Skip to main content
Glama
README.md
# ๐Ÿ›ก๏ธ MCP Agent Sentinel (`mcp-agent-sentinel`)

> **Real-time Proactive Sentinel & Breaking-Change Intelligence Server for Autonomous AI Agents**  
> *Compatible with Cursor IDE, Hermes, Claude Desktop, LangChain, AutoGen, and Windsurf*

[![Smithery Verified](https://img.shields.io/badge/Smithery-Verified-blue.svg)](https://smithery.ai/server/rmicael)
[![Glama Listed](https://img.shields.io/badge/Glama-Listed-emerald.svg)](https://glama.ai/mcp/servers/rmikael7/mcp-agent-sentinel)
[![MCP Protocol Spec](https://img.shields.io/badge/MCP-2026.1_Spec-purple.svg)](https://modelcontextprotocol.io)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)

---

## ๐Ÿ“Œ Why MCP Agent Sentinel?

Most AI agents rely on **reactive search APIs** (like Tavily or Exa) where the agent has to *guess* what to search for. If an SDK introduces a breaking change or deprecates an API parameter, your agent won't know until your production code breaks.

**MCP Agent Sentinel** is a **proactive context server** that continuously monitors ArXiv, GitHub Repositories, SDK Release Notes (MCP, OpenAI, Anthropic, Google), and Web sources. It injects clean, pre-classified intelligence and breaking change alerts directly into your agent's context window before issues occur.

---

## ๐Ÿ› ๏ธ MCP Tools Exposed

| Tool | Description | Key Parameters |
|---|---|---|
| ๐Ÿšจ `get_latest_news` | Real-time technical news, releases & breaking change alerts | `category`, `persona`, `timeframe`, `limit` |
| ๐Ÿ” `search_ai_news` | Fast full-text semantic search on the curated live feed | `query`, `persona`, `limit` |
| ๐Ÿ“Š `get_niche_digest` | Executive markdown briefing for sub-niches (e.g. AI Engineering) | `niche`, `persona`, `format` |
| ๐Ÿ“ก `get_sources_status` | Live health, timestamp & processing metrics of all scrapers | N/A |

---

## ๐Ÿ‘ฅ Persona-Based Context Filters

Data is automatically indexed and served according to consumer personas:

- ๐Ÿ› ๏ธ **`dev`**: Code diffs, breaking changes, SDK updates (`@modelcontextprotocol/sdk`), deprecations & bug fixes.
- ๐Ÿ“Š **`product`**: Pricing matrices, token efficiency, LLM benchmarks & feature availability.
- ๐Ÿ“ˆ **`investor`**: Frontier ArXiv research papers, agentic framework adoption & cloud distribution deals.
- ๐Ÿ“ฃ **`creator`**: Trending GitHub repos, viral AI tools & hooks for newsletters/youtube.

---

## โš™๏ธ Client Setup Configurations

### Option 1: Zero-Install Cloud Endpoint (Smithery 24/7)

Connect directly to the hosted server without running local Node.js processes:

- **Smithery Server URL:** `https://mcp.smithery.run/rmicael`

```json
{
  "mcpServers": {
    "mcp-agent-sentinel": {
      "url": "https://mcp.smithery.run/rmicael"
    }
  }
}
```

---

### Option 2: Run via NPX (Recommended for Local Dev)

#### 1. Claude Desktop App Setup
Locate your Claude Desktop configuration file:
- ๐ŸชŸ **Windows:** `%APPDATA%\Claude\claude_desktop_config.json`
- ๐ŸŽ **macOS:** `~/Library/Application Support/Claude/claude_desktop_config.json`

Add `mcp-agent-sentinel`:

```json
{
  "mcpServers": {
    "mcp-agent-sentinel": {
      "command": "npx",
      "args": ["-y", "mcp-agent-sentinel@latest"]
    }
  }
}
```

#### 2. Cursor IDE Setup
Add under **Cursor Settings -> Features -> MCP Servers**:

- **Name:** `mcp-agent-sentinel`
- **Type:** `command`
- **Command:** `npx -y mcp-agent-sentinel@latest`

#### 3. Antigravity IDE & Hermes Setup
Add to your `~/.gemini/config/mcp_config.json` or `~/.hermes/config/mcp_config.json`:

```json
{
  "mcpServers": {
    "mcp-agent-sentinel": {
      "command": "npx",
      "args": ["-y", "mcp-agent-sentinel@latest"]
    }
  }
}
```

---

### Option 3: Build from Source

```bash
# 1. Clone repository
git clone https://github.com/rmikael7/mcp-agent-sentinel.git
cd mcp-agent-sentinel

# 2. Install & Build
npm install
npm run build

# 3. Add to your MCP config using the built file:
# command: "node"
# args: ["/path/to/mcp-agent-sentinel/dist/index.js"]
```

---

## ๐Ÿงช Interactive Live Demo

Test the live feed parser right from your terminal:

```bash
# Interactive Persona Visualizer
npm run demo

# Verify Cursor/IDE Setup
npm run verify-cursor
```

---

## ๐Ÿ“„ License & Maintainers

- **Repository:** [github.com/rmikael7/mcp-agent-sentinel](https://github.com/rmikael7/mcp-agent-sentinel)
- **Glama.ai Hub:** [glama.ai/mcp/servers/rmikael7/mcp-agent-sentinel](https://glama.ai/mcp/servers/rmikael7/mcp-agent-sentinel)
- **Smithery Cloud:** [smithery.ai/server/rmicael](https://smithery.ai/server/rmicael)
- **Maintainers:** Agent Principal Core Team
- **License:** MIT License

TDQS

A3.5/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: one generates executive briefings for niches, the other returns source status. No overlap.

Naming Consistency5/5

Both tools use the consistent verb_noun pattern with 'get_' prefix, following a predictable convention.

Tool Count2/5

With only 2 tools, the server feels severely under-scoped for a name implying 'Agent Sentinel' (monitoring agents). Expected more tools for a monitoring/management domain.

Completeness2/5

The tool surface is very thin: missing essential monitoring operations (e.g., list agents, pause/resume, view alerts). The niche digest tool seems out of place for a sentinel.

Maintenance

ActivityInactive
ResponsivenessNo issues