https://github.com/fbarresi/signallama

## Install

```sh
agentstack add mcp-fbarresi-signallama
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Signallama

Welcome to the **Signallama**, a lightweight and modern chat interface built using SignalR for real-time communication, designed to work seamlessly with your own custom MCP (Model Context Protocol) servers.

## 🚀 Features

- 🔌 Real-time chat powered by SignalR
- 🖥️ Responsive frontend UI
- 🔧 Seamless integration with your own MCP servers (example provided)
- 🗂️ Modular and extensible architecture
- ✅ Lightweight and easy to deploy

## 🧰 Tech Stack

- **Frontend:** JavaScript, HTML, CSS
- **Backend Communication:** [SignalR](https://learn.microsoft.com/en-us/aspnet/core/signalr/introduction)
- **Server Integration:** [MCP](https://github.com/modelcontextprotocol/csharp-sdk)

## 📦 Getting Started

### Prerequisites

- [Ollama](https://ollama.com/)
- .NET Core SDK
- MCP Server setup (optional - your own implementation)

### Configure your MCP in `appsettings.json`

Input your SSE Server or Stdio in the section McpSettings: 

````json
"McpSettings": {
    "Sse": [
      {
        "Endpoint": "https://localhost:7170",
        "UseStreamableHttp": true,
        "Name": "MyServer",
        "ConnectionTimeout": "00:00:10"
      }
    ]
  }
````

or for example using external project over stdio:
````json
"McpSettings": {
    "Sse": [
      {
        "Endpoint": "https://localhost:7170",
        "UseStreamableHttp": true,
        "Name": "MyServer",
        "ConnectionTimeout": "00:00:10"
      }
    ],
    "Stdio" : [
        "Name": "MyStuff",
        "Command": "npx",
        "Arguments": ["-y", "--verbose", "@modelcontextprotocol/server-everything"],
    ]
  }
````

### Start the project

1. start your MCP server (or use the provided one signallama.mcp)
1. start the frontend with signallama.web
1. enjoy your lightweight environment!
  

## 🤝 Contributing

Contributions are welcome! Please fork the repo and submit a pull request. Feel free to open issues for bugs, suggestions, or features.

## 📄 License

This project is licensed under the MIT License.

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [fbarresi](https://github.com/fbarresi)
- **Source:** [fbarresi/signallama](https://github.com/fbarresi/signallama)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-fbarresi-signallama
- Seller: https://agentstack.voostack.com/s/fbarresi
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.